ELF>@8@8 @xxQtd==KKPtd"", ""00Rtd""$$''00XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX p  ii  f  ui  X @P&y T&y  `Z'  ? 0ӯk t) N ui  @"H"PP"PX"`"`""." """""" ".#+#. #.0#-@#|.P#,`#x.p##.#,#,#+#+#t.# .#p.$.$H$ $.0$(@$(P$p*`$(p$"$8$$+$,$&$%$%$%$(%+%( %h*0%`*@%($P%$`%-p%,%+%+%X*%+%%%%%(%@ &&- &,0&$@&( P&,`&,p&,&,&h.&+&#&+&%&+&+'%'( 'P*0'H*@'@*P'8*`'0*p','-'b.'-'(*','-'+'^.(,(( (0(@(P("`("p("("(((!(("( ( )) )0)`@)x(P)%`)-p)-),)-)-),),)-)+)x%*-*, *,0*h(@* *P*-`*~,p*X(*h%*!*"***H(*-*x,*++++|+ +u+0+p@+*P+*`+8(p+)+((+r,+n++g++`+++`+,!, ,`0,Y+@,.P,Z.`,.p,V.,(,R+,-,x!,#,h!,X!,H!-8!-) -)0-#@-K+P-l,`-D+p-=+-(!-X%-.-(-#-R.-.-..... .N.0..@.J.P..`.F.p.B..-.6+.>..-.:..-./+../)/' /)0/#@/)P/.`/6.p/(+/'//#/#/#/x#/H%/ +0'0f, 0)008%@0'P0@`0'p0`,0-0-0-0(%0%0x"001p1` 1h"01+@1%P1X"`1H"p1$1+1p-1Z,1*1*1)1)1h#2X#2` 28"02H#@28#P2$`2@p2 2)2@2'2)2*2!2!2*3x)3(# 3#03$@3h)P3 `3'p3X)3*3 3 3*3$3$3'3x'4h'4X' 4H'04H)@4i-P4T,`4$p4$4$4.48'4('4N,444'5("5* 5'05"@5&P5"`5*p5&5H,5&5@)5d-5_-5Z-5U-5B,6<,6* 6P-062.@66,P60)`6&p6!6*6&6!6&6!6 6..6&7*70, 7*,07&@7*P7 `7$,p7!7,7@777`7K-7#7x&8*8@ 808 @8 P8*`8F-p8,8h&8,8 8 8 8A-8()8X&9x$9H& 98&098-@9 )P90`9*p9(&9 9 9x 99h 99X 9: ,:& :)0:@:*P:`:p::,:(-:):h$:X$:+::-;-; ;!0;)@;+P;.`;.p;.;.;*.;-;+;; ;;;<X=<P=<@=< = <=(<<0<<8<@<@<<H<;P<@;X<:`<:p<<h<<<<pGGGGGHGXGJGG@HHHH`I(HX@HHHeHHHH`I%hI pIPI.I IPI6I@HII@I@HIJIJJ(JV0J8J0PJ`XJ`J0xJiJJvJJJJJK K@KHKhKpKHxKKKHKKKKKK@KLL`LxLLLLLL MM HHM`M`OhMMMoMMM"NN N(N@N HN+XN@`NhNxNN N N N N N/ NA NT NNa Nm h<x<>>>>>>???,?: ?;(?D0?Z8?]@?^H?iP?lX?m`?uh?{p?}x????????????????N@ @(@0@8@@@H@P@ X@ `@ h@ p@ x@@@@@@@@@@@@@ @!@"@#@$A%A&A'A( A)(A*0A+8A,@A-HA.PA/XA0`A1hA2pA3xA4A5A6A7A8A9A<A=A>A?A@AAABACAEAFAGBHBIBJBK BL(BM0BN8BO@BPHBQPBRXBS`BThBUpBVxBWBXBYB[B\B_B`BaBbBcBdBeBfBgBhBjBkCnCoCpCq Cr(Cs0Ct8Cv@CwHCxPCyXCz`C|hC~pCxCCCCCCCCCCCCCCCCCDDDD D(D0D8D@DHDPDXD`DhDpDxDDDDDDDDDDDDDDDDDEEEE E(E0E8E@EHEPEXE`EhEpExEEEEEEEEEEEEEEEEEFFFF F(F0F8F@FHFPFXF`FhFpFxFFFFFFFFFFFFFFFFFGGGG G(G0G 8G @G HHݿHt H5%@%h%ڿh%ҿh%ʿh%¿h%h%h%hp%h`%h P%h @%h 0%h %zh %rh%jh%bh%Zh%Rh%Jh%Bh%:h%2h%*hp%"h`%hP%h@% h0%h %h%h%h%h %ھh!%Ҿh"%ʾh#%¾h$%h%%h&%h'p%h(`%h)P%h*@%h+0%h, %zh-%rh.%jh/%bh0%Zh1%Rh2%Jh3%Bh4%:h5%2h6%*h7p%"h8`%h9P%h:@% h;0%h< %h=%h>%h?%h@%ڽhA%ҽhB%ʽhC%½hD%hE%hF%hGp%hH`%hIP%hJ@%hK0%hL %zhM%rhN%jhO%bhP%ZhQ%RhR%JhS%BhT%:hU%2hV%*hWp%"hX`%hYP%hZ@% h[0%h\ %h]%h^%h_%h`%ڼha%Ҽhb%ʼhc%¼hd%he%hf%hgp%hh`%hiP%hj@%hk0%hl %zhm%rhn%jho%bhp%Zhq%Rhr%Jhs%Bht%:hu%2hv%*hwp%"hx`%hyP%hz@% h{0%h| %h}%h~%h%h%ڻh%һh%ʻh%»h%h%h%hp%h`%hP%h@%h0%h %zh%rh%jh%bh%Zh%Rh%Jh%Bh%:h%2h%*hp%"h`%hP%h@% h0%h %h%h%h%h%ںh%Һh%ʺh%ºh%h%h%hp%h`%hP%h@%h0%h %zh%rh%jh%bh%Zh%Rh%Jh%Bh%:h%2h%*hp%"h`%hP%h@% h0%h %h%h%h%h%ڹh%ҹh%ʹh%¹h%h%h%hp%h`%hP%h@%h0%h %zh%rh%jh%bh%Zh%Rh%Jh%Bh%:h%2h%*hp%"h`%hP%h@% h0%h %h%h%h%h%ڸh%Ҹh%ʸh%¸h%hSHHPHT$0HL$8Ht$(LD$@LL$HHT$`HL$ D$HT$HL$HtBLPLL$H׹1҃/w ΃LHHLA0tA0MHH9uHP[AWAVIAUATUHSQHGHHtIIMHH8u HnLH51H81JH(HHu 1E1E11J/IHtH5H8IHt"LH1#HHtHH11H貸L誸L袸HTIZL[]A\A]A^A_AWIAVI E1AUIfAATMUSHH8HT$ HHHL$ЃLL$(HHT$D$QHLHT$LL$(H1H9}IttHtHHHLIHuE1E1E1LAIHtCt?1E1?%?D$IHHIHL$1LIHHI E1HL$HHH254ATASt$ t$(t$HPPAUPPAWH`IHt ǀLLHExHHEuHfHnHL%UflfHnH(~ fl)H;HtdC t/@t2sHc$t1I5nsHcHtKHEHHt:HH1'H0IH* HHuE1L%!1HHtԿHHtHۺHtHͺHtHHxlHH^RHHD 8HH* HwH9HE1E1L% LAL9H=a tMH=ttLH=!4?]H=8 HtAH( Hx/HHu'D HuHH53H8B1H= CH51HH/HH551HHExHHEuHH=_H1H5H9H=urHH$H-H5H=/ *H52HHtH=5dHg HH52HoGH=ΫdH¸H)H=}dHH H=adHzHH ¶H1H5ŵHHH H1H5HتHJHH~H 7HIL$H=&QLwL(}f( ])$f )$H`HHILH +HH=PLs(( hf/f V((f߫fH$ )$)$)$)$RH©H (rH ۮIL!fm)HRLH=O)$H|HH,ILH HH=OL"H$H>Ht}( H ILyfm 9H³LH=PO(fh)$)$\HHtHExPHHEuGH=HEPHHECHE1E1L%6H=SHHPAHH H5[HGH!HExHHEuH}H=HHA HHH5HHAH HH{H5hHĦHA0HHSH57HH]AHH,H5fHrH,AHHH55HIHAHHH5H HAHHH5sHHAHHH5BHΥHhAHHNH5qHH7AHH#H5@H|HAHHH5HSHAHHH5~H*HAHHH5MHHtwAHHH5 HܤHtJAHHw&H5SHHtHEx9HHEu0Hy&1HE1E1L%]H=HHsHH5HUHH5H7HH5HlHH5HNHbH5H0H<H5HHH5HHH5HHH5HeHH5HGH~H5H|)HXH5H^ H2H5H@H H5H"HH5HHH5HHH5HuHtH5HWHNH5H9H(H5HnHH5HP HH5H2 HH5H HH5H HjH5H HDH5Hg HH5W7HI HH5a7H~+ HH5k7H` HH5u7HB HH5H$ H`H5H H:H5H HH5 Hw HH5 HY HH5H; HH5Hp H|H5HR HVH5H4 H0H5H H H5H HH5H HH5Hi HH5HK HrH5H- HLH5Hb H&H5HD HH5H& HH5c5H HH5m5H HH5Hy HhH5H[ HBH5H= HH5Hr HH5~HT HH5yH6 HH5uH HH5oH H^H5jH H8H5i4Hk HH5LHM HH5M4H/ HH5.Hd HH5&HFHzH54H(HTH54H H.H5HHH5H{HH5H]HH5H?HH5Ht!HpH5HVHJH5H8H$H5HHH5HHH5HHH5HmHH5HOHfH52H1H@H52HfHH5aHHHH5ZH*HH5TH HH5LHHH5EH}H\H5<H_H6H54HAHH51Hv#HH5/HXHH5,H:HH5*HHxH5#HHRH5HH,H5HoHH5HQHH5 H3HH5HhHH5HJHnH5H,HHH5HH"H5HHH5HHH5HaHH5HCHH5Hx%HdH5HZH>H5H<HH5HHH5HHH5HHH5HqHH5HSHZH5H5H4H5HjHH5HLHH5H.HH5HHH5HHvH5|HHPH5qHcH*H5fHEHH5[Hz'HH5PH\ HH5EH>HH5:H HlH5/HHFH5&HH H5HsHH5HUHH5H7HH5HlHH5HNHbH5H0H<H5HHH5HHH5HHH5HxiHH5HxOHH5Hx5HdH5HjxHEx7HHEu.H$HE1E1SL%H=THHtnH5Hx]HExHHEuHbH=PHHt.H5HxHEx9HHEu0H"&1HE1E1請L%QHDŽ$L$L$HDŽ$H$HDŽ$HDŽ$HDŽ$HDŽ$LLHHxhIH=IHu4HH8VH=xIH9H5}LHIxHIuLHL5L9st:HjH5)H8HHHH1HHHxHHuHHpHuHH5H8q=HBv&H5)HH81;"HH5)H81 HÅuHiH5*H8tHIH5*H8H$PH$HDŽ$7H$HDŽ$HDŽ$HDŽ$HDŽ$HDŽ$HDŽ$HDŽ$LLHHxhIH=&IHH`I}`H0`H0*H=9@H$H$LH$gL%cA$tA$HXH$LHHDŽ$H$HI$xHI$uL6Ht!HHExHHEuHIEhE1E1H$L$L$H8HyLqLL%/$bH$UH$HH$;14H(H=O?H}H8uH+~H5)H8lkH=jIHtH5L菿HI$xHI$uLHuH}H5H8L9utE1L% *E1L%E1L%E1L%E1L%E1L%E1L%E1L%E1L%mE1L%Y vE1L%E bE1L%1RNE1L%R:E1L%1$L^H /H=ȀHH5:SIHt8H5VH-7rI9ouHNLL:!LL L%IExHIEuL3L̂H H=H_H5IHt1H5$I9ouHNHL觳2HLw"L%L%IExHIEuL菶L0H H=JHH5IHH5tI9ouHNHLHLʸIExHIEuL HzH=pH$HHDŽ$H$HVL$H$1IOyMjH5H=L]IExHIEuLoIxHIuLXHR5M5O555]5_555ł555[5M575)5˂5݂5ς5555W5y5k5u5W5A555gP55B5555څ5̅55x555ޅ5Ѕ55܄5΄55ҁ5ԋ555Z5D5655"55Ή555555r5d5555Ĉ55555~5p555v5h5Z5L5>505"5555҅55N5@55܄5΄5555v5P525$55555փ5ȃ55 55؂5ʂ5P15;55ׁ5Ɂ55=5~5~5~5~5g~5Y~5Ã5ŀ55A5c555555575 555555Ň5w5a5S5E575)555w5Q5C5555ۅ555y5k5]5τ55555 5S5E5'55 555i5[5M5555݀5π5y5k5]5O5155555555y5k5]5O5A535%55~5~5~5~5y~5k~5]~5O~5}5}5}5}5q}5c}5U}5G}5!}5}5}5|L H|5|L3|5|H |5|H |5k|H5{5|AH@IHH5{H=zHIxHIuLyHr1H-ZH$H fHnHfHnA%eH-8AH5;)%tHH=j)$$H?HH9HjH5HQH QfHnHPflHHj)PIH HH5*{H= yHIxHIuLt(<$H!H-H +HfHnAA)=,HH5H=HHHHjHHQH QfHnڹHPflHHj)PIH HH5GzH= xHIxHIuL艭($$H&H-H H fHnAA)%HH5H=HHHHjHHQH TQfHnHBPflH~Hj)6PIH H1H5yH=5wH 'IxHIuL螬(4$H+H-lH HfHnAA)5HH5LH=H^H9HXHjHTHQH yQfHnHPflH3Hj)PIH HnH5xH=JvH"dIxHIuL賫($H0H-!H JHfHnAA)KHH5H=:HHYH HjH HQH QfHnHPflHHj)PIH HH5wH=_uH7IxHIuLȪ(,$H5H-H HfHnAA)-HH5H=HHyHHjHHQH QfHnHaPflHHj)UPIH HH5vH=ttHLIxHIuLݩ(<$H:H-H HfHnAA)=HH5kH=H}HHwHjHsHQH QfHnҹHPflHRHj) PIH H%H5vH=sHaIxHIuL($H?H-@H iH"fHnAA)jHH5 H=YH2HH,HjH(HQH QfHnHPflHH0j)PIH HbH5EuH=rHvXIxHIuL(,$HDH-H H'fHnAA)-HH5H=HHHHjHHQH :QfHnHPflHHEj)tPIH HH5btH=qH苤IxHIuLH5pH(L-' fHnH fInAHflHfHnHHQH A)l$@fHnH5VH?jflH=QPH\HeHNj)-])PH IHH5sH=pH荣IxHIuLHgp(d$@jH yHCfHnK AHVAH59H=bHKHQH 8QfHnHPflHH#Hlj)%)PH IHH5rH=oH諢IxHIuL~=TH H0fHnAA=SH H5H=HHQ)|$ fHnHjflAVHPHj f )=ǹ)PH IHH5FmH=fHיIxHIuLh($H5L%H ߸HfHnAA)HH5H=ϸHHHHjHHQH QfHnHAPflH}Hj)5PIH HH5lH=fHIxHIuL}(,$H:L%kH HfHnAA)-HH5KH=H]H HWHjHSHQH QfHnHPflH2Hj)PIH HH5kH=)eHIxHIuL蒚HkM(|$@jH MHgAVfHnAPAH5 H=DHH&HQfHnH HʵH flHj )=)PH IHiH5kH=MdH%_IxHIuL趙HNH H(L$@L55 jfHnAAVAH5ɴH=H۴HHQPfHnHHflHĴH ji ) )kPH IHH5jH=jcHBIxHIuLӘHM(d$@jH γHAVfHnAPAH5H=ųHHHQfHnHHKHflH1j- )%v)/PH IHH55jH=bHfIxHIuLH(t$@jH HAVfHnAPAH5PH=HbHkHQfHnHNHHPflHUj )5:)PH IHFH5iH=aH芔<IxHIuL($L%BH YAHHfHnAL%H5 H=E)>HHHHHjH HQH gQfHnʹHPflHHRj)PIH H|H5hH=`H蘓rIxHIuL)($HƽL%ׯH HfHnAA)HH5H=HɯHHïHjHHQH QfHnHbPflHHgj)VPIH HH5gH=_H譒IxHIuL>(,$H˼L%H HfHnAA)-HH5lH=H~H%HxHjHtHQH QfHnHPflHSH|j) PIH HH5fH=^H‘IxHIuLS(<$HлL%AH jHfHnAA)=kHH5!H=ZH3HFH-HjH)HQH NQfHnҹH̬PflHHj)PIH H3H5eH=]Hא)IxHIuLh( $HպL%H HfHnAA) HH5֫H=HHgHHjHޫHQH QfHnڹHPflHHj)uPIH HpH5 eH=]HfIxHIuL}Hְ(d$@jH تHAVfHnAPAH5H=ϪHHHQfHnHHUHflHۺj7 )%)9PH IHH57dH=8\HIxHIuL衑(4$HL%oH HfHnAA)5HH5OH=HaHH[HjHWHQH QfHnHPflH6H߹j)PIH HH5LdH=M[H%IxHIuL趐($HL%$H MHfHnAA)NHH5H==HHHHjH HQH )QfHnʹHPflHHj)PIH H6H5icH=bZH:,IxHIuLˏH$ HӦ H fHnHf fHncFAA)HH5H=צ)T$`HHHHjHHQH 6QfHnHDPflHHj)8PIH HSH5fbH=WYH/IIxHIuL(l$`Hj H f^ HõfHnA)-HAH5AH=zHSHHMHjHIHQH 6QfHnHPflH(Hj)PIH HH5vaH=_XH7yIxHIuLȍ(<$HL%H ?HȴfHnAA)=@HH5H=/HHHHjHHQH +QfHnҹHPflHݣHj)PIH HH5`H=tWHLIxHIuL݌( $L%Z8H AHֳHdzfHnAL%H5H=) HHH1HHjHHQH QQfHnڹHOPflHHj)CPIH HH5_H=VHZIxHIuL($$HL%yH H˲fHnAA)%HH5YH=HkHRHeHjHaHQH ~QfHnHPflH@H)j)PIH H3H5^H=UHo)IxHIuL(t$`H* H Sf HñfHnA)5QHAH5H=:HHeH HjH HQH QfHnHPflHH1j)PIH HcH5]H=THwYIxHIuL(T$`HҞ H fƞ HfHnA)HAH5H=HH~HHjHHQH QfHnʹHTPflHH9j)HPIH HH5\H=SHIxHIuL(\$PL54f H HůHfHnAL5TAH5WH=)HH_HHYHjHUHQH rQfHnHPflH4H=j)PIH HH5[H=RH胅IxHIuL(,$HѮL%"H KHfHnAA)-LHH5H=;HHHHjH HQH wQfHnHPflHHRj)PIH HH5[H=QH蘄IxHIuL)(<$H֭L%ךH HfHnAA)=HH5H=HɚHHÚHjHHQH TQfHnҹHbPflHHgj)VPIH H9H5,ZH=PH譃/IxHIuL>(L$PHڬL5H f HfHnA) HAH5bH=HtHHnHjHjHQH QfHnڹH PflHIHrj)PIH HlH5?YH=OH踂bIxHIuLI(d$PHիL56H _f. HfHnA)%]HAH5 H=FHHHHjHHQH QfHnHPflHH}j)PIH HH5RXH=NHÁIxHIuLT(4$HѪL%H HfHnAA)5 HH5–H=HԖH!HΖHjHʖHQH QfHnHmPflHHj)aPIH HܽH5oWH=NH؀ҽIxHIuLi($H֩L%H HfHnAA)HH5wH=HHDHHjHHQH QfHnʹH"PflH^Hj)PIH HH5VH=MHIxHIuL~($L%-H |AHǨHfHnAL%&H5/H=h)aHH7H`H1HjH-HQH QfHnHГPflH Hj)ēPIH HOH5UH=#LH~EIxHIuL茁(l$`Hا H f HfHnA)-HAH5͒H=HߒHqHْHjHՒHQH QfHnHxPflHHj)lPIH HH5TH=+KH~uIxHIuL蔀(|$`HЦ H Ǒf HfHnA)=őHAH5uH=HHHHjH}HQH QfHnҹH PflH\HŨj)PIH HH5SH=3JH }IxHIuL( $HɥL%JH sHfHnAA) tHH5*H=cH<HH6HjH2HQH QfHnڹHՏPflHHڧj)ɏPIH HH5SH=HIH |IxHIuL~($$HΤL%H (HfHnAA)%)HH5ߎH=HHHHjHHQH QfHnHPflHƎHj)~PIH H)H5$RH=]HH5{IxHIuL}(t$`Hң H ٍf HfHnA)5׍HAH5H=HHHHjHHQH QfHnH2PflHnHj)&PIH HYH54QH=eGH=zOIxHIuL|(T$`HʢX H fL HfHnA)HAH5/H=hHAHH;HjH7HQH QfHnʹHڋPflHHj)΋PIH HH5DPH=mFHEyIxHIuL{($HáL%H -HfHnAA).HH5H=HHHHjHHQH yQfHnHPflHˊHj)PIH HƶH5OH=EHZxIxHIuLz(,$HȠL%H HfHnAA)-HH5H=҉HH3HHjHHQH QfHnHDPflHH)j)8PIH HH5NH=DHowIxHIuLz(<$H͟L%nH HfHnAA)=HH5NH=H`HRHZHjHVHQH QfHnҹHPflH5H>j)PIH H@H5MH=CHv6IxHIuLy( $HҞL%#H LHfHnAA) MHH5H=<HHqHHjH HQH QfHnڹHPflHHSj)PIH H}H5LH=BHusIxHIuL*x($$H#H AHfHnAH5ɅHHH=)%HHÅHHHjHHQH QfHnHdPflHHaj)PPIH HH5KH=AHtIxHIuL8wHH ڄjAHۄHAHHHH5H H H=QPHHjf]PIH HH53MH= AHsIxHIuLuv(t$PL%!f H ɃHHfHnAL%yAH5|H=)5HHH H~HjHzHQH QfHnHPflHYHj)PIH HDH5gLH=@Hr:IxHIuLyu(T$PHL%FH of> HߚfHnA)mHAH5H=VH/H"H)HjH%HQH QfHnʹHȁPflHHj)PIH HwH5zKH=?HqmIxHIuLt(\$PHL%H f HڙfHnA)HAH5ȀH=HڀH;HԀHjHЀHQH EQfHnHkPflHHj)gPIH HH5JH=&>HpIxHIuLsHhH1L%s H fHnH@HHfHnHQH *fHnHbHQ)\$0flL5 AjAH~H5H H iH=JQPHHH&HjL5.L%~))~PH IHH5wIH=<HoIxHIuLarHj?(|$0jHLH }H}AAH}fHnHQH H}H@fHnH5}H }H flHc}QH=}PH}H}H}HjL5}L%)}*} )=}),}PH IHH5rHH=;HnIxHIuLTqH>(L$0jH_H h|Hq|AAHn|fHnHQH H:|H>fHnH5|H |H flH{QH=6|PH|H |H|HjL5|L%{{ ) {){PH IHڭH5uGH=:HmЭIxHIuLGp(d$ Hz H zfz fHnAA)%zHH5zH=zHzH HzHjHzHQH lQfHnHbzPflHzHj)NzPIH HH5 GH=9HlIxHIuLVoHH yjL%_H yH AAQHyH5yHyHHH=yPHyHŗjL%yRy  Oy PH IHnH5QFH="9HkdIxHIuLnHDaH xjAH xH AHxQH5xH=xHxHPHxHjL%x^x  [x PH IHҫH5EH=^8H6kȫIxHIuLmHxH wjAH wH AHwQH5wH=wHwHPHwH=jL%wrw  ow PH IH6H5DH=7Hrj,IxHIuLmH\:(t$ jH vHmfHnHvAHvHQH [ AQfHnHvPflH5vH=vHvHvH[jOv fJv )5wv)@vPH IHsH5>8H=6HiiIxHIuLlH AHM~%"HfHnHuHL5H zuH cuflL%8fHnHluHQH )d$fHnAAjflHtH5tH uH H=5uQPHtHuHuH*jL%uL5tt )%t)tPH IHeH5@7H=y5HQh[IxHIuLjH ;(d$jH GHsHļAAH sH sH5sHsfHnHQH H sH lfHnH=sQflŹH7sPHosHxsHsHjL%sL5 ss )%as) sPH IH}H586H=i4HAgsIxHIuLiH (t$jHJHVH?rAAH HpHQH )l$fHnAHUpjflH5XpH=pQPHkpHtpHjL%p)-ep)pPH IHH5<4H=]2H5eIxHIuLgH(\$jH oHҥfHnHnoAHqoHQH 6 AQfHnHoPflH5oH=KoH,oH5oHjL%n)&o)nPH IH H5e3H=~1HVdIxHIuLf(,$HLL%nH >nH/fHnAA)-?nHH5mH=.nHnHHnHjHmHQH $QfHnHmPflHmH%j)mPIH HGH52H=0Hkc=IxHIuLe(<$HQL%lH lH4fHnAA)=lHH5lH=lHlH7HlHjHlHQH O/QfHnҹHUlPflHlH:j)IlPIH HH51H=/HbzIxHIuLe( $HVL%kH kH9fHnAA) kHH5_kH=kHqkHUHkkHjHgkHQH $6QfHnڹH kPflHFkHOj)jPIH HH50H=.HaIxHIuL&d($$H[L%4jH ]jH>fHnAA)%^jHH5jH=MjH&jHvH jHjHjHQH :QfHnHiPflHiHdj)iPIH HH50H=-H`IxHIuL;cH(t$ jH iH fHnHiAHiHQH +?AQfHnHhPflH5hH=hHhHhHjoh fjh )5h)hhPH IH;H5n/H=,H_1IxHIuLPbHY(T$ jH gH fHnHgAHgHQH PAAQfHnʹHXgPflH5\gH=gHvgHgHj$g fg )dg)gPH IHxH5.H=+H^nIxHIuLeaH~(\$jH fHxfHnHmfAHpfHQH CAQfHnH fPflH5fH=JfH+fH4fHjL%e)%f)ePH IHH5-H=+H]IxHIuL`H(l$jH AeHfHnH.eAH1eHQH HAQfHnHdPflH5dH= eHdHdHވjL%d)-d)dPH IH H5,H=>*H]IxHIuL_H0(|$ jH dH=fHnc AHcAH5cH=cHcHQH MQfHnҹHwcPflHcHcHjfVc )=c)TcPH IHGH5,H=S)H+\=IxHIuL^H(L$ jH bHXfHnqb AHbAH5gbH=bHbHQH QQfHnڹH,bPflHXbHabH jf b ) Pb) bPH IHH5/+H=h(H@[zIxHIuL]H*(d$ jH laHtfHn&a AHIaAH5aH=UaH>aHQH UQfHnH`PflH aHaHjf` )%a)`PH IHH5L*H=}'HUZIxHIuL\Ho(t$ jH !`HfHnH`AH`HQH WAQfHnH_PflH5_H=_H_H_H>jz_ fu_ )5_)s_PH IHH5i)H=&HjYIxHIuL[H(T$jH ^HfHnH^L%TH^HQH ZAQfHnAPflHW^H5`^H^H=^H^HLjL%+^)t^)-^PH IH@H5(H=%HX6IxHIuL[H.(\$jH ]HfHnH}]AH]HQH \AQfHnH]PflH5!]H=Z]H;]HD]HmjL%\)5])\PH IHH5'H=$HWIxHIuL6ZH(l$jH Q\HؗfHnH>\AHA\HQH ]AQfHnH[PflH5[H=\H[H\HjL%[)-[)[PH IHҚH5&H=#HVȚIxHIuLWYHp;(|$jH [HfHnHZAH[HQH ?_AQfHnҹHZPflH5ZH=ZHZHZHjL%~Z)=Z)ZPH IHH5&H=#HUIxHIuLxXHH (L$ H}fHnfHnH[Yfl) YAA)YH5NYH=YH YHHVYHŨHPYHHVYHGYH}H HNYH ?YHH YfHnjH7YHQfHnHQ0H H'YflfHnHX)XfHnH d`QflŹPHBj)XPIH HH5G%H=!HTژIxHIuLWH"H( tAfHnfHnH |Afl) LWH5eWH=W)t$p(t$(T$p)5W)WHHWWHnHQWHHWWHHWH{H HOWH @WHH WfHnjH8WHQfHnHQ0H H(WflfHnHV)VfHnH ]jQflĹPH~j)VPIH HH5#H=Q H)SIxHIuLU(l$(t$pAAHz(=H5UH=U)-U)5U)=CUHHyUH8HsUHHyUHjUHKzH HqUH bUHH 8UfHnjHZUHQfHnHQ0H HJUflfHnHT)TfHnH _rQflPH}j)TPIH HH5"H=HQIxHIuL|T(\$(d$pAAH_y(-H5SH=S)S)%S)-eSHHSHHSHHSHSHxH HSH SHH ZSfHnjH|SHQfHnHQ0H HlSflfHnHR)RfHnH zQflǹPHg|j)RPIH HH5!H=HPwIxHIuL>SHH HxQfHnfHnL5^AflfInA)R(k= H5Q)=QH=Q)HQH)$HQHHQHHQHwQHxwH H~QH oQHH EQfHnjHgQHQfHnHQ0H HWQflfHnHP)PfHnH QflĹPHzj)PPIH H4H5 H=`H8O*IxHIuLQH"(l$@jH PH#fHnHOAHOHQH AQfHnHOPflH5OH=OHOHOH!zj]O )-O)_OPH IHzH5EH=~HVNpIxHIuLPH`(|$@jH NHfHn|N AHNAH5rNH=NHNHQH QfHnҹH7NPflHcNHlNH5yj)=dN)NPH IHH5{H=HtMIxHIuLPHfIngM HtfHnHtH eMAflAH5>M)gMHfHnH=XMH1MHH+MHjH'MHQH ,QfHnڹHLPflHMH/xj)LPIH HH5H=HuLߑIxHIuLOH H?(d$0L%H KHL-'AH KH KfInAHKfHn }H5NKHKHQH=KfHnHQ0H HKfl)L$pH(fHn) KfHnH HJH5KH;flH KH <jHKQPHKH&KH/KH8KHvjL%JJ fJ |J)%K) (K)JPH IHH5?H=HJzIxHIuLyM(T$0(L$pjH 2HCH xIHAH IH MIAH5IHYIfHnH=IHfIHQfHnHQ0H HIflH1fHnL%H)HfHnH HHHHflHǝH HH QPHHHHHHHHHHHWuj3H f.H )H)H) H).HPH IH9H5H=HuI/IxHIuLL(l$0(t$pjH 3HlH %GHL%H 0GH FAAHGfHnH5FH=3GH GHQfHnHQ0H H4GflHٱfHnL%EF)VFfHnH H.FHFflHYH MFH QPH`FHiFHrFH{FHFHsjE fE E)-rF)5{F)EPH IHH5bH=#HGݍIxHIuLJ(L$0(\$pjH YH2H DHAH DH DAH5SDHDfHnH=DHDHQfHnHQ0H HDflHV.fHnL%C)DfHnH HCH,DflHH CH QPH DHDHDH(DH1DHjrjC fC |C) D)(D)CPH IHH5H=HFIxHIuLIH "H%B AH tBH L%FAH yBfHnH =BHvHOBfHnfInHWBHQ\H5AfHnHQ0H HqBflHI)$H=7B)AfHnH HAHvH AH Ӱ)$HAjHAQPHAHAHAHpj)A()AfHnH@fl)@) APH IH.H5iH=HD$IxHIuLGH 'H%($($H ?H(5AH ?H ?AH5_?fHnjH=?H?H?HQfHnHQ0H H?flfHnH> ) ?fHnH H>H3?HflH ?H QPH?H?H&?H/?H8?HQoj)%@?)-I?)5b>)>PH IHH5H=HC܉IxHIuLFH5H =jAH=H`H-AH =H ܸH=QH5=H==PH=HnjH-=f`= [= PH IHDH5?H=HB:IxHIuLIEH H <jAH<HAH<H <H H5<QH=<PH<HmjH-<fm< h< PH IHH5H=HAIxHIuLDH fInH#$;H ;H^H-DZAH ;fHnH N;HgH`;fHnfHnH He;HQfl-fHnHQ0H H:flH7<)$fHn):fHnH AH:HflHK:H :H H5f:)$H=:jH:QPH:H:H:H:H,lj)-:(-H-:)%:)-9):PH IH+H5H=w HO@!IxHIuLB(T$0(L$pjH &H.H 8HhL5aH 8H 8AAH8fHnH5T8H=8H8HQfHnHQ0H H8flH7fHnL57)8fHnH H7H98flHgH 8H 8QPH8H#8H,8H58H>8Hjj7 f7 7),8) 58)7PH IHمH5tH= H>υIxHIuLfA(l$0(t$pjH CH\H 6HAH 6H Z6AH5 6Hf6fHnH=6Hs6HQfHnHQ0H H6flHfHnL55)5fHnH H5H5flHH 5H mQPH5H5H5H5H5HDij@5 f;5 65)-5)55);5PH IHH5 H= Hb=IxHIuL?(L$0(\$pjH `H9/H 24H{L5tH =4H 4AAH4fHnH53H=@4H4HQfHnHQ0H HA4flHfHnL5R3)c3fHnH H;3H3flHH Z3H QPHm3Hv3H3H3H3Hgj2 f2 2) 3)3)2PH IH<H5 H= H;2IxHIuLy>(t$0(|$pjH 6)H5H 1HAH 1H 1AH5`1H1fHnH=1H1HQfHnHQ0H H1flHfHnL50)1fHnH H0H91flH2H 1H QPH1H#1H,1H51H>1HWfj0 f0 0)5,1)=51)0PH IHH5, H=Hu:IxHIuL=H )H0H ($H /($AAH /H M/(-VH5.fHnjH=/HJ/Hc/HQfHnHQ0H H.flH;fHnH-t/).fHnH Hm.H.HflH .H QPH.H.H.H.H.Hdj+.).)%.)--)7.PH IHH5 H=&H8IxHIuL;(T$0(L$pjH He)H -HAH -H ,AH5,H,fHnH=#-H,HQfHnH,-HHQ0flH fHn:, H+,HKH,).,fHnH H^,HYflH ,,H mQPH?,HH,HQ,HZ,Hc,H\cjf+ +)[,) d,)+PH IHPH5K H=H7FIxHIuL:H(l$0jHPH)+HH *AH*fHnAH5*H*HH=*H*HQH H*H=fHnHN*H g*H xflQPHf*Ho*Hx*H1bj* )-i*)*PH IH]~H5H=Hi6S~IxHIuL8H#(|$jH u)HfHnH-ZAHU)AH5()H=a)HJ)HQH QfHnҹH(PflH)H")HKajH-()=))(PH IH}H5H=H5}IxHIuL8H(L$jH /(HfHnH-'AH(AH5'H=(H(HQH QfHnڹH'PflH'H'He`j) ')'PH IH|H5H=H4|IxHIuL57HN(d$jH &H4fHnH-&AH&AH5&H=&H&HQH QfHnHh&PflH&H&H_j)%&)N&PH IH1|H5H=H3'|IxHIuLV6Hπ(t$jH %HtfHnH%AH%HQH AQfHnH>%PflH5B%H={%H\%He%H^jH- %)5V%)%PH IHz{H5-H=H2p{IxHIuLw5HP(T$jH r$H fHnH-/$AHR$AH5%$H=^$HG$HQH QfHnʹH#PflH$H$H]j)$)#PH IHzH5H=/H2zIxHIuL4H!(\$jH 3#H/fHnH-"AH#AH5"H=#H#HQH QfHnH"PflH"H"H\j)")"PH IH zH5H=PH(1zIxHIuL3HRz(l$jH !HqfHnH!AH!HQH AQfHnH!PflH5!H=!H!H!H\jH-P!)-!)R!PH IHUyH5H=qHI0KyIxHIuL2Hs(|$jH HwfHnH-r AH AH5h H= H HQH "QfHnҹH- PflHY Hb H+[j)=Z ) PH IHxH5H=Hj/xIxHIuL1Hz(L$jH vHofHnHcAHfHQH )AQfHnڹHPflH5H=@H!H*HSZjH-) )PH IHwH5BH=H.wIxHIuL1H(d$ jH 7HlfHnH$AH'HQH 0AQfHnHPflH5H=HHHtYj f )%)PH IH$wH5H=H-wIxHIuL10~fInjH KUHġHmPH AflfHnH H )H~AHH5OH=flHHQfHnHQ0)fHnflH fHnH) H2fHnH ~;QflHPHHHH H Xj )PH IHuH5DH=mHE,uIxHIuL.~fInHrH SfHnH_AAflH5H=)~Bfl)( )IHHHhHQHbHkH HyH bH ;HQfHnjfHnHQ0H HDflfHnHDH)fHnH ?QflƹPHVj)PIH HtH5H=H*tIxHIuL-H((|$jH H5jfHnHH-H HQH nFAQfHnAPflHH5HH=HHUjH-o)=)qPH IHtH5OH=0H*sIxHIuL,H_(L$ jH HD~fHnHAHHQH 1JAQfHnڹHaPflH5eH=HHHTj- f( ) m)&PH IHAsH5H=EH)7sIxHIuL+H^(d$ jH Hd}fHnHvAHyHQH KAQfHnHPflH5H=SH4H=HTj f )%")PH IH~rH5H=ZH2(trIxHIuL*H^(t$ jH >H|fHnH+AH.HQH MAQfHnHPflH5H=HHHSj f )5)PH IHqH5H=oHG'qIxHIuL)H(T$0jHS>H,HMH AHfHnAH5HHH=HHQH HHfHnHQH jH PflQPHiHrH{HQj )l)PH IHpH5H=TH,&pIxHIuL(H(\$@jH xHzfHn2 AHUAH5(H=aHJHQH VQfHnHPflHH"H Qj))PH IHpH5 H=rHJ%pIxHIuL'H(l$@jH 6HyfHn AHAH5H=HHQH UZQfHnHPflHHH)Pj)-)PH IHToH5/H=Hh$JoIxHIuL&H (|$jH HxfHnH-AHAH5H=HHQH fQfHnҹHPflHHHJOj)=)bPH IHnH5H=H#nIxHIuL&HH0H-{ H fHnHHrHHfHnHQH 5fHnHjHw)t$pflL%AjAHH5H H qjH=RQPHH%H.H'NjL%6H- )5) PH IHmH5WH=HX"mIxHIuL$Hp(d$pjH  H]0Hq fHnL%- H HvAAH H= H HQH xQfHnHi PflH H H H(MjH5g H5P H-1 /  )% )1 PH IHlH5OH=pHH!lIxHIuL#Hg(t$pjH5t H0HN fHnL% HV HuAAHL H=e HN HVH5SVfHnH5 H PflH H H HLjH H-   )5 ) PH IHkH5GH=`H8 kIxHIuL"HH (T$jH`H H5H- VfHnAAPH5 H= H HQfHnH Ht H HKfljH-Y ) )[ PH IHkH5iH=zHRjIxHIuL!HuH (\$jH_HH5ifHnVAAH5pHHQH=PfHnH<HmflHrH;JjH-)c)PH IHOjH5H=HsEjIxHIuL!(l$PL%fW H xHEfHnHEH5vL%'AAH=d)-]HH3HrH-HjH)HQVfHnH5HPflHH1Ij)PIH H{iH5H=HwqiIxHIuL (|$PHDL%H f fHnHDH5J)=HAAH=HHqHHjHHQVfHnH5HwPflHHHQH=CPfHnHHflHHBjH-)-)PH IH4dH5/H=@H*dIxHIuL(<$H6>H-H H>H5JfHnA)= HAH=HHzkHHjHHQVfHnH5HPflHHAj)vPIH HqcH5LH=UH-gcIxHIuLHH Hj(L$@H5jfHnAVAH5H=HHHQPfHnHWHflHHAj2 ) {)4PH IHbH5H=sHKbIxHIuLHH (d$@jHiHH5fHnVAAH5IHrHQH=wPfHnHHFflHKH4@j )%9)PH IHaH5H=HiaIxHIuLH#iH \(t$jHTHGH5H-QVfHnAAPH5H=8H!HQfHnHHHHO?fljH-)5)PH IH?aH5H=H5aIxHIuLH}bH (T$jHSHH5fHnVAAH5HHQH=PfHnHHflHHl>jH-k))mPH IH`H5+H=H~`IxHIuL5HH Hag(\$ H5jfHnAVAH5H=HHHQPfHnHNHflHH=j) f$ )i)"PH IH_H5H=H_IxHIuLJH#tH H~f(l$ H5jfHnAVAH5>H=wHPHYHQPfHnHH4flH9H<j f )-)PH IH_H5H=H^IxHIuL_HqH AHe(|$ H5jfHnAVAH5H=,HHHQPfHnHHflHH;j f )=)PH IH?^H5 H= H5^IxHIuLtHm(L$0jH H)Hq fHnH-HHdL%#AHAH=HHQH 7QfHnڹHUPflHHHH:jH5KH54L%H- ) h)PH IHL]H5H=HB]IxHIuLYH"MH5{(d$ jHNHfH WfHnQAAHQHVH=VPfHnH5 HH#flH(H9j f )% )PH IH\H5H=H \IxHIuLnHǰH50Hb(t$ H }jfHnAQAH=HHHVH5PfHnHHflHH8j f} )5){PH IH[H51H=H [IxHIuL(T$`H3 H5f fHnH3H Z)HAAH=HH~aHHjHHVH5QQfHnʹH/PflHkH7j)#PIH HZH5IH="H ZIxHIuLHTCH5(\$ jH`HxH fHnQAAHcHVH=hPfHnH5HH5flH:H6j f ))PH IH3ZH5H=7H )ZIxHIuL HiH5B(l$ jH_H-H . fHnQAAHHVH=PfHnH5HHflHH5j f )-)PH IHpYH5H=LH$ fYIxHIuL H_H5H_(|$@H djfHnAQAH=HHHVH5PfHnH~HflHH 5jY )=)[PH IHXH5!H=jHB XIxHIuL H@H5ʼH=[H31@IxHIuLH5LIH@H5H= H@IxHIuLtH5ULtIH?H5:H=H?IxHIuL$H5 L$IH?H5H=kHC?IxHIuLH5ŻLIH?H5H=Hy?IxHIuLH5}LIHX?H5bH=˲HK?IxHIuL4H5EL4IH*?H5*H={HS?IxHIuLH5LIH>H5H=+H>IxHIuLH5uLIH>H5ZH=۱H>IxHIuLDH5-LDIH>H5H=Hc>IxHIuLH5LIHr>H5ʻH=;He>IxHIuLH5LIHD>H5H=H7>IxHIuLTH5ULTIH>H5:H=Hs >IxHIuLH5 LIH=H5H=KH#=IxHIuLH5źLIH=H5H=H=IxHIuLdH5LdIH=H5H=H=IxHIuLH5]LIH^=H5BH=[H3Q=IxHIuLH5LIH0=H5H= H#=IxHIuLtH5 LtIH=H5H=H<IxHIuL$H5ŹL$IH<H5H=kHC<IxHIuLH5}LIH<H5bH=H<IxHIuLH55LIHx<H5H=˭Hk<IxHIuL4H5L4IHJ<H5ҸH={HS=<IxHIuLH5LIH<H5H=+H<IxHIuLH5]LIH;H5BH=۬H;IxHIuLDH5LDIH;H5H=Hc;IxHIuLH5LIH;H5H=;H;IxHIuLH5ŸLIHd;H5H=HW;IxHIuLTH5ELTIH6;H5*H=Hs);IxHIuLH5-LIH;H5H=KH#:IxHIuLH5LIH:H5ʸH=H:IxHIuLdH5LdIH:H5H=H:IxHIuLH5MLIH~:H52H=[H3q:IxHIuLH5eLIHP:H5JH= HC:IxHIuLtH5LtIH":H5ҬH=H:IxHIuL$H5ͶL$IH9H5H=kHC9IxHIuLH5uLIH9H5ZH=H9IxHIuLH5 LIH9H5H=˨H9IxHIuL4H5ŮL4IHj9H5H={HS]9IxHIuLH5}LIH<9H5bH=+H/9IxHIuLH55LIH9H5H=ۧH9IxHIuLDH5ŮLDIH8H5H=Hc8IxHIuLH5}LIH8H5bH=;H8IxHIuLH55LIH8H5H=Hw8IxHIuLTH5LTIHV8H5ҭH=HsI8IxHIuLH5LIH(8H5H=KH#8IxHIuLH5ͳLIH7H5H=H7IxHIuLdH5LdIH7H5H=H7IxHIuLH5uLIH7H5ZH=[H37IxHIuLH5MLIHp7H52H= Hc7IxHIuLtH5LtIHB7H5zH=H57IxHIuL$H5L$IH7H5H=kHC7IxHIuLH5LIH6H5jH=H6IxHIuLH5LIH6H5ڥH=ˣH6IxHIuL4H5L4IH6H5ڨH={HS}6IxHIuLH5LIH\6H5H=+HO6IxHIuLH5LIH.6H5H=ۢH!6IxHIuLDH5-LDIH6H5H=Hc5IxHIuLH5LIH5H5jH=;H5IxHIuLH5ELIH5H5*H=H5IxHIuLTH5 LTIHv5H5H=Hsi5IxHIuLH5LIHH5H5H=KH#;5IxHIuLH5eLIH5H5JH=H 5IxHIuLdH5LdIH4H5ҥH=H4IxHIuLH5ݣLIH4H5£H=[H34IxHIuLH5LIH4H5zH= H4IxHIuLtH5ULtIHb4H5:H=HU4IxHIuL$H5 L$IH44H5H=kHC'4IxHIuLH5ŢLIH4H5H=H3IxHIuLH5]LIH3H5BH=˞H3IxHIuL4H5EL4IH3H5*H={HS3IxHIuLH5LIH|3H5H=+Ho3IxHIuLH5͡LIHN3H5H=۝HA3IxHIuLDH5LDIH 3H5rH=Hc3IxHIuLH5ELIH2H5*H=;H2IxHIuLH5}LIH2H5bH=H2IxHIuLTH5=LTIH2H5"H=Hs2IxHIuLH5LIHh2H5H=KH#[2IxHIuLH5=LIH:2H5"H=H-2IxHIuLdH5LdIH 2H5ңH=H1IxHIuLH5ELIH1H5*H=[H31IxHIuLH5LIH1H5ҟH= H1IxHIuLtH5LtIH1H5H=Hu1IxHIuL$H5L$IHT1H5zH=kHCG1IxHIuLH5ݧLIH&1H5§H=H1IxHIuLH5LIH0H5jH=˙H0IxHIuL4H5L4IH0H5H={HS0IxHIuLH5MLIH0H52H=+H0IxHIuLIExHIEuL{H-H=ݘHUHQIHt tAHRIH*0H5H=Lo 0IxHIuLIH0HH5H)0HH5;L /H5dH=L/IEgHIEZLtML%,L%,L%v,L%e,L%T,qE1L% ]E1L% IE1L% 5E1L% !E1L%  E1L% E1L% E1L% E1L%r E1L%^ E1L%J 8E1L%6 8E1L%" _mE1L% _YE1L% EE1L% 1E1L% E1L%  E1L% E1L% E1L% E1L%n E1L%Z  E1L%F  E1L%2 L}E1L% LiE1L% `UE1L% `AE1L% -E1L% E1L% E1L% E1L% E1L%~ E1L%j E1L%V E1L%B E1L%. yE1L% >eE1L% >QE1L%T=E1L%T)E1L%{E1L%{E1L%E1L%E1L%zE1L%fE1L%RE1L%>E1L%*uE1L%aE1L%ME1L%9E1L%%E1L%E1L%>E1L%>E1L%eE1L%veE1L%bE1L%NE1L%:E1L%&qE1L%]E1L%IE1L%5E1L%!E1L% E1L% E1L%8 E1L%8 E1L%r[ E1L%^[ E1L%J E1L%6 E1L%" mE1L% YE1L% EE1L% 1E1L% E1L% E1L% E1L% E1L%= E1L%n= E1L%Z` E1L%F` E1L%2 }E1L% iE1L%  UE1L% AE1L% -E1L% E1L% E1L% E1L% E1L%~ E1L%j> E1L%V> E1L%Ba E1L%.a yE1L% eE1L% QE1L% =E1L% )E1L% E1L% E1L% E1L% E1L%z E1L%f E1L%R= E1L%>= E1L%*b uE1L%b aE1L% ME1L% 9E1L% %E1L% E1L% E1L% E1L% E1L%v E1L%b E1L%N E1L%:5 E1L%&5 qE1L%` ]E1L%` IE1L%~ 5E1L%~ !E1L% E1L% E1L% E1L% E1L%r E1L%^ E1L%J E1L%6 E1L%"mE1L%YE1L%EE1L%1E1L%eE1L%e E1L%E1L%E1L%E1L%nE1L%ZFE1L%FFE1L%2}E1L%iE1L% UE1L%AE1L%R-E1L%RE1L%E1L%E1L%E1L%~E1L%jXE1L%VXE1L%BE1L%.yE1L%eE1L%QE1L%=E1L%)E1L%\E1L%\E1L%E1L%E1L%zE1L%fE1L%R0E1L%>0E1L%*ouE1L%oaE1L%ME1L%9E1L%%E1L%E1L% E1L% E1L%=E1L%v=E1L%bE1L%NE1L%:NE1L%&NqE1L%]E1L%IE1L%\5E1L%\!E1L% E1L%E1L%DE1L%DE1L%rE1L%^E1L%JE1L%6E1L%"FmE1L%FYE1L%EE1L%1E1L%E1L% E1L%WE1L%WE1L%E1L%nE1L%ZE1L%FE1L%2H}E1L%HiE1L% UE1L%AE1L%-E1L%E1L%7E1L%7E1L%E1L%~E1L%jE1L%VE1L%BXE1L%.XyE1L%eE1L%QE1L% =E1L% )E1L%gE1L%gE1L%E1L%E1L%zaE1L%faE1L%RE1L%>E1L%*,uE1L%,aE1L%ME1L%9E1L%@ %E1L%@ E1L% E1L% E1L% E1L%v E1L%bP!E1L%NP!E1L%:!E1L%&!qE1L%."]E1L%."IE1L%"5E1L%"!E1L%" E1L%"E1L%,#E1L%,#E1L%rc#E1L%^c#E1L%J#E1L%6#E1L%"$mE1L%$YE1L%;$EE1L%;$1E1L%$E1L%$ E1L%$E1L%$E1L%%E1L%n%E1L%Z'&E1L%F'&E1L%2&}E1L%&iE1L% ''UE1L%''AE1L%'-E1L%'E1L%'E1L%'E1L%L(E1L%~L(E1L%j(E1L%V(E1L%B(E1L%.(yE1L%5)eE1L%5)QE1L%)=E1L%))E1L%)E1L%)E1L% *E1L% *E1L%z\*E1L%f\*E1L%R*E1L%>*E1L%**uE1L%*aE1L%/+ME1L%/+9E1L%w+%E1L%w+E1L%+E1L%+E1L%+E1L%v+E1L%b9,E1L%N9,E1L%:,E1L%&,qE1L%,]E1L%,IE1L% -5E1L% -!E1L%_- E1L%_-E1L%-E1L%-E1L%rA.E1L%^A.E1L%Jp.E1L%6p.E1L%".mE1L%.YE1L%/EE1L%/1E1L%0E1L%0 E1L%l0E1L%l0E1L%0E1L%n0E1L%ZR1E1L%FR1E1L%21}E1L%1iE1L% 2UE1L%2AE1L%2-E1L%2E1L%2E1L%2E1L%n3E1L%~n3E1L%jp3L%Yp3L%Hp3L%7p3L%&p3qL%p3`L%p3OL%p3>L%p3-L%p3L%p3 L%p3L%p3L%p3L%|p3L%kp3L%Zp3L%Ip3L%8p3L%'p3rL%p3aL%p3PL%p3?L%p3.L%p3L%p3 L%p3L%p3L%p3L%}p3L%lp3L%[p3L%Jp3L%9p3L%(p3sL%p3bL%p3QL%p3@L%p3/L%p3L%p3 L%p3L%p3L%p3L%~p3L%mp3L%\p3L%Kp3L%:p3L%)p3tL%p3cL%p3RL%p3AL%p30L%p3L%p3L%p3L%p3L%p3L%p3L%np3L%]p3L%Lp3L%;p3L%*p3uL%p3dL%p3SL%p3BL%p31L%p3 L%p3L%p3L%p3L%p3L%p3L%op3L%^p3L%Mp3L%<p3L%+p3vL%p3eL% p3TL%p3CL%p32L%p3!L%p3L%p3L%p3L%p3L%p3L%pp3L%_p3L%Np3L%=p3L%,p3wL%p3fL% p3UL%p3DL%p33L%p3"L%p3L%p3L%p3L%p3L%p3L%qp3L%`p3L%Op3L%>p3L%-p3xL%p3gL% p3VL%p3EL%p34L%p3#L%p3L%p3L%p3L%p3L%p3L%rp3L%ap3L%Pp3L%?p3L%.p3yL%p3hL% p3WL%p3FL%p35L%p3$L%p3L%p3L%p3L%p3L%p3L%sp3L%bp3L%Qp3L%@p3L%/p3zL%p3iL% p3XL%p3GL%p36L%p3%L%p3L%p3L%p3L%p3L%p3L%tp3L%cp3L%Rp3L%Ap3L%0p3{L%p3jL%p3YL%p3HL%p37L%p3&L%p3L%p3L%p3L%p3L%p3L%up3L%dp3L%Sp3L%Bp3L%1p3|L% p3kL%p3ZL%p3IL%p38L%p3'L%p3L%p3L%p3L%p3L%p3L%vp3L%ep3L%Tp3L%Cp3L%2p3}L%!p3lL%p3[L%p3JL%p39L%p3(L%p3L%p3L%p3L%p3L%p3L%wp3L%fp3L%Up3L%Dp3L%3p3~L%"p3mL%p3\L%p3KL%p3:L%p3)L%p3L%p3L%p3L%p3L%p3L%xp3L%gp3L%Vp3L%Ep3L%4p3L%#p3nL%p3]L%p3LL%p3;L%p3*L%p3L%p3L%p3L%p3L%p3L%yp3L%hp3L%Wp3L%Fp3L%5p3L%$p3oL%p3^L%p3ML%p3L%p3-L%p3L%p3 L%p3L%p3L%p3ؽL%|p3ǽL%kp3鶽L%Zp3饽L%Ip3锽L%8p3都L%'p3rL%p3aL%p3PL%p3?L%p3.L%p3L%p3 L%p3L%p3L%p3ټL%}p3ȼL%lp3鷼L%[p3馼L%Jp3镼L%9p3鄼L%(p3sL%p3bE1L%u3NML%E1u37E1L%#E1L%E1L%E1L%L%ֻHĸ[]A\A]A^A_H=vea!G GLwH/LgHLWHLGHL7HL'HߤPĚHMH5.THHTHt H=7荗h1d]{f.ff/w>f(fTEf/rCYY CY\YXCff.@Hf( QCH?XfH1H)1HW fHnf(fH~HYf(\H9u\YB%Bf(HBH?fYH1H)1HWX f(f(f(HY\H9u\YXff.Hf(BfH?X\uBH1H)1XHW f(f(f(HY\H9u\Y'Bff.LGPAtALff.fLG`AtALff.fL!RAtALf.HGhHttDHQff.@HHtt f.HH|$蚙HtH|$HtHff.HG@HttDHH|$BH|$HG@Ht tHfDAWIAVAUATUS1H(HAL.L1L'HD$HoM~6fA$AL$HAM'$L$f($UIoI9uH|$H([]A\A]A^A_$ @AWE1AVIAUATUSHHAL&L)H/HD$H_M~7ffIZEZMAI.ZZKI^M9uH|$H[]A\A]A^A_~ fAWE1AVAUATUSHHHHHL'LwLl$0HT$HQHL$ H$HoHT$HL$H~JDA$AL$LIH|$HD$f(T$ L#Af(\$0Ls]HkL9<$uH|$~ HH[]A\A]A^A_fAWE1AVAUATIUSHHHHL7HoLl$0HT$HQHL$ H$H_HT$HL$H~zDffH|$LAZAZNHD$IffM4$ZD$(ZL$ EfMfZD$8Il$ZL$0C I\$L9<$uH|$!} HH[]A\A]A^A_fAWE1AVAUATUSHH8HHL'LwLl$(HT$HQHL$ H$HoHT$HL$H~EDA$H|$LIHD$D$ L#AD$(LsEHkL9<$uH|$v| H8[]A\A]A^A_AWE1AVAUATUSHH8HHL'LwLl$(HT$HQHL$ H$HoHT$HL$H~QDfH|$LIAZ$HD$fL#ZD$ AfLsZD$(EHkL9<$uH|${ H8[]A\A]A^A_ff.AWAVAUATU1SHH(HHL7LoLLgHT$HQHD$HT$H~3AIuHI>HD$L3LkA$L{LcH9l$uH|$H([]A\A]A^A_{ DAWAVAUATU1SHH8HHLwH7LoLHT$ HQLg HD$HT$(H~b@AHt$HAAgAUHD$ Ht$Ls$H3LkL$f(,$L{A,$Lc H9l$uH|$(H8[]A\A]A^A_Rz fAWE1AVAUATUSHH(HHLwH7LoLgHT$HQHo HD$HT$H~rfffH4$ffZAZ$AZAZd$AZUHD$IH4$LsZZMH3ELkLcHk L9|$uH|$H([]A\A]A^A_y AWAVAUATU1SHH(HHLwH7LoLHT$HQLg HD$HT$H~J@AH>H4$HAMAHD$H4$LsA$H3LkL{Lc H9l$uH|$H([]A\A]A^A_x f.AWAVAUATU1SHH8HHHqL7LoLHD$HT$ LgHt$(H~LAMAHAA_HD$ L3Lk$L{L$f($$A$$LcH9l$uH|$(H8[]A\A]A^A_,x ff.AWE1AVAUATUSHH(HHHqL7LoLgHD$HT$HoHt$H~bfffIfAZAZ$AZ\$AZMHD$L3LkZZMLcEHkL9|$uH|$H([]A\A]A^A_ew DAWAVAUATU1SHH(HHHqL7LoLHD$HT$LgHt$H~5AAEHI>HD$L3LkA$L{LcH9l$uH|$H([]A\A]A^A_v AWAVAUATU1SHH(HHQL1L/LLgHD$HT$H~HfAAEHAWAL+L{$L$f($A$LcH9l$uH|$H([]A\A]A^A_9v fAWIAVE1AUATUSHHHQL)L'HoH_H$HT$H~NffffIAZ$ZMZUAZZM'KIoI_L94$uH|$H[]A\A]A^A_u AWIAVAUATUS1HHAL.L1L'HD$HoM~ fA$HAM'EIoI9uH|$H[]A\A]A^A_*u f.AWAVAUATUSHH8HHHqLwLoLHD$Ht$(Lg HT$ H7H1LMHIHfEMHL$AA4$A|$AeAmA^HD$ HL$H+$LsLkL$f($LcHAL{ H9L$uH|$(H8[]A\A]A^A_7t AWE1AVAUATUSHH(HHHqLwHLoHD$LgHo HT$Ht$HfffH $fffZffAZ4$AZ|$ZIAZeAZAZmAZ^HD$IH $LsZZMH ELkLcHk L9|$pH|$H([]A\A]A^A_8s AWAVE1AUATUSHH(HHLgH7HoLoHT$HQL HD$HT$H~^fffH4$fZAZ]ZUAZ $HD$IH4$LcZH3AHkLkL{ L9t$uH|$H([]A\A]A^A_ur DAWAVAUATU1SHH8HHHqL7LoLHD$HT$ LgHt$(H~XAANHA'AoAUA]HD$ L3Lk$L{L$f(4$A4$LcH9l$uH|$(H8[]A\A]A^A_q AWE1AVAUATUSHH(HHHqL7LoLgHD$HT$HoHt$H~vfffIfffAZAZNAZ$$AZl$AZUAZ]HD$L3LkZZMLcEHkL9|$uH|$H([]A\A]A^A_p AWAVAUATU1SHH(HHQL1L/LLgHD$HT$H~NfAEAMHAA_AL+L{$L$f($$A$$LcH9l$uH|$H([]A\A]A^A_Sp AWE1AVAUIATUSHHHQL1L'HoH_H$HT$H~ZffffIfAZ$ZUZ]AZL$AMeImZZKI]L9<$uH|$H[]A\A]A^A_o AWAVAUATU1SHH(HHHqL7LoLHD$HT$LgHt$H~5AI}HAHD$L3LkA$L{LcH9l$uH|$H([]A\A]A^A_o AWAVE1AUATUSHH(HHHqL'HoLoHD$HT$LHt$H~NfffIAZ$AZUZMHD$L#HkZLkAL{L9t$uH|$H([]A\A]A^A_in fAWAVAUATU1SHHHHHLLoLwLgHT$HQHL$8HD$HL$ L HT$(H~UfLL$I>HAMAHt$ HD$LL$LkA$D$8L LsLcAL{ H9l$uH|$(m HH[]A\A]A^A_@AWAVAUATU1SHHHHQL1L/LLgH$HT$H~1f.AI}HAL+L{A$LcH9,$uH|$H[]A\A]A^A_!m AWAVAUATU1SHHHHQL1L/LLgH$HT$H~3f.AAEHAL+L{A$LcH9,$uH|$H[]A\A]A^A_l ff.@AWAVAUATU1SHHHHQL1L/LLgH$HT$H~3f.AAEHAL+L{A$LcH9,$uH|$H[]A\A]A^A_l ff.@AWAVE1AUATUSHHHHQL!H/LoLH$HT$H~=fffIZEAZMAH+ZLkAL{L94$uH|$H[]A\A]A^A_tk @AWAVAUATU1SHH(HHLwH7LoLHT$HQLg HD$HT$H~K@H4$AHAUAHD$H4$LsA$H3LkL{Lc H9l$uH|$H([]A\A]A^A_j fAWAVAUATU1SHH(HHLwH7LoLHT$HQLg HD$HT$H~K@H4$AHAUAHD$H4$LsA$H3LkL{Lc H9l$uH|$H([]A\A]A^A_j fAWIAVAUATU1SHHHHHLLGIrHHT$0HQMr HD$(Mj(Mz0HT$8Mb8HfHt$ A7HAmA&H|$LD$AALL$HD$0LL$LD$H|$Ht$ A$L LCH{HsLs Lk(L{0Lc8H9l$({H|$8HH[]A\A]A^A_i AWIAVE1AUATUSHHHHHLLGIrHHT$0HQMb HD$(Ij(Mj0HT$8Mz8HfffIfffLL$ fHt$AZAZuH|$ZmAZ$$ZLD$ZAZHD$0LL$ LD$H|$Ht$ZAL LCH{HsLc Hk(Lk0L{8L9t$([H|$8HH[]A\A]A^A_g AWIAVAUATUS1HHAL.L1L'HD$HoM~ fA$HAM'EIoI9uH|$H[]A\A]A^A_g f.AWAVAUIATUS1HHAH.L!L?HD$LwH~(ffHAZAM}ZAMuH9uH|$H[]A\A]A^A_g fAWAVAUATU1SHH(HHHqL7LoLHD$HT$LgHt$H~7AAMHAHD$L3LkA$L{LcH9l$uH|$H([]A\A]A^A_f AWAVAUATU1SHH(HHHqL7LoLHD$HT$LgHt$H~7AAMHAHD$L3LkA$L{LcH9l$uH|$H([]A\A]A^A_e AWE1AVAUL-PATUHSHHHLaHH$LwHT$H1L@LL1e IккH]LuIL9<$tH;HcH9uHD$HI@HL[]A\A]A^A_Re fAWAVAUATUSHHHHHLLOLoL_HT$8HQLG HD$L(Lw0HT$0Lg8HLLM1MII3HcH9L\$(A"ALT$ AAHL$LD$HD$8LD$HL$LT$ L\$(A$L3L{HLkL[LC HK(LS0Lc8H9l$tbI}HcH9jH|$0H1LT$(HL$ LD$L\$c LT$(HL$ \%LD$L\$sDH|$0HH[]A\A]A^A_c H x N1H=K1-c 1HfDH=C{@HGXHttDSHGHHxHt{HCXHt t[fDH4tff.H8f( &Hr$)$f( z&H$H[$)$f( k&H$ )$f( c&)$f( c&)L$f( f&)L$ f( i&)L$0f( l&)L$@f( o&)$f( o&)$f( o&)$f( o&)$f( o&)L$Pf( r&)L$`f( u&f/#)L$pf( p&)$f.#f(fW ^&QY l#f( $u $#^f(^\A#f/$w~f(H$T$袘T$H|$PYD$f(¾诘L$f(f(^\$H8Y"ff.wSQf(Ef(H$T$$T$H|$YD$f(xf(xf(ff.fH8f("f/f(L$f(X\$(T$ d$-l$X-!d$fW%$D$T$ \$(f(f(t$fH8f(Yf(YYY\Xf(HH=1n_ F!fH8f(fATUSHH?HH1!f(f(H~-" .!fTf/% f(H1\f(fDfH*HXf(f(XXX^^YYYf(XXH9Hf([]A\fHM HHŨL$fHd$H*$I9  赸d$$f(~-!f(X^f( YYHKf5 HtHHH)H)L)YHHH(fHfH*XH*HHYYfH*^Yf(fTYf(fTf.zuHf([]A\f. `賷$d$f(~- f(^Yf(fW%!f(\Yf(Xf(ff.Xf(fW%!f(X\\YXf(f(cf(H8XL$(f(D$ T$f(\$l$y l$t$(Xl$$f(\|$d$ f(fW% XXf(f(Y~Y$H8f(H8XL$(f($T$X\$ f(L$0-vX,$D$f(j0T$\$ ^f(T$K0T$5\\$d$(f( L$^$fW YXt$}YD$H8Hf(0fWd$\Yf(X }d$X%HYfDhf(fW%\f(f(Y_}ff.@X<$f(fW%@\\f(f(Y}Hf(fW%Y\f(f(Y|HXff.H=ffD(fDWf(f(\X\ nf(Yf(YYYf(fA(\f(X$fHf(f(YY\Xf(ff.@fD(HHDXL$8f(D$0T$fA(\$d$DD$(/f D$ f(\t$DD$(f(\D$DXD$DL$8l$0f(fD(fW-DYf(YYYfA(XAXA\Xf( t$ fHHf(Yf(YYf(Y\Xf(fHff(f(f(fD(X\fDW\ X5*f(|$Yf(YYYf(\XfA(^|$fHf(Yf(YYf(Y\Xf(Hf(8f(fW5D\ff(\f(YYf(Yf(Y\Xf(迧Hf.AWAVAUATUSHHD$D?A9~fTf.fTf.of/a{|$f(AHA\EN\l$|$PA9WD)D$9A9D$Dt$tANDDt$))C6D)Ήt$pkt6*ΉYYf*BYf*D$@YD$f(\BA9rDL?fLcDfAEA*EA)GL YB fA*F 6GL A*ADYAYf(B fA*Y\BA9~w|6fLcf*D)D|?T*ҍYB f*YYB f*Y\BfDT$E1fɅ<@BDB^Df.>&QBYDBDIM9tMuH=IH}M9uDL$tALKtHHHPH@H@AAI<MTHDHI1HfDf4ffYfA4f^HH9uDȃAtHDY^DAHT$tjH5jH=H$PH$Pt$PH$Pt$Xt$pRATt$pH$PH$PH$PPH$PL$c$H쀅D$tKLmHHHHH1H@ff4f^HH9uHcȃtI4^Dt$fW5LM,fI~fHcL$tHȃfM|H+*fInHgf(fIn^fHn^KL9uHĨL[]A\A]A^A_ft$pC AKDDL$tDL$IL$D)ALt$pL$t-IwIHAA@D!IM)IAD|IsHnfD(fAnDIfDpfnt$dDD$HfD(1fDo fDpfEfEfo5fEHfEfo ffAofDfofofrfffofofs ffofs ffffpfpfpfpfbfAofbffpfAYfrfAYfpfAYfAY<\fAoffAffrfrffpDfpfAYfAYfYfofAYfs fA\fofA<fpfpfbfAofrffrfAYfpfAYfXfXDH H9DʃAtzfAAt$fADl$X|$DAEEA*EA)GTYBfA*F7GTA*DT$dYE)EYf*BYfA*YXBA9:rDL?fLcAfDL$EDL$dAEA*EA)G\YBfA*E6G\A*ADYEE)EDL$YEfEA*BfA*YYXBD9|6fLcAfDEEAA)DEɍTA*GL*ʍ6t$d)YBfA*YYf*BYf*YXBf.DD)|$@C6t$DJrEAfD(fDW=DAt$XDT$d wLAHIw@H@!HL)H@@HrH fAnf(DHfDpfAnffpDT$HfE(D|$Pfpfo%fDYH1fYfEfEfo5fo ffEfoffDofrfDffAofDofAofAs fs ffAffEfpfpfbfAofEpffpfrfAbfofAYfpfAY3fAoT3fAofAfAfrfrfDfpDfpfAYfEYfYfA(fEYT2fpfYD,2fYf\f(f\1T1H H9D\$@D߃AWt?fAAt$f|$PDAEA*E GL YBfA*EA)EA*AYYf*BYf*D$dYD$f(\BA9wDLfHcAfEEAEA*E6GTY fA*EA)EA*AYYf( fA*Y\A9cT6fHcAfDAEA*E >GL Y fA*EA)EA*DYAY f*Y\fEC46t$Vf(fW- l$X|$@~׉T$dLHAMWIEVAAAE!IM)IAESLRIEfD(DfAnHfnt$@fEfD(|$HfDo: fDpfpfo G HfEfDpDf1EfEYfo5 fDo=# fEYfDfAofAofDfofofrffofDoffAfAs ffofs ffAfrfEfpfpfbffEpffrfYfpfY3foffAD3fofpfAYfrffAYfpfAbDfpfYfrfAYfpfAYfAYD2foffs f,2fpfpfbfA(f\fYfpfYfX1fA(f\fXT1H H9DAN<rft$DOAfɃD|$Xfl$AEA*E 6GL YBfA*EA)EA*ADYAA*YYBf*D$@Yf(\f*YXB A9D 6zfHcEQfADEAEA*EA)EY fA*F7GTA*ADYAYfA*Y f(\fA*YX D94?fHcDNf҃DAEA*E GL Y fA*EA)EA*YY f*Y\f*YX[DD)|$dFC46t$DVDNDf(fW=-|$hT$XDAщT$@A: MILAIAH@D!IM)IADHzHfAnDfD(HfDpfnl$XDD$HfD(1fDo fpfEfo5fo fE)l$@fEfDo=HfEfAofDfofrffoffAfofofs fs ffffpfpfpfbfAoffrfAYfpfAY$3fo\3fAofAffrfrfffpDfpfAYfAYfpfbfYfrfofAYffs fd2fpfp<2fAYfAYfpfbfoT$@ffAYfpfAYfXfX1D1H H9D\$dDڃA<rft$DOAfɃD|$hl$AEA*E 6GL YBfA*EA)EA*ADYAYfBfA*DL$XA)A*YYXBA9D 6zfHcEQfADEAEA*E>GTYfA*EA)EA*DT$XE)ADYAYfA*YfA*YXA9l4?fHcDNfɃDAEA*E A)GL YfA*EEA*DL$XA)YYf*YfA*YXAq1fDYH^DAHH9uH1 H=1< E1fDL$AM)ΉL$tD)Ήt$pcf.Hc1A^DAHH9uAHH=~1E1< fDHrH:ALHIAH@D!IM)IADN H~H@ fD(fAnDHfDpfnt$XDD$HfE(fE1fDpfEfEfDo Ufo5]fo eHfAofDfofofrfffofofs ffofs ffffpfpfpfpfbffbffAofrffofpffAYfAYfpDfAof<foffAfrfrfAYfDfpfAYfpfofAYfs ffYTfpfbfAYfofrfAYfpfAYfXfpfAYfXDH H9D\$@DڃAr|fAAt$f|$DAEA*EA)GTYBfA*E6GTA*DT$XAYA)Yf*BYfA*YXBA9zDL6fLcAfEEAEA*EA)G\YBfA*E>G\A*D\$XAYE)Yf*BYfA*YXB9|$@`t?fLcAfDAEA*EA)DGL TYBfA*DYf*‹T$X)DYf**YF<YXBwLHIw@H@!HL)H@@HrHf(fAnt$dHfDpffnt$@fD(DT$|$PfEfpH1fo-MDfpfEfo5FfDYDffDo=OfDYHfEfo )ffoffofrffoffAfDofofAs fs ffAfpfpfbfAoffrfAYfpfAY$3foffs T3foffAfrfDfpfpfpfbfAofffrfAYfpfAYfAYfYfpfYfY2T2fA(f\fA(f\1D1H H9D\$dDڃA<rft$DOAl$hDf|$PAEA*EA)GL YBfA*E 6GL A*YYf*BYf*D$@YD$f(\BA9D 6zfHcEQfADEAEA*EA)GTY fA*E>GTA*YYf( fA*Y\A9p4?fHcDNf҃DAEA*EA)DGL T*Y fA*YY f*Y\AvIAH@D!IM)IADHzHf(fAnDHfDpfnt$dfDT$fD(HfEfpfEH1D|$Pfpfo-nfDYDfo5lfDo=fDYfEffo ]DfoffofrffAfofofs fs ffffpfpfbfAofpffrfAYfpfAY$3fAoT3fofffrfAfrfADfpfpfbfpfAYfrfAYfYfAYD2fpfY2fA(fYf\fA(f\1D1H H9DAr|fAt$l$Xf|$P*D)YBf*A<6|?*ωYYf*BYf*D$dYD$f(\BA9SzffLc΍t6*B47t6YB f*D)*։YYf(B f*Y\BD9ffHc|?*D)Y f*A<ҍ|?*YY f*Y\jL|$@T$1F4D|$d\$Xd$@AAfAA)DfAE*EEEA*EYA)҃YfA*EE)EYfA*YfA*YXHmL|$@f\$d$P*T$dYT$l$XD^FfDffD)*Y*D)YDf*ljYf(Df*Y\LHL9ufҋ|$d\$*T$@YT$d$Pl$hDwDffAD*D)YDf*A<1*YYf(Df*Y\LHL9uKDT$@L|$@1FT$Dt$X\$fDAffD)*ADAYEA*EA)׃YfA*EA)Yf*fA*YYXHL9tf\$d$P1*T$@YT$l$XFAffAA)*AEYEA*EA)уYfA*ADYAf(fA*Y\ Hu|$dL|$@DVDt$XT$\$hd$D_ffɃADAEA*EA)YDfA*E<1A*EYA)Yf*DYfA*YXDHL9pffl$Dv\$*T$@d$XAY@DffAEDAEA*EA)YDfA*D7A*ADYAYfA*YDf(\f*YXDHL9iDfҋ|$@GL6\$*T$dYT$d$PD_EQF4fDffD)A*ɉAY*DD)AYDf*Yf(Df*Y\LHL9uLD$@HD$HL$BLD$@HD$fHL$ff.AWAVAAUATUSHHT$(HT$8f(f(d$ T$L$D$-|$DD$HT$d$ t$(5AfD(IDYAAAE}E9ED)A9mA_A9(D-d$(T$ DD$|$DL$A9ff(Ń)*vBT$ DL$DD$|$f(fA(d$(YfA(A\\YfYfTf.QYDfA( Hc^\ADxHcYAXHyYJH|$8FCHH[]A\A]A^A_HE|H=1( fH|$8D$BD$HH[]A\A]A^A_Ðff(T$)|$BhDL$*1AT$DL$f|$YfA(\fTf.=QYf(f.ff(|$DL$DŃ)*@DL$|$f(Dff(d$ )DD$Bh|$*DL$b@d$ DL$fDD$|$YfA(A\fTf.w=QY |$d$DL$3?|$d$DL$|$d$DL$?|$d$DL$|$T$DL$>|$T$DL$ff.UHHSHHHGLH@tV$HHH[]AukHLFI$HvHH[]A@HLF1MtHCH yHHH5yH81=@HH5yH8?H1[]fHtHL $HT$JEL $Ht$H`)fDHL $HT$EL $Ht$H#HCH gyH5{yHHH81:T$fu2$T$ :T$ff.z f/>,$f.f.$<f/B*-r"f/v f/v4$f/_$f(ʻ!YYX]f. $f.Q<$f.QYf($f(YYXƒf(f(f.zf/uYf(H [@f(T$8T$ff.xH [ff.H f([@f(@~P$-#fWfW$f.zf/t4$f._tXf/f(f(XYYYY $f(^D $^f(fD`Dpf(L$l$/H1L$fl$f(fHn$L$l$T$_/T$fHL$Yl$fHnf($f(YYXf(ff.HLOH?t%HupHHu6IAH6HfHt{HH>HHDH IIH HjH5)jH81.1H@HytH WjHIH5ajH81-DH jHysATUHHHGHGHHHu%GWHH ЉAH9uAHD]A\H59123xttYH3AH9tHHH5WAH8q/DgH]DA\fHYH5JH8:/AHD]A\fH@`H}HHtqHHtgHH9Eu2HAHE HHEH,HHHuo2H\2HNHH5EiAH8n.fHt 0fDtHAWAVIAUATIUHSHhLG0MtHwHhHL[]A\A]A^A_AHVL?'IHL14IHmLLHHIIEx HIEtOHhL[]A\A]A^A_DL~HvHu;HhLH1[]A\A]A^A_Af.E1L +fDHBHD$HtJ<8LD$H(+IH4MLD$tWIF I9IGHL1HHAoDADHH9uLHAt ITITH|$LD$<(LD$HHD$KD1AL|$ HHD$HL$PLHD$XH|$HLl$0IHl$8IHIHD$HLD$(EHD$PHPH#tHL$XtH|$JDHD$J ILLHL)uL|$ LD$(ILl$0Hl$8HHL$LLHAIH\$Hx HHH\$H~nLd$1DHH9tWIHx8 M\$8@LIuHD$I)IL8H([]A\A]A^A_DH9Ml$(M|$8HH9HHL;puL@M;D$uDX AT$ Dމ@@@8uA Hx8 M\$8@LI5uH:HT$LH5qH81Q3H(1[]A\A]A^A_L\$@MDHx(H8A@HDHx(H8A@HDSAIH@MMD6ff.AWIAVIAUATUHSHH8HD$(Ll$ HD$HD$ Ld$HD$1LLHtxHH|$ HHt@H98tHBHHuHD$(HH9GuKHL$MHLtu HHL$ LH5qH81H8[]A\A]A^A_HL$MHLIAWLAVAUATUH,SH8LL$pHL$M~eHD$(II1HD$IM@HUMTHHuMDHPHHt;L;uIL)L t HHL9u1H8[]A\A]A^A_fDHD$(HI9BLD$xHL$LHLLL$pLT$LT$LL$ptAt(H|$HtPILLL$p5LL$phH8[]A\A]A^A_HD$(II NjtH6$'H HT$xLH5 pH817DLD$xHL$LHLLL$pLT$LL$pLT$-HXf(\ ܾfWd$&\Yf(X d$X%HYf.LVIIM1fHI9tM9Duf.1fDITHBtv@tmL9tIXHt,HqH~S1HH9t?H;TufDLDHH9xHuH;|ffDHI9k1f(fH(XL$f(T$d$ed$t$fW%\$$ Vf(f(1,$fH(Yf(YYfY\Xf(ff.@f(HH\L$0f(D$\$8fD(T$(DX|$ fA(DD$e\$8-T$(DD$D$X|$ d$\Xd$\f(f(\YXf(AXfD(f(fDWef(fA(XCd$t$0T$H"f(XYfHnXf(T$\f(NdT$HH^f(ff.ff(f(HYf(=XXYf(fD(\\D\f(Xf(fA(\iDYYf(YYf(XfWl\f(AXJfHf(f(YY\Xf(DHG@t~HFHtt@tkH9t.HXHt*HJH~A1DHH9t/H;tufHH9tHu1H;5Ff1Dt@ff(f(HYf(XXYf(\4X\\\f(YYf(YYf(fW-\f(Xf(HHfDSHHHYf(T$T$u]HHtNHff.f(ff(H*YHYf(\HuY\fT$H*Y IT$H[YfHdH=L1 H[иfDf(f(fHf(f(-YYYY\f(X\\f(fWf(YYf(YY\f(XGf(ffffXfYf(f\fX) $$L$HLGH?t HA`HtH>HHA`@HHIH JH5JH81 1Hff.H?IIHHWtLWHw8HBLL@Ht#LIHw8HHBLLHHHH 4JH5IH81 1HHLOH?tHu`HHu'IA1HHtsHu~H>HDHyIIH HH5HH81 1H@HytH HH;IH5HH81W DH bIHywf(f(HXXL$0T$\$f(= $$Xf(l$(\F^$$fEt$0D$HD$\t$f(AYXfD(t$@f(Xl$ l$(DXf(l$8fA(DT$0] $fEHoD$(D$DT$0AYfHnfHnT$@Xl$8fW-MX\\\ f(fA(\d$ f(YfD(EYDYL$Yf(\A\AXAXXCt$(fDD$Hf(ffEYYfYff(fXf\fA^)$$L$HXff.SHHD$fiD$VfH!H|$f(f(1HSff(\fW5f(DfH*HXf(XX^Yf(^YXXH9f\$H*Xf([\$YH[fDpH[f.f\L$H[Xff.ff(f(HDYf(Yf(AYXAYt$\f(X\\7f(AYf(YYAYfD(X=fDW\f(XfA(iAt$fHf(Yf(YYY\Xf(fDff(f(HYXX%4Yf(X\f(Xt$Xf(fW=\\\fD(DYYf(Y0YA\Xf(f(@t$fHf(Yf(YYY\Xf(ff.H8f(f(HS[$f(f(f(DX\f(XAXXYH^HW1f(fD(Xf.ffD(H*HXfD(DXDXXfA(XEYXf(fD(XEXYEYAYEYYYAXfD(XDXXEXAYY^XfD(H9]f<$H*Xf(X<$YH8@XY H8ff(L$ H*D$T$(Xf(d$f(|$,X ̯|$t$ T$($l$f(d$X\YXfW%Xf(f(Y$H8fDAWAVAUATUSfH~HH$f(L$d$ l$t$T$(A fHn/ T$(ffHnD,D,A*f.fA*f.f/$HT$8DD\$T$L$ŕHHE|$ AEf(YAE}E9DAD$D)D9A_D90CD$\$(D9TDff(AAA)A*:L$\$(T$Yf(\$Yf(\L$YffTݯf.!Qf(DYHc^$D\ӃxHcfYXDHyYH|$8$$HH[]A\A]A^A_XHH[]A\A]A^A_f H=,H5^IDH|$8HH[]A\A]A^A_H>H=VP1 Ƭ7Dff(D\$AAA)A*\$f(fDff(\$D)Bh*}L$\$fYf(\$fT8f.waQYaDff(\$D)Bh*L$\$fYf(\D$fT׭f.vL$\$L$\$T$\$T$\$Ht+tLGXHwXMtIx HIt1fH5HLt1Hff.fSXfD(fEL*Hf(H@5\D\f(f(\Hf(=f(fA(f(D+X\XAXXYH@^HW1f(fD(XffD(fA(H*HXfD(XDXXEXAYEXfA(fE(XEXAYAYAYAYYYXf(AXXXXYAY^XfD(H9]AXfA(|$l$DD$f(Rl$H|$DD$YfHnHffA(l$H*X\Ql$H@[^f(@XY-Df.f(fA(D$8AXDL$0d$(T$ f(DD$l$cQDL$0Hl$d$(D$fA(fHnfHnDD$X\T$ YfA(fW=ʫDD$XXf( l$HDD$|$8YfHnf.USHHHL$D$f.d$f(OfHHd$T$Fff.P~5 (f(fTf/fD(f(HS1=XD\fA(Ȑff(fD(H*HXXDXXA^A^YAYYf(XXH9f%H*^fTf/^f(YHHf([]HH[]f(DDHH0HEff(d$H*DD$T$g?HD-DD$T$H9d$~5D^f(XDYffHsHH*HfHH*YHH)Y%H)1XHHHH9HffAXHH)H*H*H HXYXYfH*^DYf(fTYfA(fTf.zfXYf(}\$ff(d$8H*XT$0l$(f(D$Xf(L$ \\$fH~D$\$X<fHnl$(^f(fH~fHnd$8\$^T$0D$\%ڤfWL$ XYt$\$YfDfXd$\f(Ld$f(YTfDfH*XD^fHH;5tKHtFHF tQtLHMtIx HIt1HfD1@L(fDHH5TH8*HHtOHFtBtLGHHwHMtIx HIt 1HDLfDH1H5TH8HHHtOHFtBtLGPHwPMtIx HIt 1HDL0fDHH5ZTH82HUHSHHH9tHHucHH9H5mTH85tHHHtHx HHt 1H[]fHF uHH5SH8}fDUHSHHHH9tHHucHHH5UTH8tHHHtHx HHt 1H[]fHFuHLH5SH8fDATUHHHGHGHHHu%GWHH ЉAH9uAHD]A\H5ٱ1xttYHaAH9tHH6H5SAH8DgH]DA\fHH5SH8AHD]A\fH@`H}HHtqHHtgH.H9Eu2HAHE HHEHCH趺HHuoH\HNHH52AH8fHHtOHF tjtLG@Hw@MtIx HIt 1HDLfDHH5rRH8HHH5zRH8jAVfI~ATfI~USHD$uefInuW\$ffIn,,*f.zNuLf*f.z>f/u8HHcfInHc[]A\A^AfDH[]A\A^DH=\H5@OADfDAVfI~ATfI~USHD$1uefIn#uW\$ffIn,,*f.zNuLf*f.z>f/u8HHcfInHc[]A\A^?fDH[]A\A^DKH=H5pNA DfDAVfI~ATfI~USHD$auefInSuW\$ffIn,,*f.zNuLf*f.z>f/u8HHcfInHc[]A\A^7fDH[]A\A^D{H=H5MAPD(fDAUIIIATI?UHSHHNHwMItCH9HF8HDHHH1L[L]A\A]@H9H=hH9LXMI[H~&1@ILH9"H9HH9un MHH1L[L]A\A]-DH9H=ثH9LXMI[H~&1@ILH9H9HH9uHL%ڻHH=NM1LHIMHL[]A\A]@HE0HDHH9t4HuH XH9t#HHH9tHuH9FfDHMA1HYE1 uLeH=M1LIMLIHHH5MH8_ HHH9t4HuH H9t#HHH9tHuH9fDHMAM)HYE1 uLeH= MuL;E1HMA@HMAuHLH1[]A\A]QATUSHH?HH1f(%X\H|~- "f(fTf/wtf(H1\f(ffH*HXf(f(XXX^^YYYf(XXH9Hf([]A\fHHHŨL$fHT$H*$$L9 0T$$$~- f(X^YYHtHKHH5&H)H)L)f(fYHHH0fHfH*XH*HHYYfH*^Yf(fTYf(fTf.zuHf([]A\f%( p/$$T$f(,~-f(^YAVfI~USHD$D$u.,f*f.z,u*HHcfIn[]A^DH[]A^;H=|H5`GAVfI~USHD$XD$u.,f*f.z,u*HHcfIn[]A^饸DH[]A^H=H5FZAVfI~USHD$D$u.,f*f.z,u*HHcfIn[]A^ŸDH[]A^H=\H5@FAVfI~USHD$8D$u.,f*f.z,u*HHcfIn[]A^5DH[]A^H=H5Ea:AVfI~USHD$D$u.,f*f.z,u*HHcfIn[]A^շDH[]A^H=<H5 EAVfI~USHD$D$u.,f*f.z,u*HHcfIn[]A^饶DH[]A^kH=H5DAAVfI~USHD$D$u.,f*f.z,u*HHcfIn[]A^UDH[]A^H=H5DAVfI~USHD$D$u.,f*f.z,u*HHcfIn[]A^DH[]A^KH=H5pC!AVfI~USHD$hD$u.,f*f.z,u*HHcfIn[]A^UbDH[]A^H=H5BjATSHLMtA$tA$HL[A\DHHHtYHHtHPHtLg A$Lt?A$HxHHuLDL%yA$ofAUATUSHLMt"A$tA$HL[]A\A]Hu,L%A$ЃtA$tA$LfH-ķ?IHtEtEID$E1L11H(H=˲II$xHI$MtpIEHLHHHIEx HIEtoHt:LMHEHHEtTLKH-ԟEtf.fD.zmukf.zeucf.z f/H@f(]ÐH,f LjfUH*f(fT\f(fVf.z2fT$L$d$8l$0f(DD$( $c d$8 $ff(5PT$f(fTFDD$(l$0XY f/Pf.jfA(f(f(^fA(YAYAY\f(XX^XXYf.XGAlH5cH,H8HH=i;zff(f(DVbf(H@]T$L$d$8l$0f(DD$( $ d$8 $ff(5T$f(fTDD$(l$0XYf/fD/t$8d$\f( fd$t$8fD(L$0ffAfXDL$(fYf(f\fX)$f( $T$\4$?4$fd$DL$(|$0f(fD(\fA(f(DD$8l$0d$(f( d$(D$f( $DD$8fl$0f(t$ $YfA(YYAY\Xf(Yf(YY\f(YX"^H@]^XXf.fDfDW҈D)$L$$} fd$t$8fD(L$0ffAfXDL$(fYf(f\fX)$f( $T$\4$|$0d$fDL$(4$f(fD(@ff(f(f/r, 5Vf(fTf.f.jUSHxf.f.f/~50- f(f(fTfTXYf/(f/f.fD(f()t$@EQ\\$Pl$T$fA(DT$0<T$$f(БT$DT$0l$D $f(fA(T$ \DXDT$AXf(DL$(<$>DL$(<$ffD/ DT$fD(l$T$ \$Pf(t$@fD.zfD/tzD $fA/wefA(l$P)t$0\$(T$ |$DD$ DD$f|$T$ \$(f(t$0l$PD $[f.7QfD(fA(f.fD(fTDXD^fA(AYXf.7QfA(l$PL$(|$ T$0t$$$D$@f(a$D$Xf(\$t$fH~Y{T$0fH~f($ҏ$D$0f(~\$ft$|$ L$($f.l$PfD(PPD^fE(EYAYfE(EY\>AY^!fD(AY\AYXAYAY^fD(\AYEYDYXA\fD(DYAYfD.AY^ҁ,fD(EYfD.D^fHnfLn|$hDY)X\$@t$(Yu\\$Xl$XYA\fD(XT$0L$0T$\$E^fA(Dd$`Xf(E^AXDT$@f(f(AXDD$Pd$ 8f(D$XD$\9|$hf$t$(L$0Yf/DD$PDT$@Y\$ l$XDd$`EA\f(\$0AXA\l$ [8f(D$\D$Xt$(D$f(<$Y|$f(\$0f(XYYD$ XDH,f5~fUH*f(fT\f(fVf.)fD~5x-h~f(f(fTfTXY4f/Hf.f(f(f(XXYYf.:^^XXHxf([]}f(Df.~f(fW܀!f(Qf(f(l$ \\$T$T$$f(臐<$\$T$l$ Yf(\Xf(<$•$Y:@0}Hx[]f(DfA(DD$T$T$$f($DD$YAYH5|HEH8 6aH=0ff(64H5+HH8H=0tfDttTf()t$@\$Pl$$_l$$f(D$0f(l$(\T$5T$$f(T$l$(D $L$0f(T$\Xl$DXf(<$DL$ syDL$ <$ffD/ R|l$fD(T$\$Pf(t$@T$ f(T$T$$l$xt$(HHQ|$ht$`f(HHfl$f(f(YYH*YY<$\Xf(f(\$@^f(T$X^f*X<$^Xl$f(^d$Xt$Pd$d$ Xl$8d$ 蜰 L$D$0$膰 YD$(l$8f/D$0t$P\$@T$Xf(f(T$P\$8C L$ D$0D$, YD$(\$8f/D$0T$PT$h\T$xL$`f(T$0 f/<T$0qf.T$pE„@t$pf(d$|$ f(f(YYYY\5<\$f(XXD$p\D$HĈ[]Xf(fDD$h~ =fD$`f\) $$L$ 5:f/t$xd$hL$`\f(d$P\f($خ f/x;$d$`fl$pf.E„tf.DЄ~%<t$`u9fWfW)d$@T$8T$pt$05:f(f(t$(f(f(fT 8;fT0;f/f(f(t$xf(^YYYXX^f(\YYl$ d$T$$輭 l$($T$d$f/l$ |$8t$0f(f(f(YYYY\Xf.T$pf*f(^Xf(^Xf(f(^^:fD$hL$`HĈf([]f(D~;t$`7fWfWT$hT$pt$Xf(f(fDf(f(fT 9fT9f/f(f(d$xf(^YYYXX^f(\YYl$8t$0T$@\$P# l$(t$0f/l$8Z\$PT$@B|$hd$Xf(f(f(YYYY\Xf.T$pf*f(^Xf(^Xf(f(^^8f(f(d$x^YX^f(YY\XYY7HĈf([]f(fDf(f(t$x^YX^f(YY\XYYf(f(5YYYl$p\f(XYYYY%5\X$$t$`f.t$pd$P~q7l$`f(fTfTf/f(f(|$h^YXXf(d$x^f(Y\f(YY\$f(l$@\$f(fW\6fW\ $HĈ[]\f(f(f(D$x^Yf(t$hX^f(YY\XYYnD$hL$`藩 f(f(f.L$`D$Po f~-C7f(f(t$pY)l$@YYf(\3XYYYY3\X$If.f(,$~-6)l$@d$PL$`D$h^^t@SHT H f(fHnfHnfH~flH@)D$f($裑$tf/"3f($>&3fHn\$\$$H|$ fHnf( D$0\$\$ tR\$8PH tH H=5 1p |2H@f([ffHnv^2uH@fHn[KOH $HH= HL1@p $fH m@f(H $H= o $YDf(H H=^ $o $$AUATUHSHL%RMSH LRID$Hl$H$H9H=AH9LXMMHM~(1fDItH9H9HI9ut7H@8IHt*LHt$1HIHL[]A\A]Ht$L1ɺLHI[]LA\A]It$VtSE1 H^uMl$H= 辌u&HLIMuIH$E1k@H9/ID$06DHQH=zQH0HGHHIMI}Hb@H9t9HXHHqH1@HH9H9TuIE(HP@HQQL%QM+L-PMHHH9t4HuH5@H9t#HHH9tHuH9&fDIt$V f.IHHH911H=LLDHHIEx HIEtQIIEHIELlL%OH!?H5 H8j4LI:lDAWAVAUATIUHSHeH=\IHD\DƃoHcH;\V1 f~.H9})HcHT9}9|9A9HHH;XL A$tA$HM1LLHHmX(H芀I$xHI$uL0HExHHHELH[]A\A]A^A_M}`IE`MCMGAtAMw(Mt AtALHLD$FLD$HI/M9w(I}`M}`HtHx HHoMtIx HIIMtIx HI#H=ZHAD5ZDxyHcH;\~d1 ~pU9}_)HcHD9}@I$HI$LH[]A\A]A^A_鸁G19A9LcIIA;_D;5.ZD)PIcHHHHHD9HMHHD9HMHtHHH襇AA_M'D5YA$DD95Y:A@IcHq|HH`D5YLcD5tYIHqYIA99LH+IHxE1E1@W1Ix HI Ix HIM.I#HLIZLLLD$LD$}HoH]+HXHXXL A$CBLcIILLLD$}LD$A$I?M'tA$HHH^LQLDff.@AWAVAUIATIUSHH8HD$ H:HD$(HHGUHD$ M1IEH$HtHuyI $tHL$IUH4HT$ HLIH  jLQHPLD$8gH xVHH|tH|$DHH8H L 2SAH H5 H81}XZH|$HtHx HHHExHHE H H=' 1H8[]A\A]A^A_fHVI<$tH|$HGH5OHHHЅHm7tH|$HtHx HHtBHUnHHU`HHD$}HD$H8[]A\A]A^A_HD$|HD$|fDH|H81[]A\A]A^A_H H= h15[zfDLt$ LM$6QLH~>I$MHu)VfDH!LL)HDIGIHt/H0HHQwH9uHExHHEuH{H蘃HHmM9u^f.IM9GILL8LztރH6LH H5 H813{Xff.AVAUIATUSHH=EHGHH;5u.1LzIHHL[]A\A]A^LH,IMu=HH4LC`L MIxI9tzID$HHW@A$@HXHtTHJH~61 fHH9t'L;duHC`IxHIuL0z蛀IHt+E1HI9tHuL;%4tH)4LH5x H81yuIL˂tLC`HC`MrUIl$H_1 HH9t I;|u&E1KtH9tH|$hH|$uIL9uAWAVAUATUSHHG:HIHH;3H5nF1xHHH CHELd$H$H9H=2H9LXMMHM~.1@ItH9H9HI9u+H@8HDHHt$1HHIHExhHHEu^HxTHL!tI}`IE`H+yHCHPHl2H5U E1H81wHL[]A\A]A^A_fDHuVtTE1 H^uLmH= }u*LLIwM3}IHE1fH9HE0fDHt$1ɺHyI@HwHHL~IH1I}`H(HLgL9HEHOIT$A$@w@jI$XHtWHJH|1HH9cH;luIE`HIHH<'v2M$L9tMuH;-0tfHDHH9tH=2HUHYkIHtA$IFH5o:LHHHHH'"H9H="H9}H} ID$L=v2LMH=/ mHLLAIhMI$xHI$HExHHEIFH5<LLHHЅ IExHIEuLL[1WHfHL[HIH5 H8]I$xHI$uL[HEHHEHn[fH %HGHl$8HD$0H9LWL9LXMMQM~%1ItH9L9HI9uH@8HHHt$81HIMI$f aHI$xHI$KHfDM9EHT$H * LHXBpHt$81ɺ\InHwVtnE1 LvuLoH=_ `GLHAIIZMK`HHH5< H8[H9HG0H_H5 H8[HHH9t.HuH5H9tHHL9tHuI9VHwVAL)Y@AWAVAUATUSHH HHH Hy  HAH|WHH HD$PEHD$htEL%(H=#IT$Lw[HH; tH|$PHH9G fHt$xH)D$poeH$H|$PHx HH HD$PH<$ H?#H @#o1HIM H5#L _ÅcIx HI H5#H1RH|$PIH zYH|$PIHq L--H=!HD$XIUL1ZIHtAL; ,HI9ALLL$^LL$HD$`AM̓tALl$hIx HIGH|$PHtHx HHi H|$hHD$hLt$XE1HD$hH|$PHD$(Lt$8Hl$LHL$(Ht$`E1AL׼?fLl$hHtHExHHEv LLLHD$hoSH|$PLDHD$hHl$E1E1HD$(HD$XHHD$8HD$PHD$ HD$HD$0HD$XHi]HD$`HƋD$tHD$hE11Hl$@MLD$0HL$(AHT$8H|$߻HD$hHD$MtIx HI HD$hLt$PMtI$xHI$ L%+H=tHD$PIT$LWIH tAL|$PIWHBpHrH@HeLLILd$hMlH|$PHx HH HD$PIx HI L5*H=HD$hIVL3WIHgtAL|$hIWHBpHH@HHt$LILt$PMH|$hHx HH HD$hHtHx HH\ HD$PIFIFH HH AFAVHH Љ‰H9 YIHID$ID$H HH AD$AT$HH Љ‰H95 t$H[YHHot$H8 IFIFgH HH' AFAVHH Љ‰H9L XIHBID$ID$[Hi HHk AD$AT$HH Љ‰H9 XHmvL=.(H=gIWLTHHtEHEH5(HHHIM HExHHEIGH5(LHHHHg Ix HIEHl$htEH='fInfHn1H\$pflHL$H)D$pMH|$hHD$PHtHx HHHD$hHExHHEL|$PMyIx HIH-&H=HD$PHUHqSIHtAL|$hIGH5k'LHHgIMH|$hHx HHIGH5& LHD$hHHGHHl$hHIx HIEtEfInfHn1HH=&flHL$)D$pbLHD$PHExHHEH|$hHx HHHD$hL|$PM Ix HIHD$PIFIFHHH-AFAVHH Љ‰H9RDUIHID$ID$H_HHhAD$AT$HH Љ‰H9THJމLrHt$`Lt$f;PHHp1NfDH8IH|$PE1侜Hl$E1E11HD$HD$ HD$HtHx HHgH|$hHtHx HHaHtHx HHH H=O 13HD$HxHL$HHuH<$tH $Hx HHfMtI$xHI$[HL$HtHx HHMMtIExHIEBHL$ HtHx HH4HT$HtHx HH&MtIx HIHEx HHEtHĘH[]A\A]A^A_fDHHLfD{MLHD$PHHHl$1E1E1H$E1侚HD$HD$ HD$6DLKVHK~HKLKHKLKHxKHhKH߉t$(TKt$(t$(?Kt$(fDt$('Kt$(fDLK\HHE11RL * H H8H h H5ȩ 1JXZ_f.HJ}LgLGA$tA$AtAHLD$PxHHu vJLD$PHt$pLLd$pHD$xWH$I$HI$L+JH|$PHfDHHT$H $QH4$HT$1|H5y1LoOLO‰H9OHHH5 H8K%LpI0L`IIHPICIfDsJLHD$PIHGHHl$@LL|$ME1Iƾ@Ix HIt(MtIx HIt3H|$PfLLL$0t$(HLL$0t$(@Lωt$(HH|$Pt$(fD 11HI~Hl$1E1HD$E1E1E1HD$ HD$0H|$PIHl$Hx HHHD$PMtIExHIEH HD$`HzOHD$XHƋEtEH\$PE1Ld$HD$PMH\$0H\$`LD$(HL$0HHA9xLt$PMtI$xHI$HD$PLd$hMtIExHIELLLHD$hXDPMHt$XM\IHl$M4 IExHIEHl$1E1HD$E1E1HD$ HD$@FLd$hLxF A^ Hl$nfDHBhLLHHxI{DAt$"fD FLt$P+H51LKfLL‰H9Hy HH5I H8GA^ LEH51LK%LK‰H9HC H`H5! H8HD$hIH'LHl$@L|$E1ɾ{Hy1E1E1H5 H3 LL$(H81AHl$LL$(HD$HD$ HD$DIHl$@L|$1E1ɾ@Ll$ M1L|$Ld$IE1Hl$E1HD$L@Hl$@L|$1E1ɾHD$`H=PH1Ht$pLL$pHLL$=LL$HIH@H;#YH;LLLL$?LL$HD$IExHIE&HD$HD$hHHl$1E1E1HD$HD$ ML|$Ld$ILl$ M1Hl$E1E1HD$LHl$@L|$E1ɾ^fDK?%fD;?QfDIL|$Hl$@1۾ ?fDAnL>Hl$h fD>pfDH5a1LWDfGLD‰H9HVHH5q H8@LHl$@L|$E1ɾNfDA\$L.>H51LCL?D‰H9HHH5r H8?U?L[IHH[9IL=A9H Hq='IHH5y H8i?fLHl$@L|$E1ɾ-HLT$=LT$H7H5ș H8?{I8I1ILHl$@L|$n8HH51HIAfL|$LL|$LLL$H>HHH5Au H8k:>Hy>H>>HHH5t H8:q_>HL>HqH\H5t H89 >HH0H5t H89l=HHH5Xt H89=HHH5,t H8V9X=H=H(I1ff.H_f/s^f(ff/w@Hhf/wFf( $2 $X^WX?Hhf8X H|$f(^X )D$f(Yf()D$ f(XY)D$0f(W)D$@f(ZY)D$Pf(T$ $}U $T$H|$0Yf( $VU $^f(-@f(ff/lf/ V`@f/f. .USHxf/ v5 \f(f/df(L$Y0H|$0Hf(f(P$)D$0f(NHD$`)D$@f(L)D$Pf(YJT$mL$Y\f/ $L$f/vzf(H|$(Ht$ T$3T$$D$(L$XY X\ XL$ Yf(f(XXYYX^\fHx*[]Yrff(Hl$0jXH\cf(#L$)D$0f( Y\$)D$@f()D$Pf($Yf(d$R$Hd$Yf()D$0f()D$@f($)D$Pf(R$L$\$^CfU1H1SH Cvu f(BEH[]ff.ATIUSHg ohP$G@d$Xg(fWH |$HHDd$`g0Dg|$PDO`f(d$h%DwDGXL$XD$xt$pf(\w8$f(fE(fA(\$HAXf(YA\AYA\XT$Pf(f(AYY\Xf.fD(fD(f\$Xf(T$`*Dl$pXXDX^YDXf(^DXf(A^fD(DXf(XD$hXXD^Y^$EXfE(YY\$xDYf(Yf(YD\fA(YXfD.BX4$Xl$fA(T$@fA(Dt$8DL$0DT$(Dd$ Dl$4$l$8L$D$$8Y'FHf/D$Dl$Dd$ DT$(fHnDL$0Dt$8T$@wZ9"Al$hfE11fEfDE$EL$H=El$X HĐ[]f(A\fEfEfDAl$h$L$E$EL$El$XHĐ[]A\f(f(fA(D$DL$@DT$8Dd$0D|$(D\$ t$l$y+DL$@D$DT$8Dd$0fD(f(D|$(D\$ t$l$,\$Hf(fA(Dt$8DL$0DT$(Dd$ |$DD$*HfDt$8DL$0|$fD(fD(DT$(Dd$ f(f(DD$fHnff(f(fT%f/vf(H`H^f(H f/HYXH YXHYXH YXHYXH YXHYXH YXHBYXYXYXHV`HGYH HXYXH YXHYXH YXHYXH YXHYXH YXHYXYXYXYXB^f(ÐH8f($ff.zuf/wq +Y $H|$(Ht$ D$f(+D$Y$\$ t$(\$t$/\$L$H8f(YYf(Df(7-fH8f(f.HH~-L$f(YL$T$ T$ fW(L$\$d$ ~-$f(f(Yd$t$(T$(fW(d$f(D$(XX $f(XD$0D$0\D$8T$8D$0HH\ff(f(HHY $f(\$L$d$D$(T$(f(fW'd$L$Yd$\$(Y $XXf(Xf(D$0D$0\D$8T$8D$0HH\ff.f(X\$\$\\$\$\T$T$\$\T$d$\$T$\XXf(XD$D$\D$T$D$\ff.@f(Xd$d$\d$d$\T$T$d$\T$f(DD$|$Xd$A\T$T$X\T$T$\\$T$\$\T$t$l$T$\Xf(XXT$T$\T$\$T$\Xf(XD$D$\D$T$D$\ff.fAUIATIUHSHHHf/> f(>f/&f/ ADgO11fD(f(~5B-rBDYfD(f(f(f(AYYXY^X^^X^XfD(D^DXfDTfD/wD% BD BAYEYDY f(AXDAA^IAYfA(A<$A^f(X@Y^X^XY^DX^XXfD(D^fDTfD/wEYAYtDXEYDMHH[]A\A]@fA(\ff(A\AE@ff. f(Qf(L$DXl$DD$YA^f($*l$f$DD$L$f(f.Qf(+5 ?Xf(^>YYYX>X5>YYX>X5>YYX>X5>YYX>X5>YYXs>X5>YYXc>X5>YYXX^5;Y^=>YX=>YX=>YX=>YX=>YX=>YX=>YAU>YX>XYX >YX>YX>YX=YX=YX^=%>Y^Yf/ >, >Yf(\>YX =YX>Y\ =Y\=YX =YX=Y\ =Y\=Y^f(\=YX=Y\=YX=YXYY^A $ =Y\ =YX =Y\ =YX =Yf(\ =^XY]Pf. p~-Pf(fWMQY Fff.Y^ CQDg9d$(H|$8D 99Ht$0D8D^D^fA(AYDYXD\ 8YXc9YDYX9D\ 8YXE9YDYX8D\ 8YX'9YDYX8D\ 8YX 9DT$ YDYX8D\ `8YX8YDYX8D\ B8YX8YDYXe8D\ $8YX8YDYXG8D\ F8YYDYX98D^DX kDL$Xd8l8X DD$XT$YX?8YXC8YXw8YX38AYYX*8YX&8YX"8YX8YX8YX8YX8^f($ $DL$|$0t$8fA(f(DT$ T$YYDYY\ 7YAXAYX 7AYYX 7AE7XYA$X 7YX7YX 7YX7YX r7YX7YX b7YX7YX R7YXv7YX 7YXf7YYX^7YXb7^^7Y\Z7Y\V7Y\R7Y\N7YX "\B7b7DD$d$(Y%-5XY~-\7YX17YfW\7YX7Y\6YX 7Y\6YX6Y\7YX6AYYX6YX6YX6Yf(X6Y^f(YYYX\YYuHH[]A\A]HHf( $' $f(f( $  $f(f( $ $f(D$f(DD$L$$L$d$DD$$f(ff.@fH8f(f/f(v7f/r_5=f(f(fTf.v3H,ffUH*f(fT\fVf(f.f/w;f/vE-f/v7\f(^f/Xwf(^X\f/rf/(7f/f(%7Y^f(Y\ 7YX7Y\7YX6Y\6YXYD$f(T$L${L$T$^\\D$XH8d$H|$(D$#fL$f.YDL$)L$f/'\^f(fDY,у~,@ff(*ȃ^X9u\55H8f(@f1ҾH=1  f(f( 855\\%4\%4\%4YX 5Y\4YX 5Y\4YX 4Y\4YX 4Y\4YX 4YX4YX^YY%4H8XXff.@f.f(rfHf/wTf/f. jE„u&f. D„uf.zJuHHfHnHf/wwf. E„uf. D„uf( $! $D$f(?T$ $fWf(Hf(^\^f. 0E„Xf. D„Bf( $1! $~D$f(fW $T$~n^\fWf(^Dff.@AVGAUATIUSHHDŽ$HDŽ$v(ff(HĐ[]A\A]A^f.HD$ L$(D 5f(f/52f/t$0f(f(^Yf/t$(|$ f(f(YYYf(\Xf. t$(|$ f(f(YYYY\f(XD$f.fI~ YHD52AD52D-HD$fLnfHnD2IfLnfE(fH~ff(d$fD(4fDDX-w2DX5n2Af(fD(fD(f(T$fInA^A^f(f(AYYf(Y\f(AYXf.{D$fMnfInE^XfI~\$X\$A^fA(fA(YAYf(AY\f(YXf.~fHnEXEXd$A^XXfE(E]d$DYD$0AYfA/f(\$(D$ fIn%v/YYYYd$T$(L$ YY\Xf.H>/YY\\f(f(̃D$ L$(l$d$t$ |$(f(d$l$f(f(YYYY\Xf. r0l$d$YYl$d$f(f(f(YYY\f(YXf.3f( f.D$d$f/%/fD(f/%/vA$D$ L$(DL$t$ l$(f(fD(DL$f(f(AYYYAY\f(Xf.iff/t$ \/f(t$(YYf.2,f/d$  f5T.HE1-*/fLnt$0f(ff/t$( /H$5./DD$|$FDL$yDL$|$DD$?ff/-,T$ L$(YY~,fW F\CDA$fHĐf([]A\A]A^fff/f/t$ -.f/SDY b-f(fWƾ-A\f/D nA%-,-H$DD$|$DL$DD$|$DL$ z-$$YYEfA(f(fA(YYY\f(YXf.fA(f(f(f(E fHD$ \$(-*f(HD$o* f.z L@fVp;o,f/)DY +-\,D\fD/ff(A$fAYfA(AYf(Yf(YY\fA(YXf.DA^A^tff(A$ff(DHiE1fLn@5*At$0fD(f(KH/-_+E1fLnfA(f(fA(t$xD\$pDT$hDL$`Dd$XDt$PDl$H|$@l$8S t$xD\$pDT$hDL$`f(Dd$XDt$PDl$H|$@l$8fA(d$xt$pDD$hD\$`DT$XDL$PDd$HDt$@Dl$8 d$xt$pDD$hD\$`f(f(DT$XDL$PDd$HDt$@Dl$8L$(D$ fA(f(DL$DD$|$O DL$DD$|$PT$L$(f(d$D$ l$ d$l$fA(f(f(DL$f( DL$L$(D$ l$d$ l$d$D$fI~+\$(f(f(l$d$f(y l$d$f(f(f(f(f(O f(f(D$ L$(1 l$d$f(*ff.AVfAUATUHSHPf/w&f.ǹEf.E!ЍWȃvE1HP[]A\A]A^fMuHIIT$D$ $@ $D$AŋET$tuH5$T$L$IH$L$IT$fۺHD$ $U $D$t&t!1L$$HP[]A\A]A^@H|$HHt$@ $  $~%-6'\$@f(T$HXf(T$fTf/H$~-$fEfWfD/f(Y|$Y$T$AA^l$8t$0f(f(\$(fTfTT$ h %@'T$ \$(t$0f/l$8~%<=,r=b%YYf(f(fD(YYDY\f(YAXf.YA\$A$Y\$(T$ fH~f(fTfTfH~f( 5}&%T$ \$(f/rS%$YYl$|$f(f(YYYY\f(Xf.YfHnYfHn\\ff(Yf(YY\fYXf.]fff.A$e_,$f.Ef.E!9AnA\l$fA&A\$$Tf(Yf(YY\fYXf.A9fANA$fYf(\$mD~-L$8T$0fW\$(\$ )l$z f(l$t$ \$(T$0$L$8~%E1Vff(f(ĉ$$Bf(f(fd$l$d$l$uL$D$d$ d$ f(f(|$ ~%|$ %f.Vf(HGHTffDf(f(f(HY\X@H9u\YÐfH8f(f.f/f/-H )H^\f( ff(f(f(HY\X@H9u\f. YtQ^H8f(`1ҾH=15 H81ҾH=1 H8fDf(T$YY\L$?T$Hүf$L$f(fT5OfHnf/- H1(HY\f(f(f(HY\XXH9uf(T$(\$ d$L$t$g\$ d$t$L$\YT$(YY\$ %'f(f(T$Y\%'YX'\'Y\\'f(Y\\%'f(Y\\y'f(Y\\m'f(Y\\%a'f(Y\\U'f(Y\$\\C'Yf(\L$TL$X &'\$f(T$f( $\YiYL$ H8^XYf.f(T$L$t$t$Hf=L&fD(L$fHnH&T$^H\f( ff(f(f(HY\XhH9u\Y-f.AYw3Qf(^l$ f( $ $f(tf(T$l$L$T$l$L$f(뢐@f(f(fT%8f/^f(r+HHt^f(YHf(XH4f/H HYXfUYYXH YXHYXH YXHYXH YXHYXYXYXYXBHGHJHFHXH4H HYXYXH YXHYXH YXHYXH YXHYXYXYXYXB^f(Ð *H%* X-YXY^f(XXYX(&X%@f(%)Y^ 4XYX TX)Y^X)Y^)YX%YX%^%4YX%p&XL)Y^%YX%@)X,)Y^%ĩYX%()X)Y^X)Y^f()XYYX(^D'YX(X (Y^X (YY<X(^f(Xf($=(5(X-YYYf(Xf(XXX\^%,XY\XX%$\^4XYX=\XXD\X5 (Y^-(Y^%YXX%X\X-'Y^%YXX%P$\X5'Y^%YXX%'\X5'Y^%YXX%&\X-`'Y^Xf(-P'Y^pYXX&\X%('Y^%YXX&\X%'YY &^YXX&\^XXf(ff.pf(f(fT%hf/^f(&HH^f(YHf(XH4f/H HYXfUYYXH YXHYXH YXHYXH YXHYXYXYXYXBHwHJHFHXH4H HYXYXH YXHYXH YXHYXH YXHYXYXYXYXB^f(ÐH%HФf( tf(@\ \\\YX HY\YX 8Y\YX (Y\YX Y\YX YXYX^YYXff.@Hf(f/f(ңY^f(Y\YXY\YXY\YXY$f(L$*JL$^\\$Hf.f,$Df.w~f.zxf.zu  f.{fuH1Ҿ1H=D$ ~ ץD$fWfTfV H@,cb[HlXHcHf(\ ??YX ?YX ?YX?YX?YX>YX>\ x>x>YXt>YXp>YXl>YXh>YXd>YX`>\ ==YX=YX=YX=YX=YX=YX=\ F=F=YXB=YX>=YX:=YX6=YX2=YX.=\ <<YX<YX<YX<YX<YX<YX<\ <<YX<YX <YX<YX<YX<YX;\ {;{;YXw;YXs;YXo;YXk;YXg;YXc;\ ::YX:YX:YX:YX:YX:YX:\ I:I:YXE:YXA:YX=:YX9:YX5:YX1:\ 99YX9YX9YX9YX9YX9YX9\ 99YX9YX9YX 9YX9YX9YX8\ ~8~8YXz8YXv8YXr8YXn8YXj8YXf8\ 77YX7YX7YX7YX7YX7YX7\ L7L7YXH7YXD7YX@7YX<7YX87YX47\ 66YX6YX6YX6YX6YX6YX6\ 66YX6YX6YX6YX 6YX6YX6\ 55YX}5YXy5YXu5YXq5YXm5YXi5\ 44YX4YX4YX4YX4YX4YX4\ O4O4YXK4YXG4YXC4YX?4YX;4YX74\ 33YX3YX3YX3YX3YX3YX3\ 33YX3YX3YX3YX 3YX 3YX3\ 22YX2YX|2YXx2YXt2YXp2YXl2\ 11YX1YX1YX1YX1YX1YX1\ R1R1YXN1YXJ1YXF1YXB1YX>1YX:1\ 00YX0YX0YX0YX0YX0YX0\ 0 0YX0YX0YX0YX0YX 0YX0\ //YX/YX/YX{/YXw/YXs/YXo/\ ..YX.YX.YX.YX.YX.YX.\ U.U.YXQ.YXM.YXI.YXE.YXA.YX=.\ --YX-YX-YX-YX-YX-YX-\ #-#-YX-YX-YX-YX-YX-YX -\ ,,YX,YX,YX~,YXz,YXv,YXr,\ ++YX+YX+YX+YX+YX+YX+\ X+X+YXT+YXP+YXL+YXH+YXD+YX@+\ **YX*YX*YX*YX*YX*YX*\ &*&*YX"*YX*YX*YX*YX*YX*\ ))YX)YX)YX)YX})YXy)YXu)\ ((YX(YX(YX(YX(YX(YX(\ [(YXW(YXS(YXO(YXK(YXG(YXC(\ ''YX'YX'YX'YX'YX'YX'\ 1'1'YX-'YX)'YX%'YX!'YX'YX'\ &&YX&YX&YX&YX&YX&YX&\ %%YX%YX%YX%YX%YX%YX%\ f%f%YXb%YX^%YXZ%YXV%YXR%YXN%\ $$YX$YX$YX$YX$YX$YX$\ 4$4$YX0$YX,$YX($YX$$YX $YX$\ ##YX#YX#YX#YX#YX#YX#\ ##YX"YX"YX"YX"YX"YX"\ i"YXe"YXa"YX]"YXY"YXU"YXQ"\ !!YX!YX!YX!YX!YX!YX!\ ?!?!YX;!YX7!YX3!YX/!YX+!YX'!\  YX YX YX YX YX YX \  YX YX YX YXYXYX\ ttYXpYXlYXhYXdYX`YX\\ YXYXYXYXYXYX\ BBYX>YX:YX6YX2YX.YX*\ YXYXYXYXYXYX\ YX YXYXYXYXYX\ gwYXsYXoYXkYXgYXcYX_\ YXYXYXYXYXYX\ MMYXIYXEYXAYX=YX9YX5\ YXYXYXYXYXYX\ YXYXYXYX YXYX\ YX~YXzYXvYXrYXnYXj\ YXYXYXYXYXYX\ PPYXLYXHYXDYX@YX<YX8\ YXYXYXYXYXYX\ YXYXYXYXYX YX\ YXYXYXYX}YXyYXu\ YXYXYXYXYXYX\ [[YXWYXSYXOYXKYXGYXC\ YXYXYXYXYXYX\ ))YX%YX!YXYXYXYX\ YXYXYXYXYX|YXx\ OYXYXYXYXYXYX\ ffYXbYX^YXZYXVYXRYXN\ YXYXYXYXYXYX\ 44YX0YX,YX(YX$YX YX\ YXYXYXYXYXYX\ YXYXYXYXYXYX\ iiYXeYXaYX]YXYYXUYXQ\ YXYXYXYXYXYX\ ?YX;YX7YX3YX/YX+YX'\  YX YX YX YX YX YX \ m YX YX YX YX YX YX \  YX YX| YXx YXt YXp YXl \ s YX YX YX YX YX YX \ Z Z YXV YXR YXN YXJ YXF YXB \  YX YX YX YX YX YX \ ( ( YX$ YX YX YX YX YX \  YX YX YX YX YX{ YXw \ YXYXYXYXYXYX\ eeYXaYX]YXYYXUYXQYXM\ <YXYXYXYXYXYX\ ;YX7YX3YX/YX+YX'YX#\ YXYXYXYXYXYX\ YXYXYX YX YXYX\ YXYXYX|YXxYXtYXp\ WYXYXYXYXYXYX\ YXYXYXYXYXYXDf/f(rJf/v f/^DX 00^ f/wbHvf(Yf/L$L$f(\X^NH\f(Ðf(YXXYXYXYY^#HXf.f(fWtf(f(Yf/Hf/ ~r@f/~YXzYXvHYDf/ H$wf($D$f(YD$\}Hff/ }}rFDf(L$)L$$f( $Y\}H\@}ff.@f(Yf/Hf/ |f(fW" $f(Yr+ $D$f(:YD$HT$mT$$f(  $Y}H\ff/rD|ff.@,d;5H̅HcHf(T2T2YY\H2Y\Y\Yf(X1 1f(\Y\f(Y\1Y\1YX1Y\1YX1X21 21f(\Y\f(Y\1Y\1YX1Y\ 1YX1X0 0f(\5Y\f(Y\u0Y\q0YXm0Y\i0YXe0X/ /f(\Y\f(Y\/Y\/YX/Y\/YX/XO/ O/f(\Y\f(Y\3/Y\//YX+/Y\'/YX#/X. .f(\:Y\f(Y\.YX.YX.Y\.YX.X . .f(\Y\f(Y\-YX-YX-Y\-YX-Xl- l-f(\Y\f(Y\P-YXL-YXH-Y\D-YX@-X, ,f(\?Y\f(Y\,YX,YX,Y\,YX,X*, *,f(\Y\f(Y\,YX ,YX,Y\,YX+X+ +f(\Y\f(Y\m+YXi+YXe+Y\a+YX]+X* *f(\DY\f(Y\*YX*YX*Y\*YX*XG* G*f(\Y\f(Y\+*YX'*YX#*Y\*YX*X) )f(\Y\f(Y\)YX)YX)Y\~)YXz)X) )f(\IY\f(Y\(YX(YX(Y\(YX(Xd( d(f(\Y\f(Y\H(YXD(YX@(Y\<(YX8(X' 'f(\ Y\f(Y\'YX'YX'Y\'YX'X"' "'f(\N Y\f(Y\'YX'YX&Y\&YX&X& &f(\ Y\f(Y\e&YXa&YX]&Y\Y&YXU&X% %f(\ Y\f(Y\%YX%YX%Y\%YX%X?% ?%f(\S Y\f(Y\#%YX%YX%Y\%YX%X$ $f(\ Y\f(Y\$YX~$YXz$Y\v$YXr$X# #f(\ Y\f(Y\#YX#YX#Y\#YX#XT# T#f(\X Y\f(YX8#Y\4#YX0#YX,#Y\(#YX$#X" "f(\Y\f(YX"Y\"YX{"Y\w"Y\s"YXo"X! !f(\Y\f(YX!Y\!YX!Y\!Y\!YX!X5! 5!f(\9Y\f(YX!Y\!YX!Y\ !Y\ !YX!X  f(\Y\f(YXd Y\` YX\ Y\X Y\T YXP X f(\Y\f(YXY\YXY\Y\YXX f(\Y\f(YXY\YXY\Y\YXXa af(\eY\f(YXEY\AYX=Y\9Y\5YX1X f(\Y\f(YXY\YXY\Y\YX|X f(\Y\f(YXY\YXY\Y\YXXB Bf(\FY\f(YX&Y\"YXY\Y\YXX f(\Y\f(Y\qY\mYXiY\eY\aYX]X f(\Y\f(Y\Y\YXY\Y\YXX# #f(\'Y\f(Y\Y\YXY\Y\YXXn nf(\rY\f(Y\RY\NYXJY\FY\BYX>X f(\mY\f(Y\Y\YXY\Y\YXX f(\Y\f(Y\Y\YXY\Y\YXXO Of(\[Y\f(Y\3Y\/YX+Y\'Y\#YXX f(\Y\f(Y\~Y\zYXvY\rY\nYXjX f(\Y\f(Y\YXYXY\Y\YXX0 0f(\<Y\f(Y\YXYX Y\Y\YXX{ {f(\Y\f(Y\_YX[YXWY\SY\OYXKXf(\ Y\YXYXY\Y\YXXf(\ A!YXY\YXYXY\ Y\ YXXf(\ tYXpY\lYXhYXdY\`YX\YXXXf(\ oYXY\YXYXY\YXYXXf(\ BYXY\YXYX Y\YXYXXf(\ mYXiY\eYXaYX]Y\YYXUYXQXf(\ Y\Y\YXYXY\YXYXXf(\ ;Y\Y\ YXY\Y\YXYXXf(\ fY\bY\^YXZY\VY\RYXNYXJXf(\  Y\ Y\ YX Y\ Y\ YX YX Xf(\ 4 Y\ Y\ YX Y\ Y\ YX YX Xf(\ _ Y\[ YXW YXS Y\O Y\K YXG YXC Xf(\  YX Y\ YX YX Y\ Y\ YX YX Xf(\ d YX Y\ YX YX Y\ Y\ YX YX Xf(\ p( YX$ Y\ YX YX Y\ Y\ YX YX Xf(\ g Y\c Y\_ YX[ YXW Y\S Y\O YXK YXG Xf(\ Y\Y\YXYXY\Y\YXYXXf(\ EY\Y\YXY\Y\Y\YXYXXf(\ $Y\ Y\YXY\Y\YX YXYXXf(\ cY\_YX[YXWY\SY\OYXKYXGYXCX f(\ Y\f(YXY\Y\YXYXYXX f(\UY\f(YXYXY\Y\YXYXYXX0 0f(\lY\f(YXYXY\ Y\YXYXYXXg gf(\Y\f(YXKY\GY\CY\?YX;YX7YX3X f(\Y\f(YXY\~Y\zYXvYXrYXnYXjX f(\YY\f(YXY\Y\YXYXYXYXX  f(\Y\f(YXY\Y\YXYXYXYXXf(\ 7YX3Y\/Y\+Y\'YX#YXYXYXXf(\ .vYXrY\nY\jYXfYXbYX^YXZYXVXf(\ Y\Y\Y\YXYXYXYXYXXf(\ Y\Y\Y\YXYXYXYXYXXG Gf(\Y\f(YX+YX'YX#YXYXYXX f(\FY\f(Y\nYXjYXfYXbYX^YXZYXVX f(\Y\f(YXYXYXYXYXYXYXX f(\Y\f(YXYXYXYXYXYXYXXf(\ +YX'YX#YXYXYXYXYXXf(\ vYXrYXnYXjYXfYXbYX^YXZYXVXf(\ YXYXYXYXYXYXYXYXXf(\ YXYXYXYXYXYXYXXf(\ OYXKYXGYXCYX?YX;YX7YX3Xf(\ YXYXYXYXYXYXYXXf(\ YXYXYXYXYXYXYXXf(\ `HYXDYX@YX<YX8YX4YX0YX,Xf(\ YXYXYXYXYXYXYXXf(\ YXYXYXYXYXYXYXXf(\ YAYX=YX9YX5YX1YX-YX)YX%Xf(\ |YXYXYXYXYXYX|YXxXf(\ YXYXYXYXYXYXYXXf(\ :YX6YX2YX.YX*YX&YX"YXXf(\ -YXYXYXYXYXYX}Xf(\ YXYXYXYXYXYXXf(\ {RcYX_YX[YXWYXSYXOYXKXf(\ "RYXYXYXYXYXYXXf(\ P1YX-YX)YX%YX!YXYXf/8Prnf/w<fD/%rAYDYd$A\YX$fA(A\Df(T$0L$pYd$`Dt$XDd$PD|$@Dl$8\$f(ЕL$pd$`XDt$XDd$PD|$@Dl$8$f.$|$P$|$x|$p|$HfDfd$@*YD$fD|$8*XD$XXt$YfWD$ t$0t$0d$@f(D|$8f(YY$XD$`Yt$^D$HYDXXYf/bf\$PL$xT$f(f(%A^YAX^YD^A^fDfA(^~==L$0\$@)|$ fWf(l$Yd$ l$d$D$Hf(l$8Xf(YߓL$0=):fEd$l$8fD(иfD(f($H5AD^d$8fD(d$HY $fD(fE(|$fE(fE(H WfA(t$0fHnEY‰fEYY*YXT$0^f*HYf(DXAYAYDXYXYDXDXfA(Yf/v=9L$d$8\$@ $$i9f(f(T$XfWL$Pf(\$@Yl$8d$0_L$PfE|$l$8d$0D$HfE(f(\$@T$XfD(YfE(fE(Dt$l$x$$$$$ f$DD$p|$`Dt$XDd$P*D|$@Dl$8Yt$0t$0Y4$$YD$HDD$pDl$8DY$f(D|$@Dt$XDd$PX|$`Y$^t$f(DXAYYXDXt$f*Yt$xYY$DXDXAYf/=6T$0$$$$Hf(f(r\$PL$xT$Hf(T$ L$\$<$T$ <$L$H˧f(\$fHnf(f(fWp9ff(ff(f(H(f.zBu@f(Yf/hf/ ~66f(H(f.zrupf(Yf/X|f/f(f(d$fW 8YQd$D$f(T$fYf(f(H(Ðf(f(X\Y f/vff/f(s5f(fDL$Վl$f(f(fW5*8f(YD 4f(T$Y 5d$l$YQd$fl$T$L$f/D$rifW-7f(f(\$|$f(f(Yf(f(YY\f(YXf.f(Af~5H7f(fWf(|$\$f(~57f(f(Yf(YY\f(YXf.zv94f(fW\L$UL$D$f(YD$f3\f(f(f(f(f(f(ޅ~5f6f(f(hff(ff(H8f.z2u0f( $YJ$$fW%6f(H8@f.zrupf( Yf/6f/f(l$d$ Wd$ $f( $l$\Y f(H8=2f(f/f(\XYf(YYf/v(~ 84f(fTf/fTf/f(f(f|$(t$ kt$ |$($L$f(f(Wf(\$$f(\D$fW4YYf( xf(YX YX t1H8Yf/%~Z3 f(fTf/fTf/f(f(YYf/54f/5f( 0XYf(YzYYYX\0\YXf(\ Y^\Y\Y^xfHf(f(f(fD(YYXOYYDY\f(YAXf.xX0f(f(YYf(Y\f(YXf.f(f(XfW%2l$ T$f(T$$f(? $l$ \f.|/f(qf(f(d$(,$ڇ,$d$(fD$ffW-2L$ ),$$L$Of(\d$f(\D$ fW 2YYf(f.f($$fD(f($$DàY.AYDYfD(fD(fD(DX.DY\ ̠fA(YYY\g\fA(XAYY\MAYYXAYAYDX YAXD-\f(YY\\fA(Y\AY\fA(D\\XAYf(5.\f(DYA\YAXXYu- ^-f(D Q.Y\EYYYX9YA\^f(\YfD( X\XYX -\\/YY\YAYA\XYAYf(f(f(f(d$f(,$d$,$f(f(Pff.@ff(f(HHf.z:u8f(Yf/xf/ +f(HHf(f(X\Y<f/vf/+f(HH=+f/YYf/v(~ -f(fTf/fTf/f(H|$8Ht$0t$l$(d$ 軀d$ fl$(fW-S.|$0\$8f(f(|$\$|$\$t$f(f(f(YYY\f(YXf.f(T$l$eT$%*l$f(YYfW -\f(tL$d$l$f(f(Ld$Yf(9f *#(*f(Wf/%x~, Zf(fTf/fTf/f(f(d$ Yl$Yf(T$\$Yl$f(f(T$Df(D \$DYd$ YXYf(YYEXAYXXcDYY=YYfD(E\\AXYY\Yf.Hf(f(f(fD(YYX/YYDY\f(YAXf.Xf(f(YYf(Y\f(YXf.If(f(z7f.fW%N+f(ft$(|$f(|$D$ f(L$|$@z|$D$f(苆\$DD$ L$f(t$(AYf(f(YAY\f(YXf.zhf(l$d$-d$l$f(Y\%i'Yf(Hf.zuT'f(/C'f(f(fA(t$yt$f(f(qf(f(f(l$f(d$ryl$d$f(f(:f(t$Jyt$f(f(H~)f(f(f(fW/~)Hf(f(fWf(fH%L&f/D$yf\$Y]&f.Q g-%YYf/X kXKYX _YX;YX OYXKYX %^\vfW(HD$f(=\${\$Lff.Hhf(f(D$N%L$fWzl$t$L$Hf(f(l$Xt$PD$@&zf(f(f(L$0YX |D$8Yt$XfW%'f(d$wHJJD$ D$fHnwd$.f(D$f(wDT$ L$D$(D$fA(hwd$f(D$f(GwD\$(L$D$ D$fA($wd$f(D$f(wDT$ D$(L$D$fA(vd$zf(D$f(vD\$(L$D$ D$fA(vd$nf(D$f({vDT$ L$D$D$fA(Xv|$8\$0d$DD$@YDL$Ht$PYfE(fA(l$XYf(XAYDYf(AYD\XfA.f(f(|$ DT$t$l$1wt$l$f(DT$|$ f(\p"f(Yf(fD(YDY\f(YAXf.z_\\XHhf(AXXf(f(fA(l$fA(t$tl$t$fD(f(!f(f(t$ |$DT$Xtt$ |$DT$l$f(_fDUf(f(SHH=ҒD!AXf/"f(f(11@f(f(f(f(f(YYY\f(YXf.fPAXf(ȃ!ÉfD(̃f/sff*Y%$YfA(l$ d$\$($Ru$\$(fH~fH~f(f(@fHnd$l$ D$0fHnL$8f(L$0fff\f\) $$L$HH[]fffD(f([f(f(\$$r$\$fPfD(f(!ȉf(HfLnH.AXfHnf/rff.fAWf(AVUSH\HpL$(f( H\$@H$H$)L$0f( pf(XD$ Y)L$@f( a)L$Pf( dfI~)L$`f( b)L$pf( e)$f( e)$f( e)$f( e)$f( e)$f( e)$f(YXfW! fI~@fIn\$HL$qd$L$D$fInf(qH9\$f(u|$ t$(Yf(f(YXYYf(f(YY\f(Xf.zHf([]A^A_T$ \$(f(rpf(ff.SH0D$ f(fTT$(f/f(fW5 f/fH~-~f(f(f(f(fDD$ d$T$X\YD$(^Yf(fT<\$1vT$fHnH\$d$f(fHnXXf/sf(fT^XY xf/ v%H0f([@%fDUff(SHHXf/ff/rKf/rEf(\$ \L$d$T$oT$d$L$\$ f(?ff(\$ T$L$d$oo\$ T$L$d$f(f(fTHf/f\Hl$Ht$(f/H\$ T$L$f(d$F=Hd$D$8XD$HX\$ T$|$L$f(\$0T$ L$d$|$t$(f(XD$Hf/\$0L$D~ DD$8YfD(T$ d$D\@f(fD(ۃXDY\A\fD(D\XEYfD(XEYYAXfD(fAWf(f*A^f/wHXf([]@=KHd$D$8XD$H\\$ T$|$0L$f(d$Kt$(D~ f(XD$HfD(fEWf/_\$ L$|$0DD$8YfD(T$d$D\fDf(fD(f(XDY\\A\fD(\EYXD^fAW^fA(AYfD(Yf(f*\fD/wHXf([]Df/l11H=;X H-HHXf([]ff.Uf(f(fD(HH0D~fATfATf/vfH~fD(f(f(fHnf(\$(T$ DL$d$l$ $kf $D~<,T$ l$f(d$DL$f(\$(fAT*\5fATf/vDf(AXf/f/+fE1fA(D%fA(fA(fA(fD(AXHfA(fE(DXAXDXDYAYYA^Yf(XfAT_f(H='fA.ztf(^fATfA/wAYfDTfH*A^DYf(AX}H0]f/fL~f(fD(fHnf(-A\fATf/vf/w&D5hDUH0]f(H0HfA(]DUH0f(]ff.UHSHhmff.zuf.wzuff(f* $m $]^]f(~-f(Yf(fTf/%v15f/f*Y YYXYf(fXL$ L$ \L$(L$(\D$0D$ L$(\D$8\$8D$0L$ \Xf(XXD$@D$@\D$PD$P\D$@f(f)<$H$HD$HhfHnfHn[]f.uvH?1f(T$ $t $~-T$Y fTf.ssf.ff/SfDۉHt$@H|$PD$@~L$H)D$PǤfH~fH~- Pf/wzf/wpf( YYX YX Y YX YX YX \^X$m$\iff.AWAVAUATAUHSHHB|H?1H$HT$$L$HĈ[]A\A]A^A_@ELt$pLnqDl$p$EDUn$~%f(fTf. zuf(fYf/f(f)L$`Aff(\oA*Y^f/A9BDH|$`LL$pl$pL$$f(m$~%fTf.%zuf(fYf/Ef(fAD#5fHT$XHl$pOHt$`HD$`~L$h)D$p)HL$ol$pL$$f(l$f(fT Nf. .zuf(fYf/v XXf(+l$Xf+)4$fDDH|$`H|$HT$f($j$~%+Xf.z]u[fTY,fDXXAQD+LXXXXf(ffT,*f.zfH~fH~HEfHnwff.ff(H(-d*X^$^Xf(fWSL$Y\$^^l$g\$$ff(L$l$^^f. H H H5~5LA,f(D}X@Y9HHBHTYHX@H9uYXfTf(fTAYf/wHHI9t H롐YH(f(N1ҾH= 1xL fH(ff.@~%5 f(f(fTf(f.v3H,f- fUH*f(fT\f(fV\ - f(f/w6f.z8u6Y-} f(fTf.w'Xf(\f.z uf(Xf(fDH,ffUH*f(fT\f(fVAWffD(f(AVfD(f(AUATUSHf.zSuQfD(1ҾH= 1D$!K = D$HĘf(fA([]A\A]A^A_f(fT f,*f.ztfDfD.zu=_ fD(f.fD(E„tfD.DЄufD. zFuDfA(= ^^\fW-fD(f.=5/DfD.DL$Hl$Pz$u"fA(f(Dcf(fD(ffA(\f. fA(f(d$DL$,$bd$,$DL$f(^fA(^fD(f(DYYX. f(Yf(Y\DXfA. f(f(\f(fD(f.%H E„tfD. DЄA,f*fD.z u fA/:fA/DL$0fD/ A,ffA(AC*\l$ D$HL$PE1d$DT$1T$D$$DL$xgT$fXkD$$DT$D$`d$t$pT$ht$@Dd$(DT$Xd$8l$Xf/-& r-Xl$ l$ l$hf/l$`l$ f/Hf(fD(tf(AfHnfLnfI~*AAd$D\$f(fD(fD$8fA(L$(A*X\YX\$ \YYd$0fD(^^f(DYYYYD\XfD.f(AXD\$Xd$f(f(|$f(A\$\\ffIn$|$f/fd$8Dd$(fD(fD(DT$XDL$xfD(fD/xl$ fA(D|$0Dt$pffE(D\$@fE(fD(f(f(f(DT$@XAY\\DYDYAXf(fD(AYEY\f(AYDXfD.9AXEXƃ^D^X-A9afD(fA/+~ 9 D$0|$D$fWfAW^|$D$f(f(AYf(f(YAY\f(YXf.BfD(f(E<\$pD|$@f(f(1f1$PD$8$Xf(ԥ|$8\|$ 1ffI~fI~f(f(<$覥l$ 5 $`\$(T$0Xf(\|$8$h f(\X5|$YfWYYYf\$(T$0L$ X $D$f(\f(Yf( l\L$ YYqYt$0D%DXd$D|$($$L$fW 4fA(fA(AXD%lDXd$ $fA(Dd$\fDW%YfA(Yf(X$YYXD DX$$D$D$D\D$ $$fA(\RfA(DYY$AYAYHX-8|$ D$d$$XT$0fDW $\=X\$(D$YfA(fDWYYfA(Y$$YYWHD$$$$fHnX,$\-Q$fLnD\|$ DYY$fA(AYAYf(.W-|$ D$d$$XT$0fDW$\=X\$($YfW5fA(YYf(Y$$YYVH9D$$$$fHnX,$\-:$fLnD\l$ DYY$fA(AYAYf(V-T$0\$(d$$|$ Y$D$XYX\=$fW-fDW-f(fA($$YYYYyUHb$$$$fHnX,$\-$$fLnD\d$ YY$AYAYf(U-Gq|$ $d$$X\=fW$XT$0$fW \$(YYYYYY$ $(tTHpD$$$($ fHnX,$\-$fLnD\T$ DYY$fA(AYAYf(S-p|$ D$d$$ XT$0\=$(fDW%X\$(D$YfDW YfA(YfA(Y$@$HYYZSH{oD$($8$H$@fHnX,$\-$0fLnD\D$ DYY$ fA(AYAYf(R%T$0\$(l$$@|$ Y$HXYX\=$8fW%f($0fW%q$$Yf(YYYFRHgD4$$p$fHnfHn\\$ $xDXf($HfA(\YY$@f($YYQX\$$pf($$xXX$X$X$X$X$0XD$$fXX$X$X$X$X$X$8X$$%X$$XX$X$X$X$ X$@f($XT$0XX$X$f.X$X$|$X$(X$HXD$UOl$(f/$ f(Al$(f.D$ YYffD(fD(D$HL$PD$D$T$ fW$$fIn\$`$fIn\$hS$$f(f(f(D$D$YYY\f(YXf.fA(fA(fA(YYY\fA(YXf.9$,$fD(f(DYYYYfA(\f(X$f.T$D$H$L$P"D$fIn\$PXD$0 $fIn\$XXL$(QT$$ff(f(fD($YYDY\f(YAXf.\$T$f(f(YYYY\Xf.X$XkHf(fD(f(AfHnfLnHdIZDT$ E11f(~~A\fWfAWfD(D$0fD(D$Hl$Pf(fA(,$DL$P,$\DL$f(fA(Mf(fD(D$(^D$0N jff/vBjf.DGf/fA*f(YYYgl$ YYOfD(fD(|fA(fWj,rH?fD(f(λfHnfHnf.XDX9fEfA(f(D*AX\AX\5YYf(A^A^f(fA(^^fA(YYY\f(YXf.mf(fA(d$(DT$ |$DD$l$D $H|$9DD$D $l$XDXDT$ d$(f.f/H' AfHnf/s-HfD(fHnL$(D$0|$DD$,$#H|$,$DD$fD(f(f(fA(f(Gf(D$D$GD$D$f(f(fA(fA(ÃDL$Hd$@l$8D|$(DT$ Dt$\$Dl$D$aGDt$l$89D$\$fAXDT$ Dl$D|$(d$@AXDL$H^f(^X-zfD(1d$8Dd$(fD(|$@\$pfD(fD(DT$XDL$x\$T$f(f(<$F<$ff(7<$}F<$ff(f($f($PF$f(f(fA(fA(f('Ff(ff.Hf(f(Ht$ f(H|$D$ f(f.l{;t$ tuHf1H=n12 (Hu1ҾH=G1Y2 ff.@AVf(f(ATUSH~=T$ff/D$vf(\|$~=fT\$f/,fE*\f(T$E1D%YDh^fTXDdfI~t$f/5rAXfInf/s f/-fA(fA(ĸ@=tffEf(D*AXA\Yf(AXA\AY^YXf.zf/tf(^fTfD/vf/T$DEf(|$f/=rW~RL$ ff(f(f(ŃX\\Yf(XYX^AX9uHĸf([]A\A^ft$wAf.f(f(1)|$Pd$`\$0l$ :l$ f1D$hL$pf(f(l$@l$@\$01fD$ fD(L$(f(D\l$HfA(DL$@̐\$0HGl$HDL$@D$xfLnf(f(D~-6\AXfE($EXf($$A\f(A\|$0AXE\fAWYd$`fEWDY$X^f(A\XD^fD(fAWY5EXAXfE(A\Yf(X^fE(fEWDYf(EX\5AYD^XDXfAWDXfAWfE(D=DXE\DYDYYD^f(AXf(f(\A\Yf(f(AYYf(AXA\^EXfEWAYfD(DXfAWfL~fD(EXDYfA(AXA\D^Yf(A\D"Y^fHnEXfEWXfAWfH~f(AXf(f(A\AXDYDYf(AYD^f(fA(AXf(f(A\A\D^EXYf(fHnE\Yf(AY^EXfEWEYfE(EXE\XfAWAYfD(E\fH~f(AXfLnDYDYf(D^D^f(EXfEWEXfA(D=/^fAWAXAYA\Yf(AXYf(^fA(AXA\DYf(A\fD(f(f(AYfD(f(|$P)$^ DXDXYDXE\E\DXfAWAYAY^DXfAWAYfD(D\DYD^f(fAWAXD\$t$@f(ffD/t$`EXDL$H]l$ d$(\$\l$xf(f(Yd$(D$L$,$\$(T$ *T$ \$(fW9\F\,$f(f(X\d$\Qf.yD$PL$X\$$Z*$\$f(fW%\%F\Xf(f(f(fW fW`f\ xH`f([A^A_f(f(f(DL$<$'DL$<$fD(fD(L$XfA(f(f(l$(d$ DL$<$'l$(d$ DL$<$f(L$ fA(fA(|$0t$(P'|$0t$(\$ f(f(L$XD$Pt$(DD$ 't$(DD$ f($L$Xf(D$P&f(f(`f( $f(&f(f([$L$Xf(l$ D$P&l$ f(f(@8Ef(fTf/w>f/ FvHf(L$]3L$H^fDff.@AVf(f(f(Sf(f(HXfW}fW5uD$8YYYY\f(Xf./l$t$$+|$8ft$$D$@f(L$Hl$f(f(fTfTfUfUfVfVf(t$$$O1t$$$f(fD(f(YDYD\f(Yf(Xf/|$ fD.Ff(f(DD$0T$(L>fI~Dt$d$y\$ T$0fED*DXL$(f(f(YYYY\f(Xf.f(f(A^A^Xf(t$f(,$Xf(d$f(|$&0fIn|$f/,$8T$@\$HXXf(f(f(YYY\f(YXf.R^^ff/t$8vfW fWHX[A^fDHf(f(fDD$fHnd$4$%4$DD$fD.D$ d$f(f(5r $D$t$(5|<DD$0fI~fDl$|$ffW-DfW=<*\d$(\$ f(T$0Yf(Y%T$$L$XXD$T$$$].fInf/fl$H|$@4$d$f(f(YYYY\f(Xf.f(]^^\fW a:L$ D$0f(f(l$|$D $!l$|$D $=D$8f(f(\$t$,$f!\$t$,$f(f(C!D$f(f(f( $f(̻!<$%tl$fD(f(d$(%:fI~%l$|$DD$ t$0ffA(f(DD$ *\d$(fW--t$0fW=Yf(Yf( #4$T$L$XXD$f(T$4$"R,fInf/KL$HD$@f(f( f(f(f(d$f(4$d$4$@fD(fD(f(f(T$(H9fI~&4$d$yDL$ DD$0f(fA(fEAYD*DXT$(Y\f(AYf(fA(YXf.zyf(f(DD$0A^DL$ A^Xf(4$f(l$Xf(d$f(|$!*fIn|$f/l$ fA(fA(f(l$ f(|$DT$DD$D $l$ |$DT$DD$D $+ff.@fHf/vfWEf.EE{;f.J{ H@u1ҾH=1 H@u1ҾH=1 9Hff.Uff(SHxf/~=@1)|$0f/G~= )|$@=f(f(L$ |$PL$(=ffWD$0l$ l$*d$YL$(f(XYf(X\Yf(T$!T$l$ f(t$@d$^f(Xf(T$PfTfTYf/UY%E=e;Y\f.C_f.Ht \f(Hx[]fD=~5 f(|$f(=)t$@|$Pffd$(*l$ \$L$Xf(Xf(\D$T$s T$XT$\$fW\$0d$(l$ Yf(f(|$@Yf(Y^D$PXfTfTYf/wL$X SH|$hHt$` )d$Y^ ^YD$f(XAL$L$f4d$YYf.\XYYXڃX YY\ʃ\YY\XYY\XڃYYXYD$hYT$`f(\f(QYD$^Xf..A1ҾH=1 Uy1ҾH=1 W~=H)|$0fWf(L$d$`L$d$?ff.@fHf/vfWUf.U@{;f.E{ H@u1ҾH=1 H@u1ҾH=1 IHff.ATUHH(Ld$D$T$L $T$B/ $LHD$H(]A\@~-=f(f(f(fTf.v7H,f=f(fUH*f(fT\f(fVf.zf/tf(f.ATU,SH0f.\zRuP,f*f.zf/t8N1ҾH=dm 1 H0[]f(A\fDff/,fE1*˅M9|lf(f(ʉ$$P$$~-f(?>EtfTf/ f.f.CH0f([]A\fD(fd$*D\f(T$fA(DD$(Xt$ f($谣$T$=D$f($Xf(Ed$~-9fD(H t$ SDD$(DT$$fHn fD(f*AXf(f(X\\\XYAYfE(AY\^9uf*XX<f/v~A>fW%8fE1\%,*˅`1ҾH=k 15 H0[]f(A\9Df.xf/fff(\$*d$\XlL$虃L$d$-M$XXf(o\$Y$HL$^fHn$4$H;YfHnVf.f((AVf(fAUIATIUHSHH@f/f(')D$ )D$0HLt$H1f(f(L$D$L$$fۅLD$f/EH6I$Lf(f(˾D$@D$,D$vH@[]A\A]A^H ,t11$H= $*HD,E@11DT$H=$ A$T$ff/IEfDf(f(HT$L$ĄT$$fD$0L$8SD$w-H4tHT$0H=+$$fD$0A$wfLt$f(f(˿Ht$L$Lt$$fD$ L$(D$w-Hx4tHT$ H=${$fD$ AE|1ҾH=`1T$$@ $T$f@1ҾH=(1$ $@efDAA<.ffH(f/f(Jf/~ @-f(fTf.f(^f/f/fTf.f(%^T$d$sd$fT$f(f./Q^f/-wnf.1ҾH=Y1 Q$1ҾH=31 SH(fDf(H( ?f(T$YX ?YX ?YX ?YX ?YX ?YX ?YX ?YX ?YX ?YL$kT$L$f(?X ?YX?YX?YX?YX?YX?YX?YX?YX{?YXw?Yf(XH(Y\f1ҾH=1T$5 T$f ӻf.Q^H(f(f(g Y>\7f.f/%+wFf.T$~x1ҾH=#1 T$f a@ =f(T$d$YX =YX =YX =YX =YX =YX =YX =YX =YX =YL$] d$L$ff(=X =T$YX=YX{=YXw=YXs=YXo=YXk=YXg=YXc=YX_=YX%Y\fDf( T$f%Y!=f(\f(L$L$f(D$f(T$T$L$ff(AVATUSH8 f;޹Xf(fT6f/ =,;fW ,H-fI~=L$ |$l$Yl$ E1H:fHnl$f*f(fW Ȼl$( $H: $f(fHnX%T$L$f($$T$$$f(5(L$X^fTDf/AA~=*f/sf(\$(\H)YH ^fX ҷY\fHn^|$(5(f(XYf(Y^X^fT f/w-X^HXXyf(YH9u@YT$fIn(XfTQfI~fT=DYf/w dAH8fIn[]A\A^Ðf.wHf.zBf.pzu=H8[]fI~A\fInA^f.{$H8[]A\A^H8fI~[fIn]A\A^u1ҾH=л1$ ~ $fWfTfVfI~EfDHW5p (HX^HfWDf(HX^fDHl$ <$.H(fH/w0W( XHW(L$ -L$ H\(ff.f(fHf/w.~vfWf(~\HfWf(L$L$H\f(fHl$w*H<$$H<$xH HDH<$H<$Pl$0H HÐ@fZf/w f/ pv ܎\^ H\ TXZ(L$ L$ W D$(T$H\(f f/w f/ov \^H\̳f(Xf(L$=L$fW ϶$f(!$H\f(ff.@H(l$0whov|$0H(}D%H<$|$ H|$ l$0<$l$ HHff.fH8$L$H`f(fT ܴf.sf.z f/v6D f/w f/v(H? \Hfxf(1 1YYYX1X 1YYX8X 1YYX \^Xff.f( 3Xf/w f/v x3%3f(YYXX X3YYX%x3X H3YYYX%d3X 43YYX%T3X $3YYX%D3X 3YYX%<3X ,3Y^YXXff.@ff.ATf(fE1UHSHH f/vfW Af.f/ lv5f(fTf.#f( $ $^%Bf(Yf/hll-P5lYXLlYXhlYX5lY\0lYXLlYX5lYXlYX0lYX5tlY\kYXlYX5XlYYYXXXY^kY\kYXkY\kYXkY\Y^$fEaEf(XX$H 1[]A\IHsHEHH 1[]A\Df(H|$Ht$T$ $2T$ $d$\$^߮f/ek--kXYX-%kYXIkYX-kYX9kYX-kYX)kYX-jYXkYX-jYX kYX-kYXkYjYXj^ kYXXjYYX kXjYYX jXjYYX jXjYYX jXjYYX jXjYYX j^f( }Y\f(Y\fEtfW YM1Y\H []A\fWfAHHEHfDpj-(j5jXYX-jYXLjYX-jYXu<~3H`1[]A\ffD.?fl$Xz u f.of(fA(<$DD$5 mY<$DD$f/fA(f(D~ DD$ ffW|$fAW)$$L$fI~.l$X|$D~ 9f(DD$ f/fAWf(-<$\fA(f(l$ \f(t$(d$l$X<$f(d$fD(D~ f/t$(l$ fAWDt$Xf(A\ dfA(fA/\f(X\XYYEf(\YEf(YS U l 1XD$X\UXKKH`[]A\@fA(fD(fA(Dl$XfAEfA(DAAdDk+ffA(f(A*X^^fD(f(DYAYf(AYD\f(YXfA.fE(fD(fA(D^f(D^X%%AXf(^EXfA^f(fD(AYDYf(Y\f(AYDXfD.=f(fA(]U^|$@DD$8t$0D\$(DL$PDT$H^XUT$X]\$ \$ T$$f(f(YD\$(f/$t$0DD$8|$@fDT$HDL$P|$0DD$(fA(fA(t$ D\$K$lYD\$f/$t$ DD$(|$0l$XfD.f.1ҾH=+? 1 soChD~R1E~tH`[]A\fEfXEC\RC fAWfD(f(•fA(\\XYY]f(\XYY]KpffA(f(XKX1XKH`[]A\Df/f(fAWUfD/vf(f(fATfV%\\fA(f(d$(t$ DD$<$d$X<$f(f(D~ DD$f/t$ d$(fD(fAWf/|$XfD(fEW\$XfA/v fMn\fETfDVND\f(f(-Qf/|$X\XYYMf(AXA\YYMkd$Xf/fA/ffXDf(fA(<$-ʗt$(\l$ d$<$d$l$ t$(fD(f(fA(|$0DD$(d$ DL$D$|$0DD$(d$ DL$f(fD(D$kf(fA(|$0DD$(l$ Dl$$$|$0DD$(l$ $$fD(Dl$-Ԗ-ǖ>fSf(ȉHP '5f/=Yf(H|$HHt$@-kL$f(\= ^uYX\YYX]YX-!YX\uYYX5YX-YX\MYYX YX-YX]\%YYXYX-YX5\YYXYX-YX \YYYYD$f(l$(\$T$ l$(T$ \$XXD$L$\X^ޑ^Yl$H^YYD$@XYff.Q^f(HP[fD=|$ff.3f/a5Yf(Yf/'Wl$8H|$H5tL$Ht$@%^YXXYYYXYX%eXYYXYX%IXYYXYX%-XYYXYX%XYYXiYX%YY\$f(\T$0Yd$ \sY\oY\kY\gY\cYf(\$(\u(T$0t$H\$(XXD$d$ \NX%NL$l$8^f.^Yj^YYT$@XYf(Q^f(T$L$L$-v~=5~f(T$f(fDf(f(fTf.rf(f(ÃYX^\9|YD$HP[=ۃ|$=|$f(YD$HP[ff.f/f(DL$YYX\YYX"XYYX\YYXXYYX\YYXXYYX\^D$f(?L$D$f(T$Yf(f(YXD$D8L$YX\YYXXYYX \YYXXYYX\YYXXYY\X^D$f(7L$D$ f(T$ Y|L$YXT$1ҾH=B1m D$YwHP[f1ҾH=1; HP[Dx1ҾH=t1 1ҾH=R1 f(T$T$f(f(T$L$T$L$f.f(ȍVHGHT@YHX@H9uDf(VHGHTXYHX@H9uff.ff(ff/f.{xf/vHf/rpD^,ÃDfX*f(^X^f(ăuf(X^f(fuD0H(^\^\\^XX^\^XH(f(L$mL$H~5=YfHnfHnD~fHnظD$ffAW*YXYY^Xf(fTf(fTYf/suf(l$L$L$l$f(Y\XYD$H(fDf(H(f(؇ff(\f/f/~ -(f(fTf.f(^f/ f/fTf.f(^T$d$d$fT$f(f.'Q^f/`wnf.1ҾH=1Q ц$1ҾH=1+ ӆH(fDf(H( p f(T$YX b YX ^ YX Z YX V YX R YX N YX J YX F YX B YL$T$- L$X o YX YX YX YX YX YX YX YXYXYXH(Yf(\fD1ҾH=C1T$ T$f Sf.Qf(H(^f( Ys\7f.f/%0wFf.T$~x1ҾH=1 T$f a@ hf(T$d$YX TYX PYX LYX HYX DYX @YX <YX 8YX 4YL$d$L$ff(X YT$YXYXYXYXYXYXYXYXYXYX%cY\fDf(T$f%5Y\f(f(L$uL$f(D$f(T$QL$T$ff(Pf(fT̄f.@ff.,SH f/w fW f(H|$L$D$L$f(YXY\YXYXHcHiVUUUH )׍ )Ѓu YqL$uL$%?f(f(Yf(^f(\Y\f(Y^f(\Y\f(ʃufW H f([@f(DYkǺHH! ))ƒtt 9fY!Yxf.ff/f.~ނf(fTf.FwY-f(f(fTf.v3H,f-fUH*f(fT\f(fV\f.z5u3kf(fDtf(fT^fVf(Ð,,tfDf(f.f(f(fT%f/^f(*HH4^f(YHf(XH4f/H HYXfUYYXH YXHYXH YXHYXH YXHYXYXYXYXBHHJHFHXH4H HYXYXH YXHYXH YXHYXH YXHYXYXYXYXB^f(ÐH|f.f(Jf.~zuN~DSfHPf/U5%~f.t$ zu}HP[Ðf/fs %~f(f(fTf.f.zu,ƒHHB|$ f/f(f/fW f/%f(fd$(fX}T$L$f($^T$$L$X^f/D$(wHv}$fHn'$L$ f(X\f(^f/;v~;Y\;Y\;Y\;Y\;Y\;Y\;Y\;Y\.4Y\|FD~`=0|f( <~5 }fWYf(|$0f(fTf.v3H,f5{fUH*f(fT\f(fVt$0f.zu{fD x|f($Y={$H5 Y:H=zf(|$ \D$@f(f(l$83f.$~R~D$Hfd$ f/d$8<L$85Nf(1fWt$( @rXl$ T$d$L$f(,$d$,$f(t$(L$XT$^fT|f/vYd$H qzYd$@s2\\XSz^9f($d$oz$f(fT 6|f. YD$\D$ H,fl$ fUH*f(fT\f(fVf.%y&D 98f(\XYX8YX 8Y\8YX 8YX8YX 8YX8YX 8Y\8Y^ L$0X f()f(D$YY\D$ @1ҾH=1$ %x$%y$|$ $f(+8%c8f(^YXX8YYX%C8X8YYX%38X7YYX%#8X7YYX%8X7YYX%8X7YYX%7X7YYX%7X7Y\YY^ xT$T$57$7Yf(\ 7Y\ 7XYY\ 7X|7YY\ 7Xl7YY\ 7X\7YY\ 7XL7YY\ 7X<7YYX 7\,7YYX t7\7YX7YYXX7\X7^/X$n5mf/|f(|$ \$8H|YHP`\^fX $vY\f(^|$8DL$(f(XYf(Y^X^fT wfD/UDD$ ^HAXXAXf(YH9u&ff.fH(uff(\f/f/4L$YXYXYXYXYXYX~YXzYXvYXrY$f(L$5Zf(VHtYfHnX$XYX9YX5YX1YX-YX)YX%YX!YXYY\f(H(f(f(^\f(\f/f/<L$d$YX,YX(YX$YX YXYXYXYXYX Y$f(Rd$f5f(HesYL$fHnX$XYXYXYXYXYXYXYXYXYY\f.Qf(YH(f(f.f.z[1ҾH=q1 rH(f(fDf.zt1ҾH==1 $趱  $fUrgf(f(^\f(\f/lf/<d$L$Yl$X&YX"YXYXYXYXYXYX YXY$f(Ll$f(HcqYL$d$fHnX$XfYXYXYXYXYXYXYXYXYY\f.Qf(Yf.zt1ҾH=w1d$ $  $d$fpf(d$^L$,$\f(,$fL$d$f(f.wQQf(YNf($m$u_v~%0af(f( _fTfTf.v:f.v f.rf.^vf.fH~fH~HCfHn@f.wff.<ATfUSHP-^\f.zFuDf/1ҾH=_1ѝ Q^HP[]A\h^=0_f(f(^f(fTf.v5H,ffUD^H*f(fAT\fVf( ]^D$@fTT$\$l$輷f.]l$\$T$zu5]Xt$@t$@|$@ff.f/HD$Hf1f/v fW`f/-Z]nff.f(Qf(T$t$\$l$ ~%_\$f(f(_t$fTT$f/v2fD(=\l$ DYA^fD(fDTfA/.ff.QfTE1H\f/fHn%=o`|$0@|$8X=Z\Y^XA^D,f(ff(Y\Y-\f.QXY[^fTf/-4f(f(\$(^t$ T$L$f(|$8Yf(l$u\$(DL$0l$L$Xf~%]T$A*Yt$ AYX^[\f(fTf/-f(t$ T$\$D$\$5[f(L$~%]f(T$\-h^D$0fTf.t$ v=H,fDZH*f(fAT\=!fUfVf(D,Off(Df(OHP[]A\钴5J^t$0f(T$fT$A*f(D$0YXf*Yf(^ʃufW ]D$@YD$HXuf(f(f(f(T$\$l$Px\$l$D$HYD$@T$\f(T$l$<t$@fl$T$f(f.{f(f(L$H\0uD$f(wT$\$D$Ht$(L$ T$\$l$Ht$(L$ T$~%Z\$l$f(\$t$L$~%Z\$t$L$f(f(T$\$l$ĮT$\$l$f(ffHf/v* Xf/wdf.z6u4XHf.WHf.zJ1ҾH= 1- WHYWfWZYKHfD1ҾH= 1D$ݖ D$^ WAD~%hY58Xf(f(fTf(f.v3H,f-1WfUH*f(fT\f(fV\ V-Vf(f/w6f.z8u6Y-Vf(fTf.w'Xf(\f.z uf(Xf(fDH,ffUH*f(fT\f(fVSf(fH f/YVf._f.1f/Vvf(^f(f/VrVf(f/ fW%Yf(ʸ-YXYX-YXYX-YXYX-YXYX-YXoYX-YX_YX-YYXXY^̅tIf(L$L$f(^UH [YY\f(f(@f(H f([@1ҾH= 1  TH [f(ff(1^\f(fW W@5 "VH [f(f(L$T$HLTT$D$fHn\f(\$L$T$YU\\f(\1f(fW VfPTf(fT Uf.sf.z f/Sv6D Sf/w f/Sv(H/\SHfhSf( YYYXxX YYX(SX pYYX xS\^Xff.H(f(~T`Sf(fTf.r fTf.s f(Gf(\Rf(H(ff/%Rft$f(f(d$T$$认T$d$$f(f/v#D$X=RH(Yf($f(\$輫 $\$YM=@Rf/^f/QPf(Y5Qt$YXYXYYXXYXQY\^XD$f(T$ $ $%Q\$T$f/Yf/ Qf(%WQYY\%YYX%wY\%sYX%oY\%kYYX%cYXX%Pf\D$f(L$$$=gPL$\|$D$@f.f/F pf/HPR%PXf(fTf.\ 0T$f(YYX YX Y XYX \^T$X~OH,fDf8OH,f-?OfUH*f(fT\f(fV,f.&f/~H tf/BjP%OYXNf(fTf. <T$Y\f(Y %\ !f(YYX YX YX Y XYX YX \^訩T$XNH,銩f.MH,f-MfUH*f(fT\f(fV1ҾH=S1 fHff(|M Xf/w f/Mv# % f(YMYXX YYX%X YYYX%X YYX%X YYX%X YYX%X Y^YXXff.@HH~Nf(f(f(LfTf.rf(fTf.s(X%HLf(f(àf(f(HHfDff.zuf/% L6f(f(d$l$荪l$d$f( f/vf5K~Mf/v>f(5K~=Nf(YfWY\fTfW^f/f(X^XY [Kf(Xf/wf/}Kgf(L$ t$l$d$d$l$t$L$ YXf(t$藜t$f(J hXf/f/JL tf(YJYXX,YYX LXYYYX 8XYYX (XYYX XYYX XY^YXXf(fxf(DY=JYDXXVDYDXxYXDYDYDXbYX.DYDXPYXDYDX>YX DYYX)Y%AX^YXXff(f(t$8f(d$l$sl$fD$0f(f(L$(f(l$ sd$fD$Hf(L$f(YsDD$(|$0Dd$fD(fD(D\$f(fA(fA(fA(ltfA(fA(]t -Hf(d$l$ Xt$8f/f/1Hf(DY"HYDXXqDYDXYX_YDYDX}YXIDYDXkYX7DYDXYYX%DYYXDY=@AX^YXXYfۙf("fL$ t$l$d$賙d$l$t$L$ f(Dfۺf(f.E„tf.fz f.Hf(T$MT$HYff.ff(f(f.f(zuf.zuf.f(zf(ÐHf(t$,$訚t$,$f(Yf(f(YY\f(YXf.z f(Hf(f(f(Uf(ff.@ff(f.E„tf.fz f.EXf/w f/Ev$H\$\$HYfD%f(YpEYXXYYX%XYYYX%XYYX%XYYX%X|YYX%XY^YXXYff(fD(f.f(fD(z4u2f.ͺEf.„tf.f(zf(fHX~5$Ff(DfTf.s~X%CfA(DD$|$f(k|$DD$fD(f(fA(f(f(YAYY\fA(AYXf.f(HXfDfA(fTf.ofD.zuf/%\CfA(f(DD$ |$d$DL$ΡDL$d$f(|$DD$ f/f~5EDBf/fA(~Ef(DBAYfWAY\fTfW^fD/Lf(f(f(DD$@f(|$8DT$Hd$DL$FmDL$ff(D$0fA(fA(L$(f(DL$ md$fD$Bf(f(L$f(lt$0D|$Dt$fD(fD(Dl$(f(fA(fA(fA(mfA(fA(m ANf(d$DL$ X|$8DD$@DT$Hf/f/A 55f(YAYXXYYX5 XYYYX5XYYX5XYYX5XYYXY-X^YXXDYDD$|$XfA(DT$#DT$|$DD$f(fDf(X^XY 4@f(Xf/*f/R@5f(Y-D@YXXYYX5XYYYX5XpYYX5X`YYX5XPYYXpYlX^YXXDYDD$|$X%0?fA(DD$|$f(蝓DD$|$fD(f(-ff(L$0DT$(DL$ d$DD$|$萑|$DD$d$DL$ DT$(L$0L@> (Xf/f/> 4f(Y>YXX YYX X ܿYYYXX ȿYYXX YYXؿX YYXпX Y^YXXfD(f.DD$|$N|$DD$ffD(L$0DT$(DL$ d$DD$|$|$DD$d$L$0f(DL$ DT$(cf(f(fA(fA(}f(U@fHf(f/vfW?=f/%<f(Y\% =d$AH"d$ df(fH f(f(f(HY\X@H9u\Y2<HYÐf(\$ѕ\$-CHĀf(fH^\-Y<f(f(f(HY\X@H9u\Y;ff.YwQ^Hf(f(L$L$f(ff(f/vfWz>;f/r\%<;HՀ HY\;f(f(f(HY\X@H9u\YD-H f(H^\-2;f(f(f(HY\X@H9u\f. :Yw Q^f(Hf(L$ȐL$H^f(DH8f(f(:fT-D<f/:H}f'f(HY\h:fDf(f(f(HY\XHH9uf(t$(\$ L$d$l$WL$d$f(l$\$ f(t$(\Ym9YYf/vfW<H8f.f(\$l$l$H|=Vf:f(\$^f(H\=i9f(f(f(HY\X@H9u\Y8f.YwQ^f(:f(t$\$L$t$\$L$f(@f(f(fT%p:8f/~=>8f(fH{ Gf(HY\-8fDf(f(f(HY\X@H9u\f/YY-Hzf հf(H^\-8 @f(f(f(HY\X@H9u\f. ^7YwQf/^f(rfWb:H(f(t$\$L$肍L$t$\$^f/f(vfW:H(Dff(f/vfW957f(Yf/r, 7f/*Y%Z6\DHHf(\$H|$8Ht$0-^% TYXX|Y\%YX 4YX`Y\%YX YXDY\%hYX YX(Y\%LYX YX Y\%0YX ĩYY\%YD$Yf(YXL$(Yd$ XYXYXYXYT$\55f(臊L$(f 5d$ T$XXD$\$\%Xf.^5^YL$0^YYd$8\Y }Q^HHf(fDf(f(\ \YXYY\YXY XYX YX YX ܧYX اYX ԧYX ЧYX ̧^f(L$(L$f(ffHHf(f/4f/^t-H|$85ǩ%'Ht$0T$f(\$(YYXX6YX-ZYX%YXYX->YX%ҨYXYX-"YX%YXYX-YX%YXƨYX-YX%~YYX-֨Y$Yf(f(Y\5Xd$ Yl$XYXYXYXYf(L$vl$fX-L$X 1d$ \$(T$^XX$ f.^YY\$8Yd$0\YQ^HHf(Y ĦXYXYX ȦY\YX YXԦYX YX YX YX YX ^f(\ \HHYYY~ 3fWf(~ 3HHfWf( $ $f(ff.Sff(H f.ff/=0f/f(%-T$Y\f(f(YXY\X f(Y\X%f(Y\Xf(Y\Xf(Y\X%f(Y\Xf(Y\XY\\\_/YW/YfH~f(\$T$D${/f/\$\/f(\$輈Ht\$ f(fHfDf(f(f(HY\X@H9u\Y.YfA1ҾH=41m e.H [-.f(T$fWv1^\-.l$Hpof$T$l$f(H f(f(f(HY\X@H9u\Y-ff.YQ^H [f(fD1ҾH=%31m -H [Df(T$1T$-H$rTf(fH^\--f(f(f(HY\X@H9u\Y -ff.YwCQ^f(L$H YfHn[\f(L$0L$f(f(L$L$f(fDSff(H f.f/_=,f/f(-aT$Y\f(f(YX%GY\X?f(Y\X-3f(Y\X%'f(Y\Xf(Y\X-f(Y\X%f(Y\XY\\\%+Y+YfH~f(d$K~T$D$+f/ed$\%+f(d$Hpf T$d$f(H @f(f(f(HY\X@H9u\Y*YD$uA1ҾH=:01j *H [-*Hk f(H^\-*f(f(f(HY\X@H9u\f. 6*YQ^H [f(f1ҾH=/1ki *H [Df(T$虃T$Hn5f%f(H^f(\5* f(f(f(HY\X@H9u\Yr)f.Yw\f(Q^L$f(L$YL$H f(fHn[\Yf(L$L$f(f(L$T$_L$T$뉐fH8f(f.f/=8)f/f(fW+$X$Hh-(ff(H^f(\-( f(f(f(HY\X@H9u\Y2(f.YQ^H8f(81ҾH=-1]g 'H81ҾH=d-1;g 'H8fDf('T$YY\l$ozT$l$f$'f(fT )f/%\'HkmHY\%'f(f(f(HY\XXH9uf(T$(\$ t$l$L$觀t$\$ L$l$\Y&T$(YYf(f(Y$Y\YX%\%Y\\ ؟f(Y\\̟f(Y\\%f(Y\\ f(Y\\f(Y\\%f(Y\\ Yf(\X\Y%H8^Xf(T$l$L$mL$fDڞH{hf(l$D^T$f(HD\%f(f(fA(HY\X`H9u\Y%9%f.Yw)Q^ef( $|{ $f(f(T$\$l$S{T$\$l$f(ff.fH8f(f.f/%f/-$Hd H^\f( ff(f(f(HY\X@H9u\f. 6$YtQ^H8f(`1ҾH=G)1ec #H81ҾH=)1;c #H8fDf(#T$YY\L$ovT$H$f$#L$f(fT5%fHnf/-P#H gaHY\f(f(f(HY\XXH9uf(T$(\$ d$L$t$|\$ d$t$L$\Y"T$(YY\$ %ߛf(f(T$Y\%͛YXɛ\ɛY\\f(Y\\%f(Y\\f(Y\\f(Y\\%f(Y\\f(Y\$\\sYf(\L${L$X V\$f(T$f( $\Y!YL$ H8^XYf.f(T$L$t${t$H!f=|fD(L$fHnH dMT$^H\f( ff(f(f(HY\XhH9u\Y- f.AYw3Qf(^l$ f( $w $f(tf(T$l$L$vT$l$L$f(뢐HH-t!f(f/&ff.(f/Nf( B\$YYX\YYX XYYX \ؔYYX XȔYYX \YYX XYYX ؔ\Ȕ^D$f(=r\$D$f(ȏL$Y f(f(YXD$HHf( =H|$8Y;%Ht$0\$^LYXXY\8YX%̒YXY\YX%YXܒY\YX%YXY\YX%xYXY\ȒYX%\YY\YD$Yf(f(Y\=Xd$(YT$ XYXYXYX~Yf(L$sd$(T$ L$XXD$\$\AX A^u^Yd$8^YYD$0XY%ff.wiQ^HHf(fD1ҾH=|1e\ uHH1ҾH=|1;\ HHf(d$sd$f(HHf(f/&ff.f/>f(B T$YXY\ YXYX YX Y\ YXYX ВYXY\ YXܒYXؒYXܒ^f(Y $&T$D$f(qn T$YD$^\YX$HH^\%H|$8=-Ht$0T$f(\$(YYXXYX%BYX-֐YXYX%&YX-YXYX% YX-YXʐYX%YX-YXYX%ҐYX-fYYX%Y$Yf(f(Y\=ՐXl$ Yd$XYXYXYXYf(L$^od$L$X%rX rl$ \$(T$^XX$^ff.YY\$0Yl$8XY[wcQ^HHf(1ҾH=y1X HH1ҾH=x1X 3HHf($po$f(DSf(؉H0 7=f/=ff.f/f( \$YYX\wYYX XgYYX \WYYX XGYYX o\7YYX _X'YYX W\G^$f(j\$fH~f(IfHnY=f(f(YX$fDff.f/Gf(T$$#$D$f($5l$T$f(D~D=f(fDf(f(fATf.rf(f(YX^\9|YH0[@%f($^$H0[YYf( H|$(\=+\$Ht$ ^\Yf(XTY\ YXDY\ YX4Y\ YX$Y\ xYXY\ hYY\ `YfH~YXL$YXYX݉YXىYXՉYX YX$f(YXYXYXYXYT$jfHn%L$T$\ ĉXX$$\$Xf(^d$(^Y^Y YD$ XYff.Q^H0[f(f1ҾH=1$S $YH0[f(f1ҾH=`1S 3H0[DK1ҾH=s1]S m1ҾH=s1;S f( $ j $f(fff/f.zuzf(Dff(H*f(fT%X%oY%f/wATH0+f.\$ !\$(f/vfW?Ld$ HL$LD$}D$fɅuWT$Bw#H 4uBuf/sf\$ H0f(A\f(LH=WrD$5T$D$ffDpff.f(f(ff/f.zuf(Df(fT%$f(X%Y%Pf/wATH0f.\$ \$(f/vfWLd$ HL$LD$>|D$fɅuXT$Bw$H 4uCuf/Ms \$ H0f(A\Pf(LH=pD$~4T$D$ffDff.ATfD(USH@f.D$0D$8ufD.fD(efEfD(fE/fE.EfE.E„tyAtj1DH=,p1D$O D$fEAAL$8D$0H@[]A\f.fDW'jffE/DT$fA(fA(D$DD$rnD$fE f/DT$fA(AXf/ 1f/@f. lmGf/5nDD$fA/Lf/L f/\tf/%JfE/-?Ld$0fE/ȸf(f(f(fA(LAfA(DFHfA(D$fHnDZFD$fEɅ 1ҾH=8n1D$M D$fED Pf(H@[]A\Y#\$ DD$D\$$`$fW fE%+DT$YD\$DD$\$ f/f.1ҾH=m1D$M D$fEf(s)D$0fE/SKZ fA(,E-HD$E11DD$H=mL AD$fEf(Rs)D$01fE/~fA(-HL$0fA(%~fTfAT~D$Y f/fA(fA(s3辈D$fEɅAf{#D$fEfDfE/ȾF>x} -X~Ld$0fA(LD$fA(fA(YD$fEɅYY@Ld$0fA(ú-}%}|LfA(fA(D$l$(d$ \$DT$DD$D$fEɅDD$DT$)\$d$ l$(ufE/[fE/H1ҾH=j1D$CJ D$fE1ҾH=j1D$J D$fEf(f(ff/wf.z(u&f f(fx f(ATH02f.\$ (\$(f/vfWF Ld$ HL$LD$tD$fɅuNT$Bw*H #4u9uf/ sfT$ H0f(A\LH=D$,T$D$ffD ff.ATfD(USH@+f.D$0!D$8ufD.fD(efEfD(fE/fE.EfE.E„tyAtj1DH=S1D$!H D$fEAAL$8D$0H@[]A\f.fDW jffE/DT$fA(fA(D$DD$fD$fE w{f/DT$fA(AXf/ R{1f/@f. WylmGf/5zDD$fA/Lf/ f/\xf/%yfE/-yLd$0fE/ȸf(f(f(fA(LAfA(uyDFH2zfA(D$fHnD>D$fEɅ 1ҾH=_ 1D$-F D$fED f(H@[]A\Y\$ DD$D\$$MY$fW fE%xDT$YD\$DD$\$ f/f.1ҾH= 1D$uE D$fEf(Bl)D$0fE/SKfA(,E-HD$E11DD$H=) D AD$fEf(k)D$01fE/~kfA(-wHL$0fA(%jwfTfATqvD$Y Sxf/fA(fA(s3.D$fEɅAfD$fEfDfE/ȾF>u -vLd$0fA(LD$fA(fA(QD$fEɅYY@Ld$0fA(ú-iv%YviuLfA(fA(D$l$(d$ \$DT$DD$gD$fEɅDD$DT$)\$d$ l$(ufE/[fE/H1ҾH=1D$B D$fE1ҾH=1D$B D$fEf.f(ATH0HxWff.zuH0A\@~%f(fTf.HvNf.{<$H0A\D1ҾH=1A H0A\@uf(s^f.Vf(Qf/Vw/ff(H*X'fTX%+Y%kf/vYH0A\f. f.D$  D$(f/vfWLd$ f(HL$Ll$$9l$l$fɅuAT$Bw*H 4u,uf/C@DD$ 0LH=a\$,$$T$\$f,$H<$\$UW\$H<$f~%f(fDf.ATSHH8HL$$C_f,$\$f.zuf(H8[A\~x f(fTf.w fTf.vpf.zuf.- f(zJuHf(f.1ҾH=1k? H8f[A\X[f.fH*XD$ D$(1f.'f/vfWLd$ f(f(˾HL$Ll$$i$l$fT$Bw?H p 4u(f.ܺE„tf/=sd$(|$ Dpf(fd$<$SX<$d$f(f(Yf(YY\f(YXf. f(f(f(f(Q%xf(sLH=^\$,$!T$\$f,$ATf(USH@Hu/f.ff.aH@[]A\f.HoLgHHff.~fE-M*HsAYH@[]A\^\f(Ðf(fTtf.6f.[UnH~=8%f(fTf.6f.$f(fEM*Hf(fTf.Sf.5-n^f.qf(Qf/w-f/ܾf(wf(f($$|$$YfWk]fD11$H=; fEH$M*x:f-^f.zgf.~=%h-(1ҾH=L1\$l$D$ ; D$l$\$f.l^f.f(Qf/fwlff(H*X7fTX=;Y={f/w=f(l$ d$DD$$$l$ d$DD$$f(YT0l^f.^f(Qf/fEf(L*DXfA(fTX Y ȼf/wKf(f(fA()|$0d$ l$\$4$df(|$04$d$ l$\$YfW-;fDfEf(f(M*fW-ffWf(-Df(&f(t$0)|$ \$l$D$Ot$0f(|$ \$l$f(D$t$ )|$d$$Ot$ f(|$d$$f(ot$$yOt$$f(sDf.ff/ f/H( f/ xT$^Y^ $f(\$Y-/kf(l$ Rf\$f.f($Kl$XQT$f(f(f(f\f/fH(f(f( T$YYQ $N$T$ff(f(Yf(Y\f(YXYYf(\Yf(\Yf/Q]H(f(f(Df(d$P QD$^Nl$ $f(d$f(YXYYXYXYf.ff/f/H( $f/u%k^Y^T$f(d$Y-if(l$P $d$f(f.D$Hl$XO%f(]H(f(f(f f( YYO $L$f%f(Yf(Y\f(YXYYf(\Yf(\Yf(\f/Sf(H(f(ff(T$N Q$_L,$T$f% YT$f(YXYXYXYf.z \ff.f(z\ŒDf.f f(f/4f/H8& $f/f(sT$Y^t$ ^D$f(\$Y-ff(l$(Mf\$T$f.f(D$Fl$(X^M $@ f(T$YY%M $J$f%Ref(T$YYY\f(f(YYlYYY \Y \fYKf(fW f(H8f.f(T$d$kL $If,$ff(5T$Yf(d$YXXYYXf(XTd4^\$ YYXXY\L$Y^Yf#Kf(fW 'fHf. s%Yf(fTf/w<L$L$f/ Yv-\f(H@f.>ff/f/xf(qqYYXXqYYXqXqYYXqXqYYXqXqYYXq H^YXÐf(f(\ HYXffW f(f({Y\fD1ҾH=v 1/ cfD1ҾH= P1/ ;fDH(ff$fL$f($fY@Y)$$L$謹D$f(^L$fYD$)$$L$H(ff.HLq Yf/f(wNfW Yi-qXf/w f/ vMf(HBfWX\$oYA\$HY\D ppf(Y@YXX pYYXpX pYYYXpX lpYYXpX \pYYX|pX LpYYXtpX dpHY^YXXH8f/_f(f(D$(fffY`WL$ )$$L$趷f(BYYf(T$ $nL $-T$d$ f/\$(v f(H8HYYf(\$ f(XT$\Yf(Y $fHnY:Gf/BT$\$ f(v\%0fW@f(d$f(f艟Ad$X$Xf/ f(\ r\ f/X f(H8@ff.zu f.zu lSHf/w f/uv+1ҾH=Δ 1+ ^H[f/v%11\f(f/g\y Qf(YXYX AYXUY\ 1YXEYX !Y\5Y\ IYX%YY\YXY\^YXY@>kfYf. Qf(T$=T$Pf(^f/f(\ ^f(Y֣XXYXYXYX~YXYXnYXYX^YXY\NY\zY\>Y\jY\fY\bY^\fWfY8pX0XYX(YXTYXYXDYXYX4YXYX$YXYXYXآYXYXXYXY^ f(v?f(ff.ff.VH8~f(f(fTfTf.(f.z"u ff(f/H8ff(Yf/ f(^f/l$(\$ d$<$<<$D$|$f(^o *\$ d$|$$^f(f(Zt$l$(f(YY$f(YyY\ff/\fWH8fD^%f( $ t,$YYffDl$ \$d$|$s 3|$Yf(^e $K $\$d$Yf(|$XYYf(f(f(\ ^4$4$l$ f\f(ff(f(f(,$ڸ,$fff.f.zH(H$H(fHf.zH(H̜D$H(Ðf.z \陰ff.f(z\eD~ff/r f/s t;f.{Eff.zt)H(ILD$fWbH(D0uVff.ff.Sf(fH@f/_5f(f(t$(^f(fW-f/If/f(;f/ !vf/-|$(<$|$0=o|$8f(D$\$0X\$8Y؃f(\$fTEf/Ecf(d$ L$\$<;\$L$D$D$(\;T$L$d$ \$\f(^f.{If/OD$0$X\$8YJf=|$(DuH@f([@f/r:fW%zf(=l$(X^f(D@f(f(d$<d$$f(<XD$($^{Hf. d%Yf(fTf/w<L$L$f/ Yv-\f(H@f.>ff/f/hf(bbYYXXbYYXbXbYYXbXbYYXbXbYYXb H^YXÐf(f(\ HYXffW f(of(kY\fD1ҾH=fu 1 SfD1ҾH=@1 +fDff.zu tf.zu SHf/w f/v+1ҾH=. 1 H[f/v%1\f(f/ǘ\a٘ f(YXYX YXY\ YXYX Y\Y\ YXYY\}YXyY\}^YXYq@s2fYf. Qf(T$F2T$f(^f/f(\ T^f(Y6XXYXYXYXޗYX YXΗYXYXYXY\Y\ڗY\Y\ʗY\ƗY\—Y^\fW~fYЗXXYXYXYXxYXYXhYXYXXYXYXHYXtYX8YXdYXYXTY^ f(3f(ff.ff.z"H(IL$H(@ff.@f.z"H(IL蹓D$H(fDff.@f.z \yff.f(z\ED~ff/r rf/s lt;f.{Eff.zt)H(ILD$fWBH(Du6ff.ffH(f/\$T$H+T$fHn5 T$f/wf/v%\Y}-YD$H(D\Y\-YD$H(@H%8fWPT$d$]ff.@Sff(H0f/Y fH~fT L$5t$\$(t$ H%f(T$fHn4%T$f/f/\D$YmT$ ,YD$(T$ D$Hf(fHn+4f.+m|$f/}\}Y X,f(|f/D$L$vvfHn4T$YfHnT$ 1L$T$YH0f([\T$(Y+YD$ T$(D$.fDhYD$3f.EL$l$f~Yf.fTf(ff.fTzSfV U@H0f([=-fW|$|$(l$ ffT$(D\Y*f(fW vf.`YT$Y RH0[YYYYf(T$fTfV~?ffHf/vfW* r1 f.{Of/w!\AYH*\Y)fWHfufHD 8f/wzf/2wpY ZY\ ZYYX ZY\ ZYX ZY\ ZYYX ZYXH5\HfSff(ȻH f/v fW f/ KU~5f(^y`f(fTf(f.{f(¿L$T$T$1~s-Cf(T$L$fTf.T$L$1T$L$f(f(\,tXT$Ѓtۃ_YD$\Y Yf(YуxY\tYXpY\lYXhY\dYYXufW{H [DH,f5GfUH*f(fT\fVf(H,f5fUH*f(fT\f(fVM `Y\ TYX PY\ LYX HY\ DYX pY\1ҾH=1 H f[ffH(f(f/vfW Ff/ ~ 5f(^]f(fTf(f.f(¿L$T$T$V/~-f(T$L$fTf. T$L$/T$L$f(f(\,tXbT$ƒ ]YT$N\Yf(Yf(ȃY \ YX Y\ YX Y\ ~YX Y\ufWH(ÃDfDH,f5ofUH*f(fT\fVf(H,f57fUH*f(fT\f(fV"1ҾH=1K fH(fY \ YX Y\ YX Y\ YYXff.@fHf/f/=fD Uf(&-;f(5GD^f(fTfD.Y\ f/wQf.{^f.Zf.1ҾH=r1( Hf(\fA(f(f.zuf(Hf(fDH,ffUH*fD(DfDTA\fVf(=@fWhf/Ȓ=@0fD(1ҾH=1p fHf(f(f(HfYh\$$\$HYf(f.fHf/&f/5D f(.=kf(-wDF^f(fTfD.YS\f/saf(fA(\f.{\f. X f.1ҾH=1K Hf(f.f(\f.zuf(Hf(H,ffUH*fD(DfDTA\fVf(5@fWf/5hXfD(1ҾH=1 fHf(f(Y \$f("\$HYf(fDf(HÐYXYXYff.@ff.f/~ XfTf/ zf/f(d@\Yf/wf/v@^Xf/wf. f.Y5ʐf(\~f(f(Y\-Y\Xf(Y\X5f(Y\\-f(Y\Xf(Y\X5zf(Y\\-nf(Y\Xbf(Y\X5Vf(Y\\-Jf(Y\X>f(Y\X52f(Y\\-&f(Y\\Y\X\YXY^Ð~ 5f(f(fTf(f.wJf. f(DfH觶f(sH^fH,f5WfUH*f(fT\f(fVf.끐^f(Ðf(Df/f.H(xNff(f/w@f/f.zTuRf*\^$1ҾH=er 1 H(fDh25WfD(fDW-af/ffD(D~0*fD(fD(DQ:D Af(PXD^ff(f(*DYAYAXXfD(f.fETz f/fD/@f(^D\D^fE(fETfD(fD(fD(f(f(fE/v~ЍPiff(f(YY*\f(H(1ҾH=p 1K kfDfA(|$x"|$YFff(|$Dl$l|$f-\GHDl$\fHnff(*ȃ^X9ufEf(f(D*A\^D~1f(f(DX8XfA(Xf.^Yzf/t f(^Xf.zf/tf(^fATfA/wffA(\$*DD$l$l$DD$YD$fA(YD$\$\DfA(fD(AYfD(AYfD(f(AYfD(f(AYfDfD//>wfD(fD(f(f(@f(fW L$ L$^_ff(H(Sf(fLnf(ff.ff.f.SH xMff(f/w?f/_f.‰zQuOfJ*\^!@1ҾH=n 1{ #H [Dh25fD(fDWf/ffD(D~ *fD(fD(D5D<f(PXD^ff(f(*DYAYAXXfD(f.fETz f/fD/-N<f(^D\D^fE(fETfD(fD(fD(f(f(fE/v~ЍPiff(f(YY*\H f([fD1ҾH=ul 1 kkfDfA(|$|$YFff(H|$D\$ H|$f-BH+D\$\fHnDff(*ȃ^X9ufEf(f(D*A\^D~ f(f(D3XfA(Xf.^Yzf/t f(^Xf.zf/tf(^fATfA/wffA(\$*l$DD$kl$DD$YD$fA(jYD$\$\DfA(fD(AYfD(AYfD(f(AYfD(f(AYfDfD/-9wfD(fD(f(f(@f(fWL$1L$^_fH f([f(fLnf(f.H(xNff(f/w@f/ f.zTuRf *\^$1ҾH=i 1; H(fDh25fD(fDW-f/ffD(D~*fD(fD(D1D 8f(PXD^ff(f(*DYAYAXXfD(f.fETz f/fD/8f(^D\D^fE(fETfD(fD(fD(f(f(fE/v~ЍPiff(f(YY*\f(H(x1ҾH=5h 1+kfDfA(|$|$YFff(|$Dl$|$f->HDl$\fHnff(*ȃ^X9ufEf(f(D*A\^D~f(f(D/XfA(Xf.^Yzf/t f(^Xf.zf/tf(^fATfA/wffA(\$*l$DD$+l$DD$YD$fA(*YD$\$\DfA(fD(AYfD(AYfD(f(AYfD(f(AYfDfD/5wfD(fD(f(f(@f(fWlL$L$^_ff(H(鳯f(fLnf(fEf(f(fA.z,u*fA.zuD-AXD^fA(SHPfD/p-~=1D~f()|$@D)D$0d$ t$l$($J$Y$l$(D$f(T$X,$sT$,$1d$ t$fE\$fD(D$0fE(Xf(|$@D pXY^f(fAWY D=tsfA(fɃXfEfD(*fD(DXD*XXAYDYAXYfA(^Yf(A\^fTf/ wtfEWHPfA([f~=X-(f(f(fTf(f.-,w2f.z]u[D~1fAW,‰)QfDH,ffUH*f(fT\f(fVf.{D~־1 ff.@AUfATU1SHHf/D$ $T$0rA\$1f\$,D$*\ BsfTJf/@4$ff/o5gHDŽ$\f/t$vC  $T$0H$D$$ Hĸ[]A\A]ff/uvut$0\t$\$ fH~\4$f(t$ t$\$ f(D$p\f(fTaf/*f(ff/ HDŽ$,t$t$ D$ H D$(fHnXT$ D$8f(T$@L$8t$Xt$Xf(t$xL$8L$8T$X$\$f(L$8XL$8T$@\\L$(f(L$8t$xY$L$8l$YD$ XYL$@l$8aT$8H t$@YfHnDf(X-f.-df.f.-<~x |$ Xf.=&f.f.=XL$XXL$f. ޸xf.nf. :X$$Xd$f.%\%f.f.%sDYL$A\^f/-of(\D$(YX^Yf(Yff.z ^fTf/|o|$pff.y  H Z-Rf\l$ DD$D$fHnfHn$DL$@fA(fA(ʃXXXXAYYf(XX^Y^X9uD$0d$@t$8ߡD$D$ Ρt$YD$xt$ D$($YD$(d$@YD$ YD$ D$X$$X4$D$f(rYD$t$8YD$YtfW5L$pD$4$ t$pff/4$IY$D$ X@f(\$ f\$,$*\ ~mfTf/MHDŽ$pT$0 $L$D$L臜7p$f/X\T$LL$\$ $D$=LD$(D$ LD$D$ fHnL$ l$0LD$\,$\f(l$8L$@踦L$@fD$\A*f(|$ d$ L$YD$Yd$(d$(f =6X|$H$l$8\$D$ fHnf(f(L|$ t$LfW5Yf(|$LD$fH~D$fHnLD$\$fH~åfD$A*4$fHn\f( Y$d$(YD$f(fT%]XfTQ_}#4$Y^X$X$$D$024$$Y'fD(fDf(f(Mf(ft$`f.T$Xl$PL$Hd$@|f(|$8=|$8f(d$@L$Hl$PT$Xt$`ft$Pf.T$Hf(d$@l$8l$8d$@T$Ht$Pf(@ft$hf.T$`l$Xf(\$PL$H|$@d$8d$8|$@L$H\$PfD(l$XT$`t$hft$hf.T$`l$Xd$Pf(\$H|$@L$8L$8|$@\$Hd$Pl$XT$`t$h~1ҾH=#1|$8?|$8f(fWfTfV UX1ҾH=ӵ1L$H\$@|$8L$HD~|$8\$@f(d$Pl$XfAWT$`t$hfATfV D1ҾH=S1l$@d$8il$@d$8T$Ht$Pf(fW fT fV % 1ҾH=1d$P\$HL$@|$8d$P~|$8L$@fD(\$Hl$XfDWT$`t$hfDTfDVhfD,$|$~ Uf/fWfWf(\$ DT$0H$\$ D$D$^\$f(\ $0YD$$@11H=HHHĸ[]A\A]f(D$\$ fWT$0 $H$D$\$ ^\$f(\t$f(菕YD$$gf(t$~6HD$$f(fWfW,|$ D$0t$fH~D$D$$L$t$YfHn^$YYD$ D$ HwfHnDAVff(f(ATUSHf.HD$x$\$i<$t$ d$\f(fI~\f(l$Xt$ fd$D$0f.Ef.Et<$f.E„f(d$ 1t$t$fd$ D$8f/f(t$ d$d$ff(f/t$ '15L$=/f/fD(D\D$qff/T$L$~Af.ED L$f(fTf/w f. z8u6f(\$ cfTf/f(\$fTf/l$,$ff/ f/D$f(\$X\DD$@d$Pt$8f(fH~)T$ fTf(L$pL$f(T$ Ht$8\d$PDD$@\$XfHnfTf( bf/-f/l$ f/)T$@d$Pt$8DD$ \$WfInf\$DD$ f/t$8d$Pf(T$@ Fb1,$)T$`L$X\t$@\$PDD$8f(d$ l$hH f\$Pf/f(T$`l$fHnd$ DD$8\t$@L$XfT f/T$ff/^l$EX$謔$D$蜔$$YfIn$$l$D$f(YD$,$D 3dYD$x@f( a1\fTf/ff( `1\f(fTf/@SD-HĈf([]A\A^\L$0~f( `fTf/( ~ff/\$A~f()T$`d$Xt$@\$PDD$ D $f(T$` `HD\DD$ \$Pt$@d$XfHnfDTfA/ul$t |$8f/wf/\$$f(f(H|$xD bf(D$xfA/1ҾH=1,$,$fffA/+@ ^1ҾH=P1y-Z@ ^f(fTf/f(fWf(fH~ɦf/ f(f(f(t$0)T$ D$0f(t$ l$\$X\YD$^YfT$$f(p\$fHnHV$$l$f(fHnXXf/sf(T$ fT^XY f/ ]R- EL$fA(d$ $d$\$D$fInf(\Ql$Yff(fTfTf/f(fW fA(d$ t$d$$H^D$f(f(fHn\^t$f(f(d$ \l$Y]fW% f(fA("D _f(D$xRf.Af(fA(d$fW ɧd$$fInHD$f(fHn\^f(d$f(l$Y@fW5hf(C7f/T$ff/T$ [L$fA(l$-l$\$H|$x$D$fInf(#l$D ^YD$x-DfD(D\fATf/f/oT$ff/Xd$ff/R2fIn1\fTf( E[f/@fHnfHn\,$d$P\f(fHnt$^\$\$8l$0f(f(XXHt$d$Pl$0D$fHn\$8t$ \Xf(d$0f(f(X.~t$ \$D$f(t$PfWfWf(\$d$~e\$Yf(f(d$ d$0fWf(Jt$Y$t$0D$fHn T$d$0Yf(d$8T$D$0fIn YD$0t$PL$d$8f(t$0\Yf(L$貌T$t$0Yf(T$<$d$8D$0\f(YD$0l$ YD$YD$Yl$Xlff/T$\$$f(f(H|$xDD$ d$t$>t$D [f(D$xd$DD$ fD/%fEf(\D$0\$DL$@l$P,f(DD$8d$HD$xD*DX$4$fA(DT$d$4$DT$H3D$ \$f(f(fHnfA(X4$d$Hf(DT$f(D$xD\$ XfHnDD$8l$PDL$@X%Dd$fDfA(D\׃f(fD(XD\fA(\AY\f(\YAYAYAYAYAYYfA(X^fD(9uD$xf(T$f/ff/fDff.雸ff.ff/vΞDHH|$ ڐHD ff.AWf(f(AVAUATUSfH~HHl$xfW-\$`l$h-X$\l$pff/ f.f/f(f(HDŽ$XXHDŽ$$$T$`D$p|$0L$ht$ 5Xt$`HfH~L$fHnf($$fHn計4$YfH~t$ f(苈|$0$f(w<$fHnYfHn^YYD$$5$,X$f(fT f/ 5H֜L%ZfW= fI~HD$H5 H-D$PfI~t$0ft$HE1*Yt$PfInf(fW l$Xt$H $ $fInf(X%AT$ L$f($$OT$ fIn$$f(L$X^fTf/AA~= f/sf(\$Xf\śYH H^fHnX Y\^t$XfInf(XYf(Y^X^fT gf/w)X-Q^HXX-=YL9u@YT$HfHnXfT!f(fTfH~YD$0f/w d[5H$X$f(fT ˜f/AHfWL%&=- 5 HD$HD$PfI~fI~H-zt$0@fl$HE1*Yl$PfInf(fW Mt$Xl$H $G $fInf(X% T$ L$f($$T$ fIn$$f(L$X^fT͛f/AA~5 f/sf(\$Xf\YH5H^fHnX VY\^|$XfInf(XYf(Y^X^fT /f/w)X-^HXX-YL9u@YT$HfHnXfTf(fTݚfH~YD$0f/w d[5HH$X$f(fT f/=HjH-fWv-n5fI~HD$H= D$PfI~fI~|$0fDf|$HE1*Y|$PfInf(fW l$X|$H $ $fInf(X%ɗT$ L$f($$T$ fIn$$f(L$X^fTf/AA~=a f/sf(\$Xf\MYH BHc^fHnX Y\^t$XfInf(XYf(Y^X^fT f/w)X-ٖ^HXX-ŖYH9u@YT$HfInD$0XfTfI~fT=Yf/w d[HqL$$$fHnfL$`fT$x)L$)$f(L$f($f$$D$p$L$h$f$$)H$HDŽ$0$(fDŽ$8f(D$$f(f(f(Yf(YYYf(\Xf.d $X$XHH[]A\A]A^A_@l$`ZD!f/D\L,MSHfDD$h1DL$pf(f(fLnffA(H*XHfEL*DYf(XXDYYDYYfA(A^A^fD(f(EYAYf(AYD\f(AYXfA.AXAXI9HfE(fD(HHCHffA(҃HH H*XXH3HHfEHH L*EXD$f.5/f.f.5-fI~$BfH~$"fH~PL$ L$hf(D$D$pot$`fW5!|$ D$0fH~t$ $fHnf(fHnf(l$`D%ǒt$Dt$0fD(fD(DX|$ XDYXDY,$DXfD(fHnf/D,$wL,MHZfE1DD$hDL$pf(f(Dt$fLnf(t$ f.ffA(H*XMfI*YfA(fA(XAXYYYY^^fD(f(EYAYf(AYD\f(AYXfA.f(AXAXM9]LfE(fD(IHCHffA(ăHH H*XXM3LLfHH H*Xf(\L,I?fHn\L,I?v$ff.$fI~9ff(D$`fHnl$ d$0f(f(|$XX4$$f($裾d$0l$ f4$YYXX|$$$0Dt$t$ $fE(DYf(YYD\fA(Yf(XfD.f($$fHnfA($ffT$xDD$X)d$0)T$ DT$PD\$|$H$fHnz<$D\$YfA(<$DT$PD$fA(mYD$$Y$t$fH~f(襦|$H$f(荦-ݎ\l$`$f(,$hH$fHnnt$f(d$0f(T$ L$hf$$D$p$,$f$f(H$HDŽ$0$(fDŽ$8f(谱DD$X$$fHn$ffDfY$fAX)$$L$x$fI~;1ҾH=Β1$fWfTfVfI~ff(UfA(fA($$d$Xl$PDT$HDd$0Dl$ DD$D $d$X$$l$PfD(DT$HDd$0Dl$ DD$D $fA(fA($$$D$D$D$Dt$XDl$PDD$HDL$0Dt$X$$fD($f(Dl$PDD$HD$DL$0D$D$x$f(f($if(t$f(f(fA(|$Pt$HD\$0DT$ Dd$(|$Pt$HD\$0DT$ fD(f(Dd$fAVf(ATUSHfT W-7f/]ff.t$`= ~51H-YfW)t$@D$PD$0fI~=|$ =|$(l$0fd$ E1Yl$P*f(f(|$8fWL$@l$0ADXd$ T$AL$f(d$T$|$(f(d$L$X^fT=f/vfInD$(YT$0^T$8XfTfI~fT5Yf/w\*Nf(-ԉf(\l$ f(fT‹L$f/w(XD$ H|$|{fI~HĈfIn[]A\A^IL$fD$hf.l$`B-!~5iL%;YfW)t$@L$XL$0l$8-^l$(t$0fd$ 1Yt$X*f(f(l$PfWL$@t$0Xd$ T$L$f(d$T$l$(f(d$L$X^fTf/vl$8YT$0^T$PD$(XfT]l$8fT-OYf/w**fI~l$8|$hX|$8fI~d-f/f(l$ t$PHY\f(f^X Y\^|$Pt$(f(XYf(Y^X^fT |f/t$ ^HXXXYI9u-2f/f(\$8l$ HAY\^fX Y\^t$8|$(f(XYf(Y^X^fT ňf/|$ ^HXXXYH9u\AWfI~AVAUATUSHD$Xf(l$HL$`T$x\$ sq|$x\|$`$f(fH~t$fInfW52L$HT$`fYf(fW d$fW$$\$'fH~D$xL$p$D$XY$fHnl$|$ d$\$YYJf/t$0l$8 H,ff(H$-CE1,$fDfH*l$ \\,$MfI*YfHn|$(\XL$`t$\$YfD(DYf(\$Hf(YfInAY^^t$|$(Xt$X|$f(f(L9tnL\$Id$H:HƒfHH H*X%@LLfHH H*X!-,$fd$0l$8f(f(YYYYf(\f(X$$f.2$|$XfW=Ɇ$$f(fH~D$XL$ȵD$fHn踵YD$l$fHnYYD$xfH~l$infHnl$x\l$XYl$P$d$Yf($Y-f(D$P\fTf/$l 藻l$ X,$D$p$f(T-=<D$hD$X$$Xf(fT vf/,5l-LH-зfWXt$05Jl$(-dfI~5_D$8fI~t$@fDfl$(E1*Yl$8fIn$f(fW l$(L$L$fInf(X$$T$L$f(d$T$fInd$f(L$X^fTif/AA~-=f/sf(<$$HNY\f(^fX Y\^fIn$f(XYf(Y^X^fT ̂f/w&4$^HXXXYH9u@YT$(t$0D$@XfTt$0fT5tYf/w dY$XD$P$f(fT <f/J-25H-fW=>l$(-t$85*fI~$fI~t$@f|$8E1*fInY$$f(fW |$8L$L$fInf(X$$T$L$f(d$yT$fInd$f(L$X^fT.f/AA~-f/sf(<$$HY\f(^fX ~Y\^fIn$f(XYf(Y^X^fT f/w+4$^HXXXYH9ufYT$8l$(D$@XfTBl$(fT-4Yf/w dQ$A$$D$`$L$ t4$\t$xXt$`L$ D$$f(tl$Y$l$ӯ|$`X|$ ft$l$fH~fI~l$fH~$Y]$T$hXT$p\T$0\T$(f(X$YYfD(f(DYYD\XfA.fE(fD(|$<$fIn\$H$l$(f(f($t$ XDL$@D$DT$8^$XXD$pD$pf(^L$XXXD$hD$hf(^f(XD$0D$0D$P\\^$X\$Xl$(XXYfXI*YfHn^|$$f(f(f($f(DT$8DL$@D$YYY\f(YXf.:f(f(X|$fA(fA(l$@DXD$t$8|$DD$L$D$D$Y,f/D$)It$8l$@I  IEf|$PH*f/f. f(fD(fD(fD(D$X4$fInD$$\$HDL$@X\D$xDT$8XXd$ |$XXYfI*YfHn^Q|$D$f(f(f(DT$8YDL$@AYY\f(AYXf.f(f(f(D$fA(DT$@|$8DD$;DT$@D$|$8DD$f(f( f(\H,H?f+l$ X,$=pD$h$f($X=y$f(fT {f/ -=xH-ufW{5l$0-|$(= fI~D$8fI~|$@ft$(E1*Yt$8fInf(fW {l$pt$(L$L$fInf(X$$T$L$f(d$_T$fInd$f(L$X^fTzf/AA~-f/sf(<$l$pHY\f(^fX wY\^t$pfInf(XYf(Y^X^fT }yf/w'<$^HXXXYH9uDYT$(|$0D$@XfT2y|$0fT=$yYf/w da$D$XX$f(fT xf/ 5-vH-FfWy=t$(5l$8-fI~D$pfI~l$@@fl$8E1*Yl$pfIn$f(fW \yl$8L$[L$fInf(X$$T$L$f(d$,T$fInd$f(L$X^fTwf/AA~-f/sf(4$$HƪY\f(^fX nuY\^fIn$f(XYf(Y^X^fT Dwf/w&4$^HXXXYH9u@YT$8t$(D$@XfTvt$(fT5vYf/wdYf$XD$P$f(fT vf/2=5tH-fWw-|$8=t$p5fI~$fI~t$@f|$pE1*fInY$$f(fW w|$pL$L$fInf(X$$T$L$f(d$T$fInd$f(L$X^fTuf/AA~-rf/sf(<$$HY\f(^fX +sY\^fIn$f(XYf(Y^X^fT uf/w+<$^HXXXYH9ufYT$pl$8D$@XfTtl$8fT-tYf/w dQ$1$$D$`$L$ Di$\T$xXT$`L$ D$f(T$it$Y$t$Jl$ f|$`DD$T$fH~t$XD$t$DY$f(Xf($$T$hXT$0\T$(\T$8f(X$YAYf(AY\f(YXf.jfD(fD(f(fA(H$AXt$8\$HD$DL$xDT$p^|$`$d$@XD\$XD$hD$hfA(^L$XXXD$0D$0fA(^fA(XD$(D$(D$P\A\^$X\$XXl$ t$8Yf(fH*AXfHnY,$^fIn=,$D$$D\$fA(d$@|$`f(fD(DT$pDL$xYYDY\f(AYAXf.9fD(f(X|$Xd$fA(D\$pfA(l$`t$@DD$|$d$L$$D$Yef/$wPH DD$t$@l$`D\$p1ҾH=9t1b= o|$|$$l$$d$f(Yf(YYY\f(Xf.X$X$H[]A\A]A^A_fDf.-nf. f.-n93-Tnl$09f|$Xf.=nf.f.=n-nl$0&L$Hf(fIn$%HmL$8L$ XL$PD$@fHn<$t$`D$\f(t$x\f(Pl$<$L$ YD$P\Xl$BdYD$\$8fInT$@F$fD(fD(fD(f(\D1ҾH="r1K-ll$l$$|$$d$f(Yf(YYY\f(Xf.$f(f($t$Pf.5lf.f.5l-6ll$8|$Xf.=lw~f.zxf.=rl5/-kl$(t$Pf.5Rlw-f.z'f.52l-kl$(|$P|$(zt$Xt$(|$P|$8|$X|$0$l$0Cl$Xff.D$XD$0$ff.N$ģD$0|$Pff.D$P蚣D$(|$Xff.{|D$XtD$(|$Pff.{D$PND$8u1ҾH=o1輩D$PfWnmfTfmfVD$8u1ҾH=Zo1|$fT-+mfV-Sl$(81ҾH=o1=D$PfWlfTlfVD$(1ҾH=n1$fWlfTlfVD$0m81ҾH=n1貨$fT-alfV-l$0f(f(f(D$DL$@DT$8|$菻|$DT$8DL$@f(f(D$tf(fA($D\$`l$@t$D$4D\$`l$@t$D$fD(fD(f(f(@f(f(f(D\$xfA(l$pDL$`DT$@|$$$Ⱥl$pD\$xDL$`DT$@fD(f(|$$$`f(f($d$@l$8t$ld$@l$8t$fD(fD(fD(f($f(f($#\$8T$0f(f($$ff.黜ff.f.ff/w%,gf/v.H1Ҿ1H=I e gHh5gf(fTf.wBf/wf*f/wf.{xf.f(\\zvutf(f(ǽH,ffUH*f(fT\f(fVf/v [^HfDff**pff/w]f/wy,H1Ҿ1H= ]HfDff\Ѓ**f(f(ff/wf/R]wy,H1Ҿ1H=n 苜3]HfDff**頞ff/w\f/wy,H1Ҿ1H= +\HfDff\Ѓ**f(8f.ff/w%|\f/v.H1Ҿ1H= 赛]\HH^5]f(fTf.wBf/wf*f/wf.{xf.f(\\zvutf(f(H,ffUH*f(fT\f(fVf/vf(fHf/wT[f/v&1ҾH=} 1葚9[H@5(]=[f(f(fTf.f*f/wf/f.f.\ f/~]d$fWf(d$Y[~]fWNH,ffUH*f(fT\f(fVf*f/GfD0ZXf(f(Hf(韛f(Df(\f(HYfHn\f(ff.f.fH(f(f/w-Yf/v&1ҾH= 1iYH(@X[5(Zf(fTf.wzf/wf*f/sf.$f.f(\f/%\t$f([t$^ ZfW[fH,ffUH*f(fT\fVf(f/WfDXf(f(HQXd$Xt$fHnf(\$ՙf/%XH.Xt$\$d$fHnvW\f(f(H(f(4@f(f(f(^HWfHn\f(]f(f(f(ff(f(DsXf/~ Yyf(%uWf(f(fTfD.f.|uzf(fTf/Xwf.zbu`fD(f(f(fDTfE.[f.z-u+-VYf/vf/vf(\ ff(f/BfHH\fD(DXYf/r f/f(|$fT\$Y) $f/fA(f($$X\DD$ʋ$$DD$A^^f(HH@H,ffUH*f(fT\f(fVf..fDfA(d$8T$ DD$0 AT$ f( $DD$0fTT$(^L$ $fA(@T$(\$D$l$ Yf(T$X\$(Y^f(DXf(D$膬|$T$f->YD$,f/YD^f*f.f(~ Wf(fTf(fD.v3H,f%TfUH*f(fT\f(fVf./)Tff/,Յf(f(ĸDfff(*XY\Yf(fTfA/v^f(9u^ÐfA(f(DD$X\c}DD$$fA(警 $fW VHH\f(oH,fEfUL*fA(fTD\fA(fVf.rf.f.\$(d$8z u\רud\d$D$Yf(臥D$d$HHAYYDYD$f(UD$AYD%Rf(ÐAVATUSHxD$0f( $蒥t$0 $f({^f/f(_f.|R $f(=}Rd$05|$f(f(ft"Xf(^YXf(Yf/rL$Y^l$0Hx\[]A\A^f(fD5R=8f(ffWUt$f(t$0|$ =tFff(*^XYf(f(^XfTSf(fTSYf/rf(l$P1l$05KQYfI~f(fTNSf/Lff.l$05H-YfW- Tl$Hl$(t$8fDl$(fd$E1Yl$H*f(f(|$@fW Sl$(DAXd$T$AL$f($$誧T$$$f(|$ L$X^fT_Rf/vt$8YT$(^T$@D$ XfT5Rt$8fT5'RYf/w *fInHl$l\T$8@f(\L$f(fTQ $f/f(w芢 $fD$Xf.-iH-YfW RL$HL$(l$8|$(fd$E1Y|$H*f(f(l$@fW UR|$(DAXd$T$AL$f($$*T$$$f(l$ L$X^fTPf/v|$8YT$(^T$@D$ XfTP|$8fT=PYf/w *D$XfInHl$lXD$8\9 _NHx[]f(A\A^XD$Hl$lHe@fIn\ Nf(fT(Pf.f.f(fW Qzfl$fTfUfVD$0H $?f(fIn\lYD$P $Hx[]A\A^\f(rfInHl$l]fMf/wyf/bMwof( YYYX XYYXL$XzYYXM\^XfW Pf(蠦f(\L$fW O2HD$8D-f/f(|$l$@H́Y\f(^fX tLY\^t$@|$ f(XYf(Y^X^fT LNf/|$^HXXXYH9u-f/f(t$l$@HY\f(^fX KY\^t$@|$ f(XYf(Y^X^fT Mf/|$^HXXXYH9uff.@ff/wf/wf.z:u8f(H1Ҿ1H= gKHf.L%Kf(fTf.%Jw X!H,ffUH*f(fT\fVf(Xff.ff/wfJYYH1Ҿ1H=> 觉OJHf.f(f(ff/wYf(qH1Ҿ1H= WIHf.ff/wf/wf.z:u8IH1Ҿ1H=- IHfK%hJf(fTf.%tIw XH,ffUH*f(fT\fVf(X錝ff.f.f.AWff(AVAUATUSHxf/r=Hf/s8HYH= 1&%HHxf([]A\A]A^A_f/f(v^~=JDIfTfA.wBf/rLf(fTfA.w=f.zGuEf.zQuOHNx%XHf(H[@HK@f.{f.Hz/u-f(Gu1ҾH= 1N%G#%Gf(͈D$YT$ \\$l$f/fI~fI~roHGfHn\$D$fl$T$ \fD(fD.zkuiHjGfE(fLnfHnfD.fA(zH9GfHn臛fMnD$T$ D\\$l$ffAPfEfInH FfD/λVD*Af/%GfLnd$lAl$0\$8T$@f(f(fInDL$(D\$ DT$d$̚DL$(fD\$ d$DT$fE(fMnD\fA(fEfAPуD*fA.EՄ|fD.DфiEf(HuFA\YD$fLnXfA/r fHnAfD(HH`K H= 1%Ef/ 5fHnL$fD(l$0\$8T$@ffD(fA(fInd$(DL$ D\$DT$聙DL$ fD\$DT$d$(fL~fMnD\fA(fEfAPуD*fD.EфfD.Dф@cfA(\YD$%EAXf/r f(ĽfA(H1ҾH=T 1贃%4DfD.z|d$A\fEPHDAdl$@fHn\$fD(T$HTDT$f~=Ef(\T$DL$ Dd$(fDPAE8tHH\$HD$fL~fE(fLnfA(f(fTfTf/#fA(fD(D\$f(fTE\Y nX . fA(fT^f/ 1CufD.l$fHnfA(fA(fD(A\\\E\^BD^\f.Qf.-B\MQfD/JfA/?fA(f(\^fA(^f(fHnA\A^YfA(\Yf(^fA(A\D^AYXD\$8DL$0DT$(T$ L$5L$=B\f(躖HT$ DT$(DL$0D\$8EfD(AYfL~fInDd$(f/l$DL$ fInDXfA(DT$fInDd$(DL$ \~=CDT$fH[AfHnd$fE(1Al$8\$0T$@f(f(fInDL$(D\$ DT$d$c\D$0fDL$(D\$ d$fE(DT$fD(fPfA(ÃfD.fED*EՄfD.عEфE!f(HAA\YD$fLnXfA/r fHnAfD(H1ҾH=0 1fl$@\$H< T$HH= f(f(P%?%l$8\$0T$@ fD(fA(fInd$(DL$ D\$DT$\D$0fDL$ D\$DT$fL~d$(fD(fPfA(ÃfD.fED*Eфu\fD.عEфuH@fA(\YD$%?AXf/r f(ĽfA(H!,l$8\$0T$@fE(fLnpl$8\$0T$@Yl$0\$8T$@l$0\$8T$@.Nf(D\$hDd$`DL$XDT$PT$8l$0Dl$(\$ L$蒔D\$hDd$`T$8l$0f(DL$XDT$PDl$(\$ L$/D\$hDd$`DL$XDT$PT$8Dl$0\$(d$ L$D\$hfDd$`DL$XDT$PT$8Dl$0\$(d$ L$f.f.fH(f/w0f/f(w&f.zHuFf/2=w-0=H(1ҾH={1c| =H(fDf.{J~>%b=f(f(fTfTf.v,f.wf(<t@f.f(f/\fT^vf/v-=f/@f/=F<f/v f/f(L$\$9IfH<\$f.L$fHnf(f(D%f( t#Xf(^YXf(AYf/rY^;f.wdf(Q^f/f(H(RHTf(藏H8;fHn\f(#f(L$d$\$cL$d$\$f(nfH(f/wBYf(f.z"f/wVf/wPf.zrupf/:w/:H(D1ҾH=p 1y:H(fD1ҾH=˚1y[:H(fDf.F~>< :f(f(fTfTf.f."f(f/^\fT>^v f/v-z:f/f/=9f(f/v f/ f(T$\$FfH9\$f.T$fHnf(f(Df(t#Xf(^YXf(AYf/rY^f.\f(Dtf8`f.w_f(Q^f/f(f(H(Et3ff(H8fHn\f(f(L$T$\$賎L$T$\$f(sfH(f/wJ8YYf.z"f/wVf/wPf.zrupf/7w/7H(D1ҾH= 1#w7H(fD1ҾH=1v7H(fDf.>~9%7f(f(fTfTf.f.f(f/\fT^vf/v-7f/f/=7f/v f/f(L$T$CfH6T$f.L$fHnf(f(Df( t#Xf(^YXf(AYf/rY^f.df(Dtf06hf.w_f(QE^f/f(H(Bt3fDf(7H5fHn\f(f(d$L$T$d$L$T$f(sf.fH(f/w(f/f(wf.z@u>f/Z5v%f(f1ҾH=1t35H(fDf.{R~%75f(f(fTfTf.vYHL$8XH4H YHYXHtXYXH YYXHYXH YXHYXH YXHYXH X H4H YYXXH4YYXX H YYXBXH4YX H YXH4YX H YXYX YX YX A^D^(f/DD$v f/f(=\\ X ^f(fTf/sfD(fD fDW HH=t1AYfH*f(^XfTf(fTAYf/vYf(T$(Ym\$ ^XuDD$~%T$(\$ DY D1ҾH=3|1\$(T$ DD$[\D$5DD$~%T$ \$(,$Yf(\^A^\f(fTf.w-;YY,$\^\ЃH`f([]A^@$5Xf/wf/1\$HT$@L$(l$ ml$ L$(T$@\$Hf(\fff.B5|$0f(fTf.Zf.!f(HX:H1ҾH=z1$Y$H`[]f(A^@$fDf(\$HT$@l$(sT$@l$(D$ f(^f(\$Hf(\$(pYD$ DD$\$(T$@~%DYf(ff.d$f.$$/!f5fInfD=Кf(DY5_YDXX=DYDXКYX=YDYDXYX=DYDXYX=tDYDXYX=bDYDXYX=xYA^YXXfD5f\D$8H`[]f(A^f.fInf(f/eM\fT^vkf/ve-f/vWf(f(t$@DD$(T$ \$$\D$\$T$ DD$(~%t$@f/f/$t$@f(f(DD$(T$ \$v f/0[$fT$ DD$(f.~%.\$t$@D$f(D <fA(fA( t)AXfD(D^AYXfD(EYfD/rY^\D$(3fod$f/%rl $H`f([]\A^r}ff.f(Q|^f/^rfD Dkjf($\QfA(\$@T$(l$ t$7l\$@T$(~%l$ fD(t$f(T$Ht$@L$(DD$ \$kT$Ht$@L$(DD$ f(\$ff.fHH~TfD(f(fD(D\fDTAYfA(fTf/vpf(d$L$gd$L$H|$<Yf(f(\T$T$ y\f/f(HHVnfD=f(5fX\fD(D^%fA.UEQDafE/>fE(HDH4D^EYHfA(DXH4fE/H AHEYDXfAUAYEYDXH EYDXHEYDXH EYDXHEYDXH EYDXHEYDXEYDXEYDXEYDXBH[3HJHFHXH4H HAYXAYXH AYXHAYXH AYXHAYXH AYXHAYXAYXAYXAYXBD^f/E^Dd$v f/Bf(\\f(X^f(fTf/fD(׸fDWD fHH=OAYfH*f(^XfTfD(fDTEYfD/vDgfD(̸H2DXfA/(fD/q5f(YYXXQYYX5qXAYYYX5]X-YYX5MXYYX5=X YYX-Y)X^YXX\Y YY^Xf(jYD$HHf1ҾH=q1PfHHffA(L$(d$ |$l$^cl$|$d$ L$(f(hDfA(L$(d$ l$iL$(l$d$ D$^f(f(SgYD$YD$HHfA(L$(d$ l$Dl$DT$HfHf~L$(d$ fD(fHnHl$Dl$DT$fHn8f.~=f(f5f(2f.\f(XYf(fTf.r f.f/rf(Xf.zu5=D~(^Xf(fATf.r f.wf/rf(Xf.zuf.7UH0f/%vf(fTf/f(Xf/xf/&Hl$,f($$HT$t$$$HD$f(uL$\f(gt$T$fH#$$Yf.fHnf/wmf.f~f(fTf. cDf(f(fTfD.\f.z,Ǩt fWDf.f/wff.~~f(fTf. h=8f(f(fTf.\f.z:,ƨtfW:H0f(]~f(fD(D fTfD(fD.fA.OIDf(fTfD/-f/;f.z f/{ tfDf(DP5D~D~`f(fD(D & fTf(fD.v'H,ffUH*DfDTDXfDVfA.y fTf/cf(H,ffDUH*DfDTDXfEVfA.f(T$L$$$bL$$$Ht f(T$fD(f(f(Dd YfHnfD(D\AYD\ AY\f(AYY- YY^f(X^f(YA\AYAYAYY YYXXY^XY,fT% fWf(sfT5 fWf(ff(fD(fD(fTfD.v2H,ffD(fDUH*DfDTAXfAVfD(fA.oifTfD/UY cY H0]f(H,ffUH*f(fT\f(fVH,ffUH*f(fT\f(fVDYYRff.` ~=` f(f5 f(2f.\f(XYf(fTf.r f.f/rf(Xf.zu5=j D~ (^Xf(fATf.r f.wf/rf(Xf.zuf.7UH0f/%zvf(fT f/f(Xf/xf/&Hl$,f($$HT$t$\$$HD$f(EL$\f(at$T$fH$$Yf.fHnf/wmf.f~ f(fTf. 3Df(f(fTfD.\f.z,Ǩt fW Df.f/wff.~N f(fTf. h=f(f(fTf.\f.z:,ƨtfW H0f(]~f(fD(D fTfD(fD.fA.OIDxf(fTfD/-f/;f.z f/KtfDf(DP5D~D~0f(fD(D fTf(fD.v'H,ffUH*DfDTDXfDVfA.y fTf/cf(H,ffDUH*DfDTDXfEVfA.f(T$L$$$~\L$$$HDf(T$fD(f(f(D4YfHnfD(D\AYD\ kAY\f(AYYYY^f(X^f(YA\AYAYAYY YYXXY^XY,fT%fWf(sfT5ofWf(ff(fD(fD(fTfD.v2H,ffD(fDUH*DfDTAXfAVfD(fA.oifTfD/UYcYH0]f(H,ffUH*f(fT\f(fVH,ffUH*f(fT\f(fVDYYRff.f.f(H(HxQff.zu Hu`H(f(fTf.lvzf. R{HH(1ҾH=}1BH(fDf(H(ufH*YYXks^f.w/QD$fH*X3YD$H(H|$L$wXL$H|$D$@f.Uf(f(SHX~-5fTf(f.wZf.кfE„t f/f/wsf.f.f/f(HX[]@H,ffUH*f(UfT\f(fVnf.f/| f(Yf(fTf.:Xf.lf/bf(fTfTf/}f/f(fW=<$vfH~нf(H$^f(YX5f.DvQD^fA(AY[T$ \$A^t$DD$X5^f(RT$ f t$DD$Y\$XfA(^f.QD$f(DD$(Y\$ T$t$`YYD$DD$(fT$t$\$ f(XD$wAY^f.QD$($T$ DD$Y\$XH5: fT$ \$$D \oH m6fHnfHnf(~-DD$@f(ÍxYX9YÍxXA9YÍxXA 9YÍxXA09YÍx XA@9YÍx XAP9YÍxXA`9YÍxXAp9YÍxX9~rYÍxX9~_YÍxX9~LYÍxX9~9YÍxX9~&YÍxX9~YXt(YÃ~YÃ~YÃ~ Yà uY@tAY^XfD(@t fDW|fTAXfD/HY 9Kf(jf.H|$H1f(r|$HfHX*[]Yf/~ fWfW#H,ffUD H*f(fAT\fVf(fD1ҾH= 1;A @X fTYf/AYf/Y|$L$f(|$CL$|$f($YoYD$(YYX) HX[]1ҾH= 1: HX[]1ҾH=]1T$ L$|$:T$ L$|$'11ҾT$8H=]l$0D$ L$|$k:HLkT$8l$0D$ L$|$fLnf(T$(L$ t$!Qt$D D^f(fA(DD$AY\$PT$(L$ DD$\$f(T$0DD$ \$t$PT$0DD$ \$t$D$(T$(DD$ \$t$kPT$(DD$ \$t$D$f.Uf(f(SHX~- 5 fTf(f.wZf.кfE„t f/f/wsf.f.f/f(HX[]@H,ffUH*f(5 fT\f(fVnf.f/| f(Yf(fTf.:Xf.lf/bf(fTfTf/uf/f(fW= <$vfH~нf(H$^f(YX5i f.DV QD^fA(AY; T$ \$A^t$DD$X ^f(JT$ f t$DD$Y\$XfA(^f.QD$f(DD$(Y\$ T$t$@QYD$DD$(fT$t$\$ f(XD$W AY^f.QD$($T$ DD$Y\$PH5 fT$ \$$D ^D$ff(\ f(>T$f(^v+|ff.f(f(ff/vf DAUATSH@f.f({M)\$0)\$ f/ʻLl$Ld$ T$LL$w0$T$fɅudT$Bw(H  4uOuf/r~N)\$ ft{D$ H@[A\A]fW jfDLH=A D$$ T$D$f$fH fD~8 = f(f(fTf(f.f.f/Yf(fTf.v3H,f- fUH*f(fT\fVf( Y\,¨f(D$ fW )D$ H,ffUDb H*f(fAT\f(fV0fDLd$0LL$1$uND$wH5 4u9D$ f(\$8fW% T$0L$(D$ LH= $$f.f.SHH HL$$Cf4$\$f.z uN f(Htf(H [~8  f(fTf.w fTf.vxf.zRuPf.5p " f(@1ҾH= 1+# H f[f H f([fDff(f(t$H*Xi \$膜t$\$D$Tf( $fZ8E=D$|$f(f(YfA(f(YY\f(AYXf.fA(f(f(f(k5fDf H*9fY f(fff.@ -h f(f(fTf.v3H,f-e fUH*f(fT\f(fVf.fzf/tf// wHԓHf(ATfD(USHĀfD.f(&H)D$`)D$pFf.fD(7ffD(ѻfA/f(fA/OfA(fA(DD$DT$DL$@ TDL$DT$DD$f/fAXf/ T1ff/f.э@GfA/D$\5 fA(fE(HD$0t$8H6R=SLd$`fA(5SL%SfHnRfA(DL$DT$DD$DD$DT$DL$,ffD/)t$hd$`DL$(~= DT$ f(DD$fTfTt$d$9 R- d$t$f/DD$DT$ DL$(r H QYfHnY|$0\$8f(f(YYYY\f(Xf.WYYf)D$`D$\uYD$\Ld$`LH=ADL$DT$DD$zD$\DL$DT$DD$ht{L$hD$`H[]A\fDfDW fA/ jf.D$\Ld$`[f H[]f(A\ fA(fA(F fTf.fD.z fD/KLd$pfA(HL$\LfA(DD$fA(HDD$D$\w+H* 4tLH=@DD$-DD$ AY0ffYGfYD$pfXD$`)D$`fffD.fD/`ffA/AA HD$hD$`MDI,ffAU2 H*f(AfT\f(fVfDA,f~ fA(fA/fE(fA(fWfDW*\Y vfWH|$HHt$@DL$(DT$ DD$D\$L$1d$Hl$@L$D\$DD$DT$ d$0DL$(~e l$8)ŃGf(f(fWfWt$0d$8&  fA(fA( fTf.v5I,ffAU H*f(AfT\f(fVfD.ffA(fA(DD$*DT$DL$AY;DL$DT$D$`f(OEDD$L$hfYD$`)D$`JfD$\D  % AYf(f(fTf.wif.z f/Q {@D$\PH 4^@"DH,f% fUH*f(fT\f(fV_fDD$\fD;\$0T$8f(f(DL$ DT$DD$l$z,DL$ DT$DD$l$Uf.ATfD(USHĀf.f(?)D$`)D$p7fD.fD('ffD(ʻfA/f(fA/OfA(fA(DD$DT$DL$7 {LDL$DT$DD$f/fAXf/ IL1ff/f.э@GfA/D$\^5 fA(fE(HD$0t$8HI=JLd$`fA(5JL%KfHnJfA(DL$DT$DD$DD$DT$DL$ffD/)t$hd$`DL$(~ DT$ f(DD$fTfTt$d$0 J- d$t$f/DD$DT$ DL$(rk HHYfHnY|$0\$8f(f(YYYY\f(Xf.YYf)D$`D$\tSD$\Ld$`LH=9DL$DT$DD$:DL$DT$DD$txL$hD$`H[]A\fDW fA/0zf.D$\Ld$`kf h H[]f(A\P fA(fA( fTf.pfD.z fD/NLd$pfA(fA(¾fA(HL$\LDD$DT$DL$n@DL$DT$DD$ D$\wGH 4t9LH='8DL$DT$DD$DL$DT$DD$D$pL$xDT$fA(DD$fWW ^/ *DT$fDD$D$pfD/L$x L$AY9'YHL$YYD$pXL$hXD$`L$hD$`@I,ffAU H*f(AfT\f(fVVfDA,f~ fA(fA/fE(fA(fWfDW*\Y2 vfWH|$HHt$@DL$(DT$ DD$D\$L$k)l$Ht$@L$D\$DD$DT$ l$0DL$(~ t$8)Ńf(fWfWt$8d$0D$\gD@D$\H 4q3DYW D$DD$fA(DT$,T$DT$l$xYfA(l$T$p,L$DD$YfDD$\fD\$0T$8f(f(DL$ DT$DD$l$$DL$ DT$DD$l$f.AVfI~ATfI~UfH~SfH~HD$L$0ffHnfInf/D$Pf(f(XTd$l$o0 o l$d$f/ff/+HD$ HD$(5 f/t$vUy fHnfMfIn&fHnX=^ D$(L$ fInf(fH~fH~/D$fHn\fIn/5 f/CL|$f/#f(C8fIn)D$Pf(A8)D$`f(D8)D$pf(G8)$f(G8)$f(G8)$f(G8)$f(G8)$fHn$fHnf(~d f( fTf.fInfTf.H( ffHn|$t$fHn!%fInfHn%fInfHnH D$@Ld$PfHnL$Hf$|$t$fH \\fHnf(f(l$HL$@f(f(YYYY\Xf.ADffW] d$8*l$0f(f(YYX^^Xf(|$Xt$-|$t$D$f(f(u-Y@t$f/D$|$wHl$0d$8HD$(L$ H[]XXA\A^D @Jf(fTt f/f(f(d$l$1d$l$D$ L$f(f(,5 T$ \$YY#l$d$D$( f(fW= L$ \f(fI~fI~fH~fH~N,D$ fHnfHnn fTf.v+H,fs fUH*fTXfVf.WQff.C=1ҾH= 1x  H[]f(A\A^fDOOf(f(H[]A\A^Df(\L$ % f(f(fTf.fHnff/. f(fInX\$XT$f(fI~BT$f(f(,~X@ffInfd$*fInl$\D$!l$d$\\9uD$(L$ H[]XXA\A^fHfHnfInfHn݌XD$(XL$ H[]A\A^H,ffHnffUf/H*fV=W f(fIn\|$\T$f(t$0T$f(f(,%1fD$ffIn*XT$0l$d$l$d$XX9uL$HD$@t$|$%t$|$f(f(,ff.ff/rC%n 5> f(f(fTf.wDf.ʺE„tf.DЄu[H ~2 fWfW"HH,f5 fUH*f(fT\f(fVf(f(ff.@fHf/rC% 5z f(f(fTf.w0f.˺E„tf.DЄuGJ!HH,f5G fUH*f(fT\f(fV1ҾH=+1c Hf(ff.fSff(f(H@f/ :f/vf(f(PH@[f.~- f(fTf/wf(f(T$\5| $f(fH~'$=T$f/f(f(wD 8 - f(fTf.wZff.E„,f.DЄ1ҾH=*10 f(H,f- fUH*f(fT\f(fVn f(f(f(T$\ $%$=T$~-E f/f(fHn]fHn$\ D$0L$8f(f(T$%$f/ T$vgfHnf(Yf(f(D$0L$8XX@ f/fPèJf(f(դ~ ff(f(fWfWG \$(T$ fDff(\$*T$^Xf(^f(,$Xf(d$ $,$5*7d$f/ T$\$f(f(|$(t$ f(f(YYYY\f(Xf.@\$(T$ l$$$l$$$f(f( @~%P f(fWf(~%7 fW^fD% = f(~ YX%6fTfV.f(fTf.v5H,ffUD H*f(fAT\fVf(YfW T$\$\d$ V\$T$$L$f(f(2d$ f(s\\\$f(\L$_ff.@Uf(f(HSHH8fT f.d ~f(Y6f/f/= YbY- % L$(T$ f(f(Y^YXXYYXΊXYYXXvYYXXfYYXXVYYXXFYYX~X6YYXnX&YYX^X^YYXV^f(^\FYXB\$YX8YX4YX0YX,YX(YX$|$YXYXYfD( fA(XYXYXYXYXYXYXYXYXYXY5܉XYX^f(d$%|$$f(聫T$ \$d$4$- L$(f(Yf(YYYYX\^^- \X ff/v~ fWfWU1+H8[]f( ,YYYXXYYX \YYXXԆYYX\ĆYYX܆X܆YYXԆYX^YYXXYYXԆ\YYXĆXYYX\|YY%| XXY^-H f({Y8 8 L$|$^$f(b$|$Yf(X T$̎Y$-׾ T$L$\f.Uf(f(SHH f.L$0 L$8\f.Rff(f/wgf(HL$0LD$,f($ $'D$,v;tvT$0L$8HH[]f(fW fH) ,t11H= 0$f(#)D$0ufW l$0L$8f(l$L$\$a\$$f(轧$$l$L$f(HHYf([]YYY\Xf(Ð 8 HH[]f(f(f1ҾH= 1$V$ff.USHHf.f(-")l$0cf(f(f.Qff(f/wff(HL$0LD$,f($$&D$,v:tuT$0L$8HH[]f(fDfW@ fHI ,t11H= P$f(- ")l$0ul$0L$8f(\$l$L$艋\$$f($$l$L$f(HHYf([]YYY\Xf(f X HH[]f(f(f1ҾH= 1$v$!ff.USHHf.f(-!)l$0cf(f(f.Qff(f/wff(HL$0LD$,f($$&D$,v:tuT$0L$8HH[]f(fDfW` fHi ,t11H= p$f(-@ )l$0ul$0L$8f(\$l$L$詉\$$f($$l$L$f(HHYf([]YYY\Xf(f x HH[]f(f(f1ҾH=: 1$$!ff.USHHf.f(->)l$0f.f(ff(f.Ef.Etf.DȄXf/ûwuf(f(HL$0LD$,$f($umD$,wH ,tnL$8T$0HHf([]fWH yfD HH[]f(f(Ð1ҾH= 1$F$ufW l$0L$8f(l$L$\$荇\$$f($$l$L$f(HHYf([]YYY\Xf(D 8 X 11H=7 $f(-^u )l$0@AVfD(fEAUATUHSHD$ t fD/L$ gfA(^Ʒ fD.QD$D~ AfE(DL$fDAFfDD$ *DXt$DXY IA,f*fA.zfA/t fE/CfE.f(=f)$)$@ fE/ DD$(AfD/L$({ (fA(fATf/ T$(AXf/ (1l$(H$H$DL$Pf/fD\$HDd$@DD$0f.&@G,Չ$AAD)D)*\Y D$$DD$0Dd$@D\$pD\$H~ DL$P$Ѓ)ЃzfAWf(fD(AYAXf.#H%=&H$T$(fA(5&%x'&fHnDL$PD\$HDd$@DD$0zDD$0Dd$@D\$HAD~' DL$Pj D) $$DL$`D$f(f(Dd$PfATfATDD$H\$@T$0  &% D~ T$0f/\$@DD$HDd$PDL$`D$r6 H$YfHnY$t$pf(f(YYYY\f(Xf.YYf)$E11ҾDL$PH=Ը D\$HDd$@DD$0$DD$0Dd$@D\$HD~ DL$Pf.D$(fA(fA(Dd$PDD$HD\$@DL$0诂Dd$PD~? $f(DD$H$D\$@fY$DL$0)$A|$(% fA(f(f(fATf.v3H,f fUH*f(fT\f(fVt$(f. f/ jwfA(Yf(fATf.F YNwL$(\,Kf($fW- >f.fE.fA(fA(fA(%ֱ fATf.v5I,ffAUհ H*f(AfT\f(fVfE/~ vfA.E„t fDWfWfE/'fE.qkfE. fE/ l$AYD0 XD$fAWY ^fA*^Y\$\$DX)f(fATf(_|$fA(fATY|$f/w.fA. C f.rAA'@L$\$fATfATDxY !)DYXAXEHfA([]A\A]A^ÐfD. fD/ * fA(AYf(fATf.}XfD.fD/AfA(fA(fATf/+fATkfE/fA(AfWt$(A^f(YX% fD. Q= ^f(Y{ D\$pD$^)\$`D$T$Pd$HDD$@|$0X6 ^f( ! DD$@d$H|$0AYT$PD$Xf(D$f(\$`D\$p^fD. QD$0fA()\$pYDd$`D$D$$T$PDD$Hd$@YD$0$DD$Hd$@D$T$PfA(f(\$pDd$`D$AXD$0 Y^fD. Q$D$(D\$pD$Y)\$`D$|$PT$HDD$@bT$HH5 DD$@|$PD$(H fHnfHnD-D\$pf(\$`fA(D$D~Y D$Df(zAYX9YzXA9YzXA 9YzXA09Yz XA@9Yz XAP9YzXA`9YzXAp9YzX9}qYzX9}^YzX9}KYzX9}8YzX9}%YzX9}YXfDt(Yƒ~Yƒ~Yƒ~ Yƒ uY@tY^Xf(@tfWfATXfD/HAY 9QfA(oDL$P1ҾDŽ$D\$HDd$@DD$0H=F 1DD$0Dd$@D~- D\$HDL$Pf(5G)$$A$f.{LfDfA(fA(DL$@Dd$0D\$(\>DL$@D~ Dd$0D\$(f(|$t fA*XD$Y^U AY^YD$=DfA(fW=S A|$(*fDŽ$DL$PD\$HDd$@DD$01ҾDl$~ Y- D%nf(fATYf/ AYf/tYl$0L$@A/fA*YYl$,@fA(1H$DL$HD\$@)\$0Dd$(f$DL$HA*D\$@D~! f(\$0Dd$(YYl$D1ҾH=1DL$@D\$0Dd$(&-Χ Dd$(D~ D\$0DL$@H,f- fUH*f(fT\fVf(KA`fA(DL$`D$)\$PDd$Hl$0xT$(YRY$L$@l$0Dd$Hf(\$PDL$`D~ D$YfA*YXYYl$zfL~AfD(HD$(DL$P1ҾDŽ$D\$HDd$@DD$0"D%k H< Hf(|$pfW$fW|$p`1ҾH=1D$D\$p)\$`D$L$Pl$HDD$@>D\$pD$D~ԧ f(\$`D$L$Pl$HDD$@11ҾDd$pH=)$D$D$T$`$L$Pl$HDD$@HT$`$Dd$pfLnL$PD$AYl$HD$D~ DD$@f($f/>ol$1ҾH=L 1DL$HD\$@)\$0Dd$(l$Y- Dd$(f(\$0D~u D\$@DL$H1ҾH=gL 1DL$HD\$@)\$0Dd$(l$Y- mEH,f% fUH*f(fT\fVf(DŽ$T$(fA(L$fA(H$LDd$PDD$HD\$@DL$0DL$0D\$@DD$HDd$P$wH} 4$D$(DL$p$D\$`D$DD$Pt$@\$0rD$HD$()l$HYD$0Yl$@DL$pD\$`DD$PD~ D$\LH= DL$PD\$HDd$@DD$0DL$PD\$HDd$@DD$0$PCH k D,E&11DDL$PH= D\$HDd$@DD$0OADD$0Dd$@D~ D\$HDL$PAADL$D\$DL$D\$D$ fA(t fA(D\$PDd$HDD$@DL$0D\$PDd$HDD$@DL$0fD(|D$D$)\$pDd$`$T$Pd$HDD$@?f(\$pD$D$Dd$`D$0$T$Pd$HDD$@f()\$pD$D$Dd$`$DD$Pd$H=X d$H^f(f(|$@YT$0f(\$pD$D$Dd$`f($DD$P|$@T$0h$D$pD$D\$PDd$HDD$@d$0:D\$PD$D~ Dd$HDD$@d$0zD$D$)\$pDd$`$T$Pd$HDD$@f(\$pD$D$Dd$`$$T$Pd$HDD$@ff.ATfD(USHĀf.f( $)D$`)D$pfD.fD(fһfA/.fA/$fA(DD$DL$DL$DD$f Lf/fA(Xf/ /1H|$HHt$@DL$f/fA(DD$f.fɍ@GA,ЉD$\D)Љ)*\Y#.fd$@l$HDD$d$8DL$~% l$0Ѓ)Ѓ<$fA(fWf(f(YfWf(Y\AXf.*fA/BHs=[Ld$`fA(5AL%4fHnDL$DD$DD$DL$)\$hT$`DL$(~ DD$ f(\$fTfTT$x P-` T$\$f/DD$ DL$(r Hy YfHnY|$0t$8f(f(YYYY\f(Xf.YYf)D$`YfD$\Ld$`LH=\ DL$DD$DL$DD$L$hD$`H[]A\DfDWw fA/DD$\Ld$`{f ( H[]f(A\wD$\?Dl$0fWfWfWl$0fWl$0l$8fWl$8;f~ fA(fA(%n fTf(f.v5I,ffAU-j H*f(AfT\f(fVfD.zlfD/ue -`AYf(fTf.&Y `D\A,f(d$`fW%~ )$$$L$lf.$Ld$pfA(HT$\LfA(DD$#DD$D$\wH 4\$pd$hfA(DD$ l$xH\$`\$(d$,$iDD$ D$fA(vL$\$(f(fHnYYYL$Y$\\H,f% fUH*f(fT\fVf(LH=^ D$D$D$\fDD$\H 4L$0D$8DL$ DD$l$DL$ DD$l$) f(f(DL$DD$xDL$DD$f~% ff.f(H(HxYf(- f(f.w f.% vqff.zuff(f(H(@ H H(f(f(1ҾH=Y 1%C fH(f(fDff.E„t1f.E„t#% f(Hif(`Dff(f(t$H*X ,$7,$t$D$f(f(L$fDL$DT$ff(fD(,$fA(YfA(YAY\fA(YXf.zf.zu f(f(f(fA(fA(fA(,$ff(f(ff.AUATUSHhf.f(- )l$P)l$@f(f(f.ff(f/wuLd$ LfHnfA(% ' DL$D$ D$DL$D~Ǎ )T$P\$XDL$DD$f(f(\$fATfAT$l$ ? %O \$f/DD$D~= DL$rY He Y fHnt$(|$ f(f(f(YYYY\f(Xf.YYf)D$P $f.D$LLd$PLH=4 DL$D$ʭDL$D~j D$tgD$PHp[]A\fDWW fA/DD$LLd$Pf Hp[]A\fA(fA(fA(% fATf.v5I,ffAU H*f(AfT\f(fVfD.fD/sO5S AYf(fATf.wW WOYD\A,f(D$PfW fDt[D$LfH,ffDU H*f(fT\fAVf(ofDD$L(fDD$LDHѓ 42Ld$`fA(HT$LLfA(fD$D$uwD$LwHx 4ub|$Pl$`fA(DD$|$l$WDD$$fA(Brf($YL$YD$\LH= D$D$L$(f(DL$DD$$$ DL$$$D~ DD$fA( f^ DL$D$DL$D$fD(ff.fATfD(USHĀfD.f(F  $)D$`)D$pf.fD(fһfA/^fA/$fA(DD$DL$FDL$DD$f f/2fA(Xf/ o 1H|$HHt$@DL$f/fA(DD$f.fɍ@GA,ЉD$\D)Љ)*\Yc nft$@~% DD$t$8t$HDL$t$0Ѓ)Ѓ<$fA(fWf(f(YfWf(Y\AXf.fA/rH = Ld$`fA(5 L%D t fHnDL$DD$TDD$DL$)\$hT$`DL$(~܆ DD$ f(\$fTfTT$ % T$\$f/DD$ DL$(rX H YfHnY|$0t$8f(f(f(YYYY\f(Xf.YYf)D$`u6D$\PwbH 1 4tKD$\Ld$`LH=ω DL$DD$D$\DL$DD$5L$hD$`H[]A\fDW fA/rfD$\Ld$`kf 8 H[]f(A\D$\/Dt$0fWfWfWt$0qfWt$0t$8fWt$8 f $fA(fA(DL$DD$RDL$DD$D$`f(b L$hfYD$`)D$`~` fA(fA(%& fTf(f.v5I,ffAU-" H*f(AfT\f(fVfD.zdfD/u] GAYf(fTf.Y GD\A,'f(d$`fW%6 )$$$L$f$Ld$pfA(HT$\LfA(DD$DD$D$\wH 4\$pd$hfA(DD$ l$xH\$`\$(d$,$PDD$ D$fA(6kL$\$(f(fHnYYYL$Y$\\0H,f% fUH*f(fT\fVf(LH=p D$趣D$pfDD$\XL$0f(DL$ DD$d$DL$ DD$d$ f(f(DL$DD$WDL$DD$f~%͂ 3,fD(fATUfD(S*HĀfD.zfD/tffA/%fE.f( )D$`)D$pffE(лfA/f(fA/D~'  fA(fATf/{f(AXf/h 1H|$HHt$@D)\$f/fDL$ DD$D$f.fA(@GA,҉D$\D)Љ)*\Y l$@|$HD$D~%k DD$DL$ l$0fD(\$|$8Ѓ)Ѓu f(|$0fAWfAWl$8|$0fEWffAYXfA.H = Ld$`fA(5 LfHnfA(%  D)\$DL$ DD$D$譎D$DD$DL$ fD(\$h)\$hT$`DL$(DD$f(DT$ fATfDT\$fA($$ %| \$f/DT$ DD$DL$(r} H YfHnYt$8|$0f(f(f(YYYY\f(Xf.2YYf)D$`u7D$\PwoH r 4tXfD$\Ld$`LH= DL$ DD$D$KD$\DL$ DD$D$D$`f.zUH[]A\@fDW~ fA/ojf.D$\Ld$`[fHfA(fA([]A\f1ҾH= 1苺3{ H[]A\f.D~} fA(fA({ fATfA(f.v5I,ffAU%z H*f(AfT\f(fVfD.=fD/2 @AYf(fATf.Y z@D\A,¨f(D$`fW} DfA(fA(fDD$ DL$D$JDD$ DL$D$`f( D$L$hfYD$`)D$`ft[D$\fH,ffDUy H*f(fT\fAVf( fDD$\`fDLd$pfA(fA(HT$\LfDD$ DT$D $D $DT$DD$ D$\wH@ 4l$`t$pfA(DL$0DD$(l$ t$DT$HDT$$fA(bDL$0DD$(f($YL$YD$ \@`LH=n~ DL$ DD$D$覛DL$ DD$D$8L$8f(DL$DD$ d$D$DL$DD$ d$D$fA( x fw D)\$DL$ DD$D$=fD(\$DL$ DD$D$fD(AWf(AVAUATUSHhf.f( )D$P)D$@f.f(ff(f/f.Ef.E„txf/D$<L|$i IEA$f.L OI11H=n Hth I$211H=n ŧHFh IEDSf(HHujf.ff/f. h E„f. h D„f.zsuqHg H[fHnHH$w $HHD$f(\f $T$H*Y^\f(H[ff( $" $D$f(讹T$ $~kj f(H[fWf(^\^fWfPg H[ff/f. vg E„uf. f D„uf( $ $~i D$f(fW $T$~i ^\fWf(^fWfW i f(f(觢fWoi f.f.f(UHH HxUff/Gf.e E„u&f.pf D„uf.z@u>HWf fHnH ]@1ҾH=k 1e H ]Df(H|$Ht$$D$$fWh L$^Htf(\^HH Zf ~-Jg %e Y^\f(fTf.v=9fH*ʃY^\f(f(fTf.f(H9|HGfd T$H*T$HfWg $f(AY$H ]fDf(ff.@AUf(ATIUHSHHuX,+d fYf/sf/v;f/A'v?Hc d I$HH[]A\A]Ð 릐D,Etf/wL$(T$ l$艶l$H|$<c f(f(\c Xl$Yf(\$d$Ud$\f(\$fT$ l$L$(Yf.#f/f.~5*e f(fTf.c f(fD(f(D c fTfD.v9H,ffUD5b H*fD(DfETA\fVfD(A\f.zyA,t.fWe $fDXfTe fWf(~5rd EWfD(fD(э4DYDXD D%b CL-f(ںfD(ffD.rf9t]ff**A\YA^Yf(XfTf(A_fD(f(fTfD(EYfD/wf.zufDTDD$DL$ f(d$\$t<\$d$DL$ XDYL$DXE $HH[]A\A] \$DL$ d$XfY(a Y~5c fTf(|$D f(KfSff(Hf/f.z8u6` f/Tf.B<D)f(fWc f\h` ,*~4f.ĺE„t!A` Hİ[XX YX| f/H_ = ~% b H$<$1f()d$H$L$(T$ yf(d$$f(D$xfTY,$f/#T$ L$(f(f(fTX fTf/@-P_ $$1f/Đf/v f(DpT$)$$f(fTY-f/-'f/~^ Y踱T$f($$D$lU_ =^ f(X!_ Xf(f(YfTf.t$(f"f/w f/D|_ f(f(fA/M \f(XYfA/sD^ fD/w$@X^f(XfD/f.zu1ҾH=9 1)d$0|$ T$,$2,$ ] T$|$ f(d$0\1|$ T$)$$fTf/- 1H=K ؜T$f($$f|$ f.f/5] f.? t$(f.5] - ^ f(f(fTf.v+H,ffUH*f(fT\f(fV\f.zth,\ tM',f*f.z>u<\ fW _ 1f($4$YHİ[fx\ Hİ[X\ f.f/"\ wf.~6^ f(fTf. \ w-\ f(f(fTf.v3H,f-[ fUH*f(fT\f(fV\f.z G,[ ! \ [ h[ Yf/f/R,؅f/L$0$$=)[ H$f(5[ f(|$(\XT$Yf(4$d$ Md$ \f(z4$f-a#T$|$(Yf.L$0f/[f.;~%\ f(fTf.Z wif(fD(fD(D<[ fTfD.v2H,ffDUH*fD(DfDTA\fAVfD(A\f.Y- Z fD(fD(D D%^Z DYDXڍTf(f(ffD.re9t^fED*fA(A\AYA^YfD(XfDTfA(_f(f(fTfD(EYfE/wf.zuf(DL$P)d$@DD$0|$(4$L$ T$|$(4$f(d$@DL$PX=DD$0fTT$L$ AY<$f(D$pfTYAX$f/'DHyX =~%Z H$HX <$HD$puf(fTb[ fV[ Y1H$f(/f(d$$$f(fTY4$f/s$T$ L$(u@'~fDH= 1 W %f/H xW f()d$@f(\5mW f/% |$0l$t$ $`t$ $f(f/d l$Y|$0f(d$@\X Yf(f(Y^Y\8 YX ^XfW Y H|$l)d$@|$0f(l$ T$ $H $f(d$@D qW D$PT$f(l$ |$0f(fTfD.v+H,fH*f(fT\f(fUfVf.z*,ƺf(\ƃDf/V D$lv Xf(X)d$@|$0L$ T$,$%@L$ f,$T$|$0Yf(d$@f.z)d$0|$ T$,$Y,$ T$|$ \f(d$0\L$PY;U f(fT5\X fWf(~%L Xf(f(YfTf.t$0f/y f/DL ff(f(fA/fD\f(XYfA/sDK fD/w$@X^f(XfD/f.zu1ҾH=Q 1)l$@|$(\$$$J$$ J \$|$(f(l$@\1|$(\$),$fTf/%) 1H=c \$f(,$|$(f.f$f/f.d$0f.%J !K f(f(fTf.v+H,ffUH*f(fT\f(fV\f.z,L$uWfTL fV*M YI fZBD1f(f()l$H$d$0\$( f(l$$$f(fTY$f/$\$(d$0'fDH=ګ 1e]#f/  H f()l$Pf(\H f/} |$@d$T$($bsT$($f(f/ d$Y|$@f(l$P\X :f(f(Y^ Y\ YX4 ^X\fW ?K H|$|)l$P|$@f(d$(\$ $%: $f(l$PDH D$`\$f(d$(f(f(fT|$@fD.v+H,ffUH*f(fT\f(fVf.zf,ºf(\ƒDf/TG D$|v Xf(X)l$P|$@L$(\$$$y1L$($$\$|$@Yf(l$Pf.F z)l$@|$(\$$$譙$$  \$|$(\f(l$@\L$`OfTI fWf(~-H f/vD$|fWI fA.A\ )l$`|$Pd$@X\$(Yf(\5 $\ ~ Y\5 Y\ n Y\5 Y\ ^ Y\5z Y\ N Y\5j YYL$fH~芘L$$f(\ C fHn\$(\8 d$@|$Pf(l$`Y^XfTH ?E fVH Y$|$@T$(f(l$Pf(f(d$YY^ \X Y\ YX Y\ YX ^XN)l$@|$(\$$$n$$\$|$(f(l$@f(Y^D fZA,fW tG DD ffD/ff(f( Y~-*F FfD(f(f(D fDTDSff(Hf/f.z8u6C f/Tf.B<T f(fWF f\xC ,*~4f.ĺE„t!QC Hİ[Xh YX f/HC = ~%E H$<$1f()d$H$L$(T$ \f(d$$f(D$xfTY,$f/#T$ L$(f(f(fTX fTf/@-`B $$1f/Đf/v f(DpT$)$$f(fTY- f/- f/~A YȔT$f($$D$leB =A f(X1B Xf(f(YfTf.t$(ff/ f/DB f(f(fA/M \f(XYfA/sDA fD/w$@X^f(XfD/f.zu1ҾH=I 1)d$0|$ T$,$B,$ @ T$|$ f(d$0\1|$ T$)$$fTf/-!1H=[ T$f($$f|$ f.f/E@ f.? t$(f.5@ -A f(f(fTf.v+H,ffUH*f(fT\f(fV\f.zth,? tM',f*f.z>u<? fW B 1f($D~$YHİ[f? Hİ[X? f.f/2? wf.~FA f(fTf. ? w-@ f(f(fTf.v3H,f-? fUH*f(fT\f(fV\f.z G,> !? > x> Yf/f/b ,؅f/L$0$$=9> H$f(5> f(|$(\XT$Yf(4$d$ 0d$ \f(芗4$f-qT$|$(Yf.L$0f/[f.;~%? f(fTf.> wif(fD(fD(DL> fTfD.v2H,ffDUH*fD(DfDTA\fAVfD(A\f.Y-= fD(fD(D D%n= DYDXڍTf(f(ffD.re9t^fED*fA(A\AYA^YfD(XfDTfA(_f(f(fTfD(EYfE/wf.zuf(DL$P)d$@DD$0|$(4$L$ T$|$(4$f(d$@DL$PX= DD$0fTT$L$ AY<$f(D$pfTYAX$f/'DH; = ~%= H$H; <$HD$puf(fTr> fV> Y1H$f(f(d$$$f(fTY4$f/s$T$ L$(u@'~fDH= 1z: %f/X  : f()d$@f(\5}: f/5 |$0l$t$ $`+t$ $f(f/t l$Y|$0f(d$@\X Yf(f(Y^ Y\H YX ^XfW < H|$l)d$@|$0f(l$ T$ $+ $f(d$@D : D$PT$f(l$ |$0f(fTfD.v+H,fH*f(fT\f(fUfVf.z*,ƺf(\ƃDf/9 D$lv Xf(X)d$@|$0L$ T$,$5#L$ f,$T$|$0Yf(d$@f.z)d$0|$ T$,$i,$ T$|$ \f(d$0\L$PYK8 f(fT5l; fWf(~%L: -f/vD$lfW5A; fA.A\Y )d$P|$@l$0XT$ Y $\5 Y\1 Y\- Y\) YD$f(\ Y\ Y\ Y\ Y\ YfH~f(1 $DD$f(T$ l$0fA(\ |$@f(d$PYfHn\ ^XKˉ$|$0t$ f(d$@f(fD(l$YYD^ x \X AY\ g AYX b AY\ ] AYX X ^XWf()d$0|$ T$,$,$T$|$ f(d$0f(kA,fW-99 D{6 f(fD/Y~%7 fD(f(f(D x fDTrfDf.f(SHH0Hxef.5 E„u>f.5 D„u,ff.zbu`fHug5 H0f([DfH0f([f1ҾH=I; 1t35 H0[f(fHfH*f/f(H|$(Ht$ L$KL$D$(^f(\\$ ^f(HPH5 ~-6 %5 Y^\f(fTf.vD f.fH*ƒY^\f(f(fTf.f(H9|f(L$aL$f(^fDH f^f.w*QD$X3 f(OjT$YQL$T$L$T$D$ff.Sff(Hf/&f.z8u6V3 f/|f.rl 7f(fW<6 f\3 ,*f.Et=~92  2 $XZi$Y@ YX f/H{2 = ~%4 H$<$f()d$H$L$8T$ Lf(d$$$f(fTY,$f/(T$ L$8f(f(fTXh fTf/b-1 $$1f/Ġf/v f(ĀT$)$$f(fTY- f/- f/h1 Y7T$f($$D$|1 =L1 f(X1 Xf(f(YfTf.l$8fH f/ f/D1 f(f(fA/l \f(XYfA/sD 1 fD/w$ @X^f(XfD/f.zu1ҾH= 1)d$@|$ T$4$o4$ -0 T$|$ f(d$@\1)d$ f/5 |$$1H=ϒ \o$|$ff(d$ f."f// f.c t$8f.5;0 -0 f(f(fTf.v+H,ffUH*f(fT\f(fV\f.ztt,8/ tT3,f*f.zFuD$/ f($fW &2 m$YH[. H[X0/ f.f/. wf.~0 f(fTf. / w-l/ f(f(fTf.v3H,f-i. fUH*f(fT\f(fV\f.z G,. . . - Yf/f/ ,؅f/L$@$v$=- H$f(-}- f(|$8\XT$Yf(,$d$ d$ \f(,$f5i T$|$8Yf.L$@f/sf.S~%/ f(fTf.m- wif(fD(fD(D- fTfD.v2H,ffDUH*fD(DfDTA\fAVfD(A\f.Y5, 4fD(fD(D D%, DYDXڍLfD(f(fD.rh9taff**A\YA^Yf(DXfTf(_f(fA(fTfD(EYfD/wf.zuf()d$`DL$Pl$@DD$8<$L$ T$`<$f(d$`DL$PDD$8fTl$@5k AYAXT$L$ 4$$Xf(fTY$f/$H* = ~% - H$H* <$H$bf(* fT- fV . YH$f(f(d$$$f(fTY4$f/S$T$ L$8P'ffDH= 1mi* f/  ) f()d$Pf(\-) f/ |$@t$l$ $`{|l$ $f(f/Ĩ t$Y|$@f(d$P\X B 9f(f(Y^ Y\ YX< ^XfW G, H|$|)d$P|$@f(t$ T$ $- $f(d$PD ) D$`T$f(t$ |$@f(fTfD.v+H,fH*f(fT\f(fUfVf.z ,źf(\ŃDf/`( D$|v Xf(X)d$P|$@L$ T$4$L$ f4$T$|$@Yf(d$Pf.z)d$@|$ T$4$z4$ $ T$|$ \f(d$@\L$`Y' f(fT-* fWf(~%) f/vD$|fW-* fA.A\ )d$`|$Pt$@XT$ Y $\ Y\ Y\} Y\y YD$f(\k Y\g Y\c Y\_ Y\[ YfH~f(y $DD$f(T$ t$@fA(\( |$Pf(d$`YfHn\ ^X+y$|$@l$ f(d$Pf(fD(t$YYD^ \X AY\ AYX AY\ AYX ^XWf()d$@|$ T$4$nx4$T$|$ f(d$@f(KA,fW5( D% f(fD/Y~%K' f(fD(f(D Ȟ fTVSff(Hf/&f.z8u6$ f/|f.rlt 7f(fW' f\$ ,*f.Et=~9~$  `$ $XZ$Y@p YX f/H $ =# ~%#& H$<$f()d$H$L$8T$ =f(d$$$f(fTY,$f/(T$ L$8f(f(fTX fTf/b-b# $$1f/Ġf/v f(ĀT$)$$f(fTY- f/- f/" YuT$f($$D$|d# =" f(X0# Xf(f(YfTf.l$8f f/ f/D# f(f(fA/l \f(XYfA/sD" fD/w$ @X^f(XfD/f.zu1ҾH=I 1)d$@|$ T$4$Ba4$ ! T$|$ f(d$@\1)d$ f/50 |$$1H=_ `$|$ff(d$ f."f/I! f.c t$8f.5! -" f(f(fTf.v+H,ffUH*f(fT\f(fV\f.ztt, tT3,f*f.zFuD f($fW # A_$YH[ H[X f.f/* wf.~>" f(fTf. w- f(f(fTf.v3H,f- fUH*f(fT\f(fV\f.z G,   p Yf/f/Z ,؅f/L$@$r$=1 H$f(-  f(|$8\XT$Yf(,$d$ d$ \f(x,$f5 T$|$8Yf.L$@f/sf.S~% f(fTf. wif(fD(fD(DD fTfD.v2H,ffDUH*fD(DfDTA\fAVfD(A\f.Y5 4fD(fD(D D%f DYDXڍLfD(f(fD.rh9taff**A\YA^Yf(DXfTf(_f(fA(fTfD(EYfD/wf.zuf()d$`DL$Pl$@DD$8<$L$ T$Q<$f(d$`DL$PDD$8fTl$@5 AYAXT$L$ 4$$Xf(fTY$f/$H = ~% H$H <$H$bf(H fTR fV YH$f(zf(d$$$f(fTY4$f/S$T$ L$8P'ffDH=r~ 1Z f/8  h f()d$Pf(\-] f/ |$@t$l$ $` nl$ $f(f/T t$Y|$@f(d$P\X 9f(f(Y^ Y\( YX̋ ^XfW  H|$|)d$P|$@f(t$ T$ $  $f(d$PD a D$`T$f(t$ |$@f(fTfD.v+H,fH*f(fT\f(fUfVf.z ,źf(\ŃDf/ D$|v Xf(X)d$P|$@L$ T$4$L$ f4$T$|$@Yf(d$Pf.z)d$@|$ T$4$Il4$ T$|$ \f(d$@\L$`Y+ f(fT-L fWf(~%, f/vD$|fW-! fA.A\9 )d$`|$Pt$@XT$ Y $\ Y\ Y\ Y\ YD$f(\ Y\ Y\ Y\ Y\ YfH~f(k $DD$f(T$ t$@fA(\ |$Pf(d$`YfHn\ ^X+j$|$@l$ f(d$Pf(fD(t$YYD^ X \Xd AY\ G AYX B AY\ = AYX 8 ^XWf()d$@|$ T$4$i4$T$|$ f(d$@f(KA,fW5 D[ f(fD/Y~% f(fD(f(D X fTVSf(fZfZH/.z3u1 /`.1+ @f(fWT f\ ,*f.EtM~I  f(T$XmLT$YZf. YX f/H = ~ H$|$f(f(ÿ)T$0H$d$ \$/f(T$0$f(\$d$ $fTYL$f/f(f(fTXj fTf/  $$1f/Ġf/v f(Āf(fTY f/w  f/HZ[,f*f.zNuL\ $f(fW%c T$f(RT$YZH[Dp H[X` f.|fN f/wf.J~ f(fTf. B w% f(f(fTf.v3H,f% fUH*f(fT\f(fV\f.z C,  0  fYf/f/ ,؅/l$Pd$@\$e\$= H$f(  f(|$0\X\$Yf(L$T$ T$ \f(lL$5~ \$|$0f.d$@l$PYa f/f.~& f(fTf. wif(fD(fD(D fTfD.v2H,ffDUH*fD(DfDTA\fAVfD(A\f.  Y5  fD(fD(D D- DYDXLfD(f(fD.rj9tcff**A\YA^YfD(DXfDTfA(_fA(fTf(f(AYfA/wf.zuf(f()T$`DD$PDT$@DL$0|$d$ \$6EDL$0|$f(T$`DD$PAX5 DT$@fT\$d$ AYt$$f(fTYAX$f/H  5! ~! H$H t$H$r  )T$\$Yb\$f(T$D$|= %  f(X Xf(f(YfTf.l$0 f/yN f/DS ff(f(fA/*@\f(XYfA/sDp fD/w$@X^f(XfD/f.zu1ҾH= o 1)T$@|$ \$t$N  t$\$|$ f(T$@\1)T$ f/5 |$\$1H=q M\$|$f(T$ f.f f/f.t$0f.5 % f(f(fTf.v+H,ffUH*f(fT\f(fV\f.z, jGfT fV YR fZ7Df(H$)T$f(d$0\$ f(T$$$f(fTYl$f/u$\$ d$0'fDH=o 1L f/X  f()T$Pf(\%} f/5 |$@t$d$ \$k*_d$ \$f(f/r t$Y|$@f(T$P\X f(f(Y^ Y\F YX| ^X\fW  H|$|)T$P|$@f(t$ \$L$L$f(T$PD} D$`\$f(t$ f(f(fT|$@fD.v+H,ffUH*f(fT\f(fVf.zb,ĺf(\ăDf/ D$|v Xf(X)T$P|$@L$ \$t$,L$ t$\$|$@Yf(T$Pf. z)T$@|$ \$t$^] t$\$|$ \f(T$@\L$`;fT q fWf(~Q f/vD$|fWF fA.A\ ^ )T$`|$Pt$@X\$ Yf(\-[ d$\ - Y\-I Y\  Y\-9 Y\ Y\-) Y\ Y\- YYL$fH~9\L$\ d$f(fHn\ \$ t$@Y|$Pf(T$`^XfT-  fVm Yl[\$|$@d$ f(T$Pf(f(t$YY^ m \Xy Y\ ] YX Y Y\ U YX Q ^XK)T$@|$ \$t$[t$\$|$ f(T$@f(Y  fZA,tfW5 gDa ffD/ff(f(Y~ -fD(fD(f(DQ fDTff.@fHf/st- 5Z f(f(fTf.wx,f.zCf/u=f/~W vDf(fWf/wf(H)>1ҾH=i 1YF H@H,f5 fUH*f(fT\f(fVPf/vf/f(fW wf/v3f(Hf(AT1ҾH=Hi 1Et HÿHfHf/wp-J 5 f(f(fTf.wp,f.z?f/u9f/~ vDf(fWf/wf(H1ҾH=h 1E HH,f5 fUH*f(fT\f(fVXf/vf/f(fW sf/v+HS1ҾH="h 1DD Hf(ÿHMff.fAVIAUIATIUHHH f/wf/Ku  } m HL$0HHT$ Ht$L$L$L$(L$8f$T$T$ T$0sS$ED$A$D$ AED$0AHH]A\A]A^f.HH]A\A]A^1Sff.[Vff.Sf(H HfHf.z!uOv HtfH [H{f( $>Y $HHD$f(#Yf $T$H*H [Y^\f(ff.f.F Ef. Euff.D„t_ H [Ð  f/sBf(H|$Ht$ $jX $D$^\D$^fW @(t ^f.w?Q$ 89Y$fW fDfW  f(L$XL$$SfD(fD(H HfHf.z+u)f.z#u!f(f(Ht ffA(fA(HDD$D $YHCffH*f(f(D $Yf(DD$Yf(Y\f(YXf.}fA(fA(DL$DD$VDD$DL$H{$L$fA(fA(Y\$\L$H [X~N H [fWfWf(f(DL$D$SDL$D$W@Sf(f(H H2f.ff.E„tf.DЄ / f.f.%  f(f(d$l$l$d$D$q f(f( $fVUAZ|$D$f(f(Yf(AYAY\f(YXf.p~%  fWfWf(f. H [f(fDHD$ $%YHCffH*f(fD(,$Yf(d$YY\f(AYXf.f(f(l$d$LTd$l$H{$L$f(f(X\$\L$H [` H [f(fD(  H [f~ fWfWf(fA(f(l$$$!Ql$$$ f/rx( f/rjq f/r\ f/r f/n f/W\a f/׃?@( f/ f/ f/w^c f/rq f/` f/:p f/׃f.H|$,f(lfWT  / f/s~ f/skf/ f/`` rk f/f(f(H8H|$,f($$\f((1f(f(/H8VBv f/sn f/ d$\$f/$f(HC$Y \j \$d$,1f(f($XYd$\$^l$Fd$$f(l$\$f(YX^Xr f/sAf/ r&} f/rf/%Wn rf/e f(f(H8f(f(H8镴f(\$T$$$B\C $$f(^ ^ X ` B$$T$,\$BBYR_  m \j Bd$\$,$f(d$\$$A$\$Xd$,AVfPIAUIATIUHHta~ y fWEAU~ ] fWfWUAEA$AfWfWA$AH]A\A]A^H]A\A]A^ATfIUHHf/wH]A\}D~ fWgE~ H fWEI$H]A\ff.fUHf/w ]@fW Hd HE]ff.ATfIUHHf/wH]A\D~ 0 fWE~  H fWEI$H]A\ff.fUHf/w ]L@fW ;H HE]ff.UHSHH( H$HD$f/HD$HD$w[ f/v51ҾH= 1= E*H([]f/wf/wfHL$HT$Hf/Ht$w $ED$D~ fWW D$~ ED$fWrAUfATUSH(f/ HD$wf/vH(f([]A\A]fD~%X =( f(f(fTf(f.6f. f/f(f(fTf.v3H,f5 fUH*f(fT\f(fVf.f/f( \f/%) 6D,X% Y%  D,f/H,T$CT$HHDHL$If(DQHA\$ H([]f(A\A]fH,ffUD H*f(fAT\f(fVfD\H,H?3H H= 1' fDAUfATUSH(f/f HD$wf/vH(f([]A\A]fD~%8 = f(f(fTf(f.6f. f/f(f(fTf.v3H,f5 fUH*f(fT\f(fVf.f/f( \f/% 6D,X% Y%  D,f/H,T$@T$HHDHL$If(D1H?\$ H([]f(A\A]fH,ffUD H*f(fAT\f(fVfD\H,H?3H H= 1%k fDHH1)HH)AWfI~AVfI~ATfI~USH,DH5[G HH89{?Ht Hx&fInH,HH?HH1H)H9}0HG H=V 1%[f] A\A^A_ÐfInfInĉ1[]A\A^A_fDAWfI~AVfI~ATUHSHDH5F AHH88D>H HxHH?HH1H)H9}4HF H= 1R$[f] A\A^A_DfInfInlj%1[]A\A^A_ff.Qff.[Off.UfHSHHf/H$HD$w8f( m f(f(=5 fTf.wCf.z f/uf/vi1ҾH= 1) Ek#H[]@H,f= fUH*f(fT\f(fVH,HIHD$f(f(þPLL$WZYt 1H=0 @11E "UUHSHH5T H$HD$f/w 1C H []A\A]A^fH,ffUH*fD(DfDTA\fVfD( \H,H?DH3 vff.@AVAUATUSHH % HD$f/f(z f/ff/f/~` f(fD(D & fTf(fD.fA.PfA/Ef(f(fTfD.v+H,ffUH*f(fT\f(fVf.f/f(\f/; D,X Y  D,f/H,\$,$,4,$\$HHDHL$If(D\$,$NHA2A,$HL$ID\$T$Df(f(D$(1ҾH= 1 H []A\A]A^fH,ffUH*fD(DfDTA\fVfD(@\H,H?DH vff.@UHSHHf/%$ f(f( f/ff/f/~5 f(f(D fTfD.v5H,fD H*f(fAT\f(fUfVf.z%f/uf(f(fTfD.w DYHY@HXH9AYYf(fATf/vcfD Xf(DD$T$L$DD$L$f(T$A\Y # \Y y H8XXf(fA(fDAWf(LcAVAUATUHSHD$8f)$`)$pf(T$h\$d$p$|$(L$ l$D5 HDŽ$D$Ph HQ D^ L $\$ $T$($" $f(H$PH $$fHDŽ$HDŽ$^D$Dt$H^fHn$f(fl$@)$@!\$hDt$HD$ް L$XD,fA*\fD(\$0fDTƲ fD. / fD/  D$(L$ DD$H f(d" f(fADD$Hf(f(l$8f/$ HDŽ$D$ DD$xH$8H$0$$i~% D$8$0$8fWT$`\$Ht ~%ܲ \$HT$`f($fWDD$x$Yf(Yf(Yf(f(YY\f(YXf.7fD.@ +E17 YD$0d$`l$H fd$`f.f(l$HD5 fD\$fD.|$8ff.\VD Dl |$PfA(fT fT5 fA/\$H  YYD$^f/(P fD(fD DX=1 DX- YDXAYDX- Y\f(fT Xf/M*H= D J fHnH=F fD(fHnf.fD((f(f(fA(fA(X A^XDX- DX^AYY\ح Xf(fT h YDXf/vfD^T$PDY fA.6EQEYAXD,fEE*fE(EYE(DT$fED\$HAl$HfE(fE(fA(fE(d$`fDfE(fA(fD(fD(fA(fA(EX A\T$8AXXD^t AX^YY\$ f(f(AYf(AYAY\f(AYXf.Y*\A\AA\D\% AYAYD- DXDXDXE9%ffA(fI~d$`Yl$HfI~fWҮ fA(fA(T$H$fY$$D$D$D$d$xl$Pt$` t$`fED5> $l$PD^d$xD$D$DYD$fE(fE(DYDYD\$EXfE.v6L$HffE(AYAYEYD\$XfA.5f(fA(fE(YYDY\f(YDXfA.4fA(fE(fE(AYDYEYD\fA(YDXfE.4E8/AH ffA(fA(Af(fD(AfLnfD(ffYYD\AXfA.7fDDUfEf(f(f(AYAYAY\f(AYXf.f/fE{E19 Mc)B@LHD \$PD HcHHHHLd5HfA(fA(fT |$`fTت t$HD\$@Dd$8DL$0DD$(d$ DT$Dt$pDl$hf/D$PDT$d$ DD$(DL$0Dd$8D\$@t$H|$`fA(fA(A_B@YfA(fA(Dl$hYDt$pl$PYY\Xf.].f(f(f(LHDDAYAYAY\f(AYXf..fA(fA(fA(AYfA(AYAYAY\Xf. .IF<F<LcIL9fA(fE(fA(YDYYD\fA(YXfD.$DXXfE(fA(fE(DXD$DXL$Yf(EYEYD\fA(YDXfE.P$fA(fAA$Af(f(f(fA(5@fD/D$[HDŽ$-Ǧ f/l$PDt$HTD$L$D$l$0$f(f(L$`YY$f(f(T$xl$0fT$x$Dt$HfI~$D$f.v f/l H fHn$= X|$0$$f(DD$HD$|$xG~%_ fW)$-. $f(DD$HD$$Y$^ fA/  K ; f($D\$D$AYXfT fD/D  fA(AYDYAXfDT fE/D AYDYAXfDTS fE/D AYDYAXfDT' fE/waD AYDYAXfDT fE/w9D AYDYAXfDTץ fE/wAYY [ XfWf(fInD$D$XY$Y m $Y$DYYL$`AXXf(YYd$HD$`f($$f( f(^f(YfY$ߢ $^E%Ң t$P\$fD(fD(D$  f/t$t$ l$8f(f(YYY\f(Xf.*D= t$PHH l$HD$AYAYfLnfHnDYD$(fHnL$@fDYL$fD(t$`D|$D$fDd$fA(Y\$0f(D5 YT$(D^\XAXAXAXAXD^AYfD(DYD^\$@AYD^D^fA(YDYD\f(YDXfE.^^ &fA(fA(fA(YYY\fA(YXf.!DYt$XD$`XL$HD$`f(XXʠ L$HEYX= fD/l$XD$HfD$`EAD$8L$ |$Hl$`f(f(f(YYYY\f(Xf.*fE1EHD[]A\A]A^A_Dd$0f(Y$@D$8L$ DD$Hf( f(fADD$Hf(f(dt$8f/$+AGfD- Xl$0f(AHi E1l$xfLnf(\$xDD$DYY\$fD(˃iEAA@AfEff(fE(fA(AYfD(EYAYEYD\DXfE.fA(fA(fT   |$PfT t$`Dt$HDT$8DL$0DD$(D\$ d$Dl$pDd$hrf/D$@d$D\$ DD$(DL$0DT$8Dt$Ht$`|$Pff(f(f(B@f(Dd$hDl$pEwAYd$@AYAYAY\Xf.f(f(f(LHDDAYAYAY\f(AYXf.fA(fA(fA(AYfA(AYAYAY\Xf."IAF<F<McE9tyf(f(f(AYAYAY\f(AYXf.|Xf(DXD$XDXL$fD(AAf(f(f(fA(E9uEgIcHDDif(f(f(AYAYAY\f(AYXf.%fEfDf(f(D$D$$T$xd$0Y% fI~L$`f(d$H(t$0L$`fIn=Ǜ d$H^T$x$D$D$^$^YL$`f$D$ ^D$8l$xDt$`t$HfTK t$HDt$`l$x$fD(XfEf(f(f(AYAYAY\f(AYXf.)fEE1f.AEAfD(fD(f(EYf(EYAfD(fD(EYEY@Hf(5F Xt$0AH3 At$xfLnf(d$0f(\f(X^Ft ffInfIn$D$D$DD$xDL$Pt$`D|$H9DD$xD- DL$Pt$`D^fD|$HD$D$AY$fA(fE(AYEY\fAYDXfD.)ffA(fE(~%# YfWYDY\EXfD.H)fA(f(f(AYYAY\f(AYXf.( XD$0fWDT$`\$ D\$H\T$8s DT$`D\$Hf(Xf(AYAYf(f(AYAY\Xf.(%# Xd$0fA(AH Ad$xfLnfA(f/t$l$ |$8f(f(YYY\f(Xf.$l$P|$`D$0 t$HH{ D$D$YYHD$PY$fHn$fYfD(fHn$f.fE(fA(\$0f( D5 Y\YD^AXAXAXAX^f($XAY^DYDY ^$AYfD(fD(DYEY^DYDYf(AYD\f(YDXfE.fA(fA(fA(YYY\fA(YXf.XD$HfE(XL$`D$Hf(YL$`fA(D\f(YfA(fA(AYAY\f(AY\f(AYXf.;X$DY$X$$T$P$f(AYXXR f/T$X-D XT$PD$ " XL$h$fT Yf/$ H l$`AA$d$H$fLnfLnfY$\fY$Xf.$#|$D|$f(fA(YYYf(fA(Y\Xf."fYD$`\fYD$HXf. "AD$8L$ $t$PDt$`d$Hl$0ud$Hl$0f(fD(fD(Dt$`DYf(f(t$P$YDYYD\DXfE. f(f(f(YYY\f(YXf./ f(f(fA(McfA(E1Af(%& Xd$0AH Ad$xfLnf(ff."Qf(f(f.$"QYD$D\$x { $$^Yf(`D\$x XL$PD$`D$fA(Y%v f(^|$PD$DY X= D$xD^fA(t$P- \$xf( $YYX$^X\$`^f(Y Y^X fDfffed$pfW% )$)$f(ud$0$NÉD$`IAE1E1H$pHD$PAHD$PLD|$8fA.HANf(T$H),0L$@\D$(l$0AEfD$8A6f/>T$HL$@f(I$f(\\$ fYf(\$xO\$xD$@f(L$H$$\T$(D$xf(L$xXL$@^D$t$HYf(Yt$HfT54 d$@fT%& $f($f(f/$D$xb$$f(T$x^T$f/1Dl$8@IID9|$`bIA A߃6EkE:Ee|$fIcHf(LtA&AnYYY\fYXf.9fAAAUT$fHcHf(LtA6A~YYY\fYXf.fAAxfEAUDD$AE*DXL$hE1EYDYL$'d$pfW%~ fEDUd$0ffu)$)$D$0$fE1E5 Xt$hD$|$D$$$YYt$ Lu AUfD$(\$YYD$(YYfD(fD(f(f(AID9f(f(f(Yf(YYY\Xf. AXAX\$xX|$Xt$T$Pf(f(d$@|$`t$Hl$8{fl$8d$@fD(\D$(A6|$`f/D$0t$HT$P\$xs7 L$pYfD/fD(fD(f(f(f(f($$t$x|$PD$l$Hd$`\L$ H$8H$0D$@f(jDL$@$8L$0fA(\D$(d$8|fIn^D$YYD$8fD(fI~fDT D$8fT D$$f(fA(%l$Hf/$d$`|$PD$@$t$x$wvD$l$`$d$HfA(!DL$@D^L$d$HfD/l$`|$P$t$x$D$-fInAEfD$8AA9tDfD(fD(f(Ef(-fAfD$@EAfDA1ffDHHHD A9wAE)DD$d$HAA$l$`$H AYAYAYHD$@AY%f.l$Hl$pfW-܌ A|$xAL$8f(t$Pd$`DL$@DD$8l$0)DD$8DŽ$DL$@l$H$d$`t$P|$xKD$d$(Y\f(Yf(Yd$(f(f(YAE9fA(fA(fA(YfA(YYY\Xf. XX|$xDXD$DXL$t$Pf(f(T$@DD$`DL$H\$8>\$8T$@f(\D$(DL$Hf/D$0DD$`t$P|$xs6& l$pYf/f(f(f(f(Df(f(D$D$T$P\$`$$d$xK\L$ H$0LD$Hf( l$H\l$($8$0f(d$8L$@L$@|$8^D$Yf(Y$fT=I t$HfT5; f(|$@f(t$8DT$8f/$L$@\$`T$Pd$xD$D$$$D$PfA($$D$DD$xT$`d$@\$8l$P^l$\$8f/d$@T$`$DD$xD$$D$HD)f$HH)`AD$9$f(f(D$D)f(f(AAfD(fD(A{fut$pfW5 t$0f\$`)$)$D$0$ McE1D9YAE1EfAO1@HHHD 9wOffeAFAHH`hE9$Dt$A$t$@t$HAd$pfW% fud$00|$ffI~fD(fD($f(f(fD(fI~=m $|$Hf(Dt$t$H$AE1fErDkAEofEAfu!H fHnPD9tHAZZ D9mff.z.u,f.z&fH~fH~HEfH~fHnfH~HEfHnf(f(IcHfADAt$`|$AEf*YYt$ |$8t$@{AEIlHM$1H)D$L$ f(fd$f(f(YY\t$0Xl$(t$,$ʫt$,$f(f(fTfTfUfUAD$AL$fVfVf(f(f(YYY\f(Yt$X,$Tt$,$ff(fTf(fTfUfUfVX\$@fVXT$8f.Ef.d$EÄt T$Xf(H]X f$$IfHn^$$\%9X fAD$I9HĈ[]A\A]A^A_L$$t$@d$8\$0T$(tt$@d$8\$0T$(8f(f(fA(ʃDd$xD\$p|$hDD$PDt$Ht$@Dl$8DL$l$$$|$hD9DD$Pf(f($$t$@XAXl$DL$\58W Dl$8Dt$HD\$pDd$xNfA(fA(fl$x|$pDD$hDt$Pt$HDl$@DL$8d$Dd$D$El$x|$pDD$hDt$PfD(t$HDl$@DL$8d$Dd$D$l$@T$8\$賬l$@T$8\$5l$hT$H\$@L$8l$hT$H\$@L$8T$0\$(QT$0\$(D$Pf(fDAWf(IAVAUATUfH~SHcH8$f)$)$ f(lj|$tHT$x$T$\$ $ff.zquo|$fAf.z u HBU I~.H|$xSfHHGHT fHH9uE1H8D[]A\A]A^A_@f/P =T 5T Y$f/ Y$|$`t$hH$HD$HDŽ$D$`L$hE1HfHnDdT HHD$xDl$pfW=fW HD$@DŽ$$$$DT$8@CffA*X|$$$Yf(AXf/ f/,ff(*\f/r d% D fD/D\fD(fA(5 i EXA^Yf/ffD. A,fA(҅~1ff*XY9ufA(d$XL$P\$H|$0DD$($跥$D$f(蟥l$HR f(DD$(\$Hf(fLn|$0L$PA\d$XAY\ \YlR XX؃|$t\u \$f/$D$p4$fHt$@f/F HHl$@ D$p|$ff.~VU HD$xDkHL$xSfHHAHT HH9uf(f(YYYf(f(\Xf.D$$ $L$$DHD$xfAJ@H)Q fHnD G ffD/hfA(fD(fE5) ^ Yf/HP YfD(DYHHXH9>AYYf(fT-R f/v$fWwS f/ |$f(fA(^|$ L$($Y$迩t$ |$L$(fD(t$8DY$DŽ$Y$L$H$L$(LDd$Af(D$ Y$L$($Dd$D$EYDNHqO ^fLnDY$D$AH$Hl$@LD$f.DfD$ $$)*X|$f(AXYf/fA(fA(fEfE(fA(fA(AYAY\Xf. Hf(HfA)Ef(fTP f(|$XfT P Dl$Pf(Dd$Hd$0l$($$HBN f/$l$(d$0$Dd$H|$XfLnDl$Pwq$$f(HM $^T$ f/l$(d$0Dd$H|$XfLnDl$PvH$Ot$8ffYYf(YY\f(Xf.fEA9\$hT$`ff(Dl$0Dd$(@Dl$0Dd$(f(f(f(HM AYAYfLnAY\f(AYXf..fD(fD(HHA9$Dl$p$fL f$$X*$$胡HdL $$$f(f(fLn$HcÍUHHD$x99DX(IDt+DHD@Dd$fA(f(f(XfA(fD(YYYYDY\fA(YAXf.VA\fA(DXDXXfA(fAAD$f(YYf(fD(AYf(AYEY\f(AYAXf.dXDXɉD)A\I f(fAA$9$HcD$DD$HH\$x'ff[fŃHA\fXA9fA(f(D KXYYf(fD(AYf(YDY\f(AYAXf.{fA(|$t$DD$$$ל|$HBJ t$DD$f($$fLn:f.fEfE(D mJ HfJ D$fA(fE(DXfHn\$fA(fA(AY^f(YAY\fA(YXf.Y$$f(AXDX I YYYl$DXfD(DXf/rfA(fA(AYAYaff(d$H\$0|$(L$ߛHI L$f(f(J \$0fLn|$(d$HA\\YH YXXMff(L$(|$K$|$L$(fD(H HDl$pASAKD$Ld$xD$0D$L$@D$D$ AoD$(Hc(fHDfE()fE(A9fD(fD(\$T$0fA(fA(fA(XYY\$@YYY\fA(YXf.KAXAX|$8ff(YYY\fYXf.|A\f(HHfDL$(AD\$ t$l$$$譥$$f/$HG l$t$D\$ DL$(fLn$t$0|$@s\$fA(fA(D$D$D$D$$DL$Xd$P|$Hl$0Dt$(Ҙd$PY$$l$0|$DL$XH%F YD$D$YfLn$Dt$(D$YD$AXDX 6F DXfD(DXf/|$HQfA(fA(f(HE f(fLnT$8ff(f(|$HDl$0Dd$(ߗHPE |$HDl$0Dd$(fLnfA(fA(fA(|$HfA(Dd$0Dl$(荗HD |$HDd$0Dl$(f(f(fLnT$8f(f(fDL$(d$ D\$t$,$*d$ HD DL$(D\$t$,$fLnT$`f(f(f($L$fA(fA(Dd$(Dl$ d$DL$D$蟖HD Dd$(Dl$ d$f(f(DL$D$fLnKfA(fA(|$@t$8Dd$0DL$(l$ d$D\$D$#HC |$@t$8Dd$0DL$(l$ fLnd$D\$D$fA(f(|$@t$8Dd$0DD$(d$ D\$DL$,$螕|$@H C t$8Dd$0d$ DD$(fLnD\$DL$,$%f.AWfD(f(AVfE(AAUfI~ATAUHSHfW=E fDWE D$@f)$)$fA(|$(DD$ L$0T$\$8d$t$Ѡf/B DD$ |$(v>f(AFf Y*Dl$AXX A Yf/l$fA(H\$T$f(DfInDD$(|$ DD$(|$ l$fInf(\$T$H$fA(AŅ%NE Ex%IE d$ bD$0L$L$LL聖d$ f$$f(t$8Yf(YYf(\f(Yf(l$(Xf.L$ CD$fLLD,A*\YDD$D$AAA)AufDWsC fDW jC $]D$D]VfA( ^D$D$f(DT$pDL$h|$`DD$XD\$H\$xy\$xD\$HD$Pf(fA(\$Rt$8|$`\$T$Pf(f.DD$XD\$HDL$hDT$pEfD.Etf.DȄ f(f(D\$P|$H\$@DD$0DT$DL$%f/D$DL$DT$DD$0\$@|$HD\$PwfAfD(f(fD(t$ d$(f(f(YAYYAY\Xf.fA(fA(fA(AYfA(YAYY\Xf.XXfEHĸD[]A\A]A^A_\$8f/\$fA(Hf(fA(DDD$(|$ RDD$(|$ Hu5AfL$L$|$8|$(tAKt$fA(Hd$f(fInDfA(DD$(|$ '||$ DD$(`DD$Pf(D\$`\$XDT$HDL$|$pDD$hُl$@t$f(fW5@ DL$f(DT$Hd$PX\$XD\$`Xf/|$pDD$hD\$xd$Xf(fA(DT$PDL$H\$`\$0l$@XXXXD$L$DD$|$d$X\$`f(DL$HDT$PD\$xDT$8f(fD(L$ D$(fA(|$0DD$DT$DL$[|$0DD$DT$DL$f(f(fA(fA(fA(d$f(l$d$l$f( f(fd$Hd$HD$(L$ AVAUATUSHHHDŽ$HDŽ$D$L$v%ff(HĠ[]A\A]A^FwAI_=: fA*fD(f/= f/|$87f(fA(A^AYf/z|$t$f(f(YYYf(\Xf. |$t$f(f(YYYY\fI~f(XfInf.f( AYfD(D: A: D5: H9 D\$@EXXfD(D% D\HD$fLnfHnHD$0DXfI~D\DY9: \Y%] DYfHnDXD\fd$ fD(d$(fE(E]5DX5' DX% fE(f(fD(f(fInfA(A^A^f(Yf(f(AYY\f(AYXf. \$0T$(XX\$0fA(T$(A^fInA^f(f(YAYfD(EYD\f(YXfA. fInEXEXd$A^AXfE(E]d$d$ Xd$ YD$8AYf/D\$@A|$l$d$t$ f(f(YYYYf(\Xf.  ٧ %٧ D$0YYYYL$(\\D$L$ ]D$L$K|$t$f(f(f(YYYYf(\Xf.  YYx|$l$ f(f(f(YYYY\Xf. f(Dd$ D$_D\$fD/ d$ f(gfD/ vD$L$t$ d$Q|$t$fD(fD(d$f(f(AYAYAYAY\f(Xt$ f. ff/|$ X%5 ^%6 f(YYf(|$f.zu f/l$-ff/f/|$>- f/Y5 f(fWr8 % \f/D6 A%] m H$DL$(DD$ DT$蔂DL$(DD$ A$DT$-+ $YY$EtAbf(f(f(AYAYAY\f(AYXf.f(f(fA(fA(iAf/ v| T$v YYL$fW 47 \A$DH3 f|$ HD$HD$0|$(f. 3  fV6  f/Y5- - \f/fA$f(]@~ `6 d$|$ fD/\$8-} fWfWYY|$T$f(f(YYYf(\Xf.|$(\$0f(f(YYYY\f(Xf.  2 YYYYXXf(f(̓wD$L$d$ l$Y|$l$f(d$ f(f(YYYYf(l$\Xf.  d$l$YYnd$l$f(f(f(Yf(YY\f(YXf.f(f(f(f(ff/ |$l$f(f(YYYf(\Xf.d,1  | fYYYY\h Xl$f.HBf5. H0 E1- fLnt$8f(ff/|$5ߢ H$Ң DL$(DD$ FDT$DT$DD$ DL$(A$lAYAYALf(f(f(AYAYAY\f(AYXf.>A^A^С ft#fA$f(fA$f(H/ E1fLnG@5 At$8fD(f(fD~`2 \$f(f(t$fWYfWYf(\f(Yf(YXf.f(f(y@~1 \$f(f(t$fWYfWYf(f(Y\f(YXf.f(f(DT$ DT$xf- Hc. E1l$8fLn-} d$8}H;. -k E1fLnfA(D\$xD$$Dd$pDt$h|$`Dl$XDD$PDL$HaD\$xD$$|$`f(f(Dd$pDt$hDl$XDD$PDL$HfA(f(D$D$Dt$x|$pDl$hDD$`DL$Xt$Pl$HDt$xD$D$|$pfD(Dl$hDD$`DL$Xt$Pl$HL$D$fA(fA(t$0d$(DL$ DD$@t$0d$(DL$ DD$T$f(f(l$(D\$ f(d$~l$(D\$ d$f(f(L$D$l$(D\$ d$~l$(D\$ d$fI~f(f(D$L$}~d$ l$f(T$f(f(f(Q~f(|f(f(fA(DT$fA(*~DT$T$0\$(f(d$ l$}d$ l$f(f(f(T$d$ f(l$f(}d$ l$f(Cf(D$L$}f(L$D$f(f(u}f(f(Gf(D$L$ S}f( f.AVfI~ATIUHSHH87_D$ L$(f(f($t$\$MD$Et$f\$T$f(f.Ef.Etf.DȄu;f(f(1f/$wfEA$H8[]A\A^fD$f(||$ 3fInf(fKf~, d$fWfW\Xf/rRf(~d$(|$ \\\\f(fA$d$f(!@f(f.DAWf(1AVAUIATIUH͹SLHh-( |$XH$L$^\$f(fT* Y H|$(L$HH$LL$8H|$0HH$H|$ Hf/ӹ<LHLH,$rf(fTR* f/4$f(f( f(|$Yf(YYT$`\$Hl$P"T$`\$Hf(Yf(f(YY$=' ^f(XY\f.|$@|$^)D' ff.D\ff(fA(\$x$T$pd$hDD$HL$ׅDD$HL$D$`fA(*Dd$`DD$HD$ d$hfD(T$p\$x$fA/cDl$H& fE/H$H$ f- D% D fD(fD(f(fA(fA(AYAYY\fA(AYXf.u&$fD(f(EYAYf(YYfd$AMf(AYYAYD\f(AY#{XfA.% YAYX% f(f(fD(YYDY\f(YAXf.#|$@f|$XEYYfA,$f($f( ff($f$f$fYfYf(ff(XfXf(XXЃ f($f( ; f($f$f$fYfYf(fXXff(XX܃ f($f( f($f$f$fYfYf(fXXff(XX܃" f($f( f($f$f$fYfYf(fXXff(XX܃ f($f( T f($f$f$fYfYf(fXXff(XX܃h f($ f(  f($0f$(f$0fYfYf(fXXff(XX܃ f($@f( f($Pf$Hf$PfYfYf(fXXff(XX܃ f($`f( m f($pf$hf$pfYfYf(fXXff(XX܃Q f($f( f($f$f$fYfYf(fXXff(XX܃ f($f( ӈ f($f$f$fYfYf(fXXff(XX܃ f($f( f($f$f$fYfYf(fXXff(XX܃ :f($f( 9 f($f$f$fYfYf(fXXff(XX܃ f($f( f($f$f$fYfYf(fXXff(XX܃ f($ f( f($0f$(f$0fYfYf(fXXff(XX܃#f($@f( R f($Pf$Hf$PfYfYf(fXXff(XXf.fW%" f(VH HEXE~# I@A8Hh[]A\A]A^A_fp XD$|$pd$hDD$`L$HdtsffDL$Hf/DD$`d$hf(|$pf/ g .HZ fHnff/Yf(\T$9 YT$Hf(A\Yf(YfI~f(YX\f. l$ffAYUfA(Yf(Y\fYXf.ffInDL$pD$Hd$hDD$`||$HfDD$`d$hDL$pf(f/fInu f/rf.f/+ H܏ f($D$fHnDL$pT$htT$hH$H$D$` Yr\$`f$fInYY$_f($f(YYfAED$H3rDL$pT$L$xfA(DL$`D$p rXXv|$@|$XYYfA$6DL$`T$f$fA(qT$HfInD$$$fqHs $f(D$H D$L$Xf(Yf(fA(YfHnfl$`t$h1q |$f(f(f(D$YDT$xYfA(f(X} YYY\fA(YX|$pf.of(XD$`H\$8fA(fXL$hH$$)$f(l$xffDl$pfD$@fWX Sp|$f/<$H) Dl$p$f($l$x$HH$f(f( HYYYY\f(Xf.XH$ffHfD fHnfHnfD(L$pH=h HHzf(f(f(fA(fA(؉YYY\f(YXf.VAYHf(HfA)  f(YfD/AtYDXDXnfA(fA(ˉ$DD$xd$p|$hDL$`DT$HD\$0sfD(fD(XXDd$(Dl$ ssDl$ Dd$(|$hd$pf(f(D\$0DT$HDL$`DD$x$fȃt3H5,h HHYYXXHD$8f|$f/|$PH$f(,$Yl$@f XYYVDff(xf(ZH$Hl$ H=s fE(H$Dd$XAD$@E1LWD\$HDt$% Lv L Fw DT$XMwMIwAUKfDHL$f(I DfA(f(f(fD(YYDY\f(YDXfD.AT$IXI9u\$fA(D$f(AYIcf(AYAY\fA(AYfD(DXfA.pfA(f(fA(AYYY\f(AYXf.HL$ Lfd$HH)CHL$(LHfD(EYf(AYAYAYffA() AYfA(AYD\XfD.zRCfA(IIHL$0YYf)I9)IcfE(fD($fD(fE(DT$HfA(fA(fA(H$ID$HD$xD$$$$D$DT$p?hHt$0L u HD$xfD(CLq IfA(IzDT$pD$YL=t D$$$Y$D$f)H$I9f$$Yd$PfD(у|$@$$AM ADu(d$`\$hE fD(AYf(DYAYYfD(D\DXfE.U]D$DX]0f(f(fD($AYDXe8YDY\f(AYAXf.dU]fE(DXD$DX$fD(f(f(YEYYD\f(AYXfA.EXAXA U]D$$fD(f(fD(YEYDYD\f(AYAXfA.EXXAU]D$$fD(f(fD(YEYEYD\f(YAXfD.`EXXAMD$U$]fE(DYf(fD(YDYD\fA(YAXfD.EXXAD$ U$(]fE(fD(DYf(YDYD\fA(YAXfD.EXXAyD$0U$8]fE(DYf(fD(YDYD\fA(YAXfD.EXXAD$@U$H]fE(DYf(fD(YDYD\fA(YAXfD.4EXXAD$PU$X]fE(DYf(fD(YDYD\fA(YAXfD.EXXA ;D$`U$h]fE(DYf(fD(YDYD\fA(YAXfD.&EXXA pxD$p$xfE(f(fD(YDYDYD\fA(YAXfD.h%EXXA te`hD$$fD(f(fD(YEYEYD\f(YAXfA.$EXXH$\$f/$DXX`D`v!fDTz fT%r DXfA/E1IH HMcfE(fE(B$fE(fD(6@D$U$]fA(fE(De D](Yf(YDY\f(YAXf.>"fE(U]E$DXDX$fD(f(fD(DYYDYA\fD(DYEXfA. AXEXA+D$U$]fE(DYf(fD(YDYD\fA(YAXfD.AXDXAD$ U$(]fE(DYf(fD(YDYD\fA(YAXfD./AXDXAUD$0U$8]fE(DYf(fD(YDYD\fA(YAXfD.AXDXAD$@U$H]fE(DYf(fD(YDYD\fA(YAXfD.wAXDXAD$PU$X]fE(DYf(fD(YDYD\fA(YAXfD.AXDXAD$`U$h]fE(DYf(fD(YDYD\fA(YAXfD.AXDXAD$pU$x]fE(DYf(fD(YDYD\fA(YAXfD.cAXDXA >D$U$]fE(DYf(fD(YDYD\fA(YAXfD.AXDXA pxD$$fE(f(fD(YDYDYD\fA(YAXfD.AXDXA tf`hD$$fD(f(fD(YEYEYD\f(YAXfA.HAXDXHD$8\$f/$X DXX DXfT% fDT AXf/AD$@AEuAIH H[HD$8 $$Xf(H$f( hYYYY\f(Xf.<H$fH HHcE1fT fT f(At$PHL$8E1LX f(H=^ XfHnY^YAuCAHD$8 fXH$f8fY)<$(@fEL1fA(ؐD fA/$DYYBAXDXw HHH9uYff/DYA@EfAfXAu;@LAAIHA"fEL1fA(@AD fA/$DYYBAXDXw HHH9uYfE1DYf/fAfXgSAD\$@E1YfDL$xfIn^D$H\$pd$hDD$`]ff/l$HDD$`d$h\$pf(DL$x fA(fA(DD$xd$p|$hDL$`DT$HD\$0`fD(fD(XXDd$(Dl$ `Dl$ Dd$(|$hd$pf(f(D\$0DT$HDL$`DD$x@DL$xD$pfIn^D$Hd$hDD$`\DD$`d$h\$pDL$xf(X YfҸf(f(f(H$I$D$$D$D$D$D$D$D$t$xl$pWA$I9L` l$pt$xfD(Lc XЋ$D$IzD$D$L Gd $D$D$H$D$D$DD$fA($fA(fA(DL$xH$D$$$D$D$D$Dl$pVH=_ H$$$f(D$fD($D$L Hc LWDL$xDl$pLb D$D$fA(f(f(܉$L$HD$pD$D$|$xDd$hDT$`t$HD\$0d$(DD$ U|$xHD$pH=dQ f(t$H$f(L$Dd$hD$DT$`D$D\$0d$(DD$ fA(f(f(H$fA(DD$xD$$$D$D$D$D$|$pUH=] H$$$|$pL a LWD$D$La D$DD$xD$D$"f(f(ĉL$t$(l$ tTt$(l$ L$GfA(Dd$xH$$$D$D$D$D$D$|$pSL\ |$pDd$xD$f(D$L` D$IzD$L z` H$D$$$\$hT$`fA(H$$$D$D$D$DL$x|$p&SH=[ $$D$|$pfD(fD(H$DL$xL _ LWD$L_ D$f(fA(͉L$fA(t$Hl$0|$(d$ Rt$HL$l$0|$(fD(f(d$ fA(fA(f(܉L$ fA(DL$p|$ht$`l$HDd$0Dl$(RDL$pL$ f(|$ht$`f(l$HDd$0Dl$($f($Qf(D$fA($$D$|$xDl$pQ|$x$$Dl$pD$*fA(ff(d$pf(DD$hDL$`0Qd$pDD$hDL$`6f(f(fDL$xd$pDD$h|$`PDL$xd$pf(|$`f(DD$hf(f(|$`T$P|$`\$HT$f(nfA(DL$xH$$$D$$D$D$D$|$p/PH=Y $$fD(DL$xD$f(H$|$pL \ LW$D$L\ D$D$6fA(DL$xH$$$D$$D$D$D$|$pNOH='X $$fD(DL$xD$f(H$|$pL [ LW$D$L0[ D$D$fA(DL$xH$$$D$$D$D$D$|$pmNH=FW $$fD(DL$xD$f(H$|$pL Z LW$D$LOZ D$D$fA(DL$xH$$$D$$D$D$D$|$pMH=eV $$fD(DL$xD$f(H$|$pL Z LW$D$LnY D$D$UfA(DL$xH$$$D$$D$D$D$|$pLH=U $$fD(DL$xD$f(H$|$pL 3Y LW$D$LX D$D$ fA(DL$xH$$$D$$D$D$D$|$pKH=T $$fD(DL$xD$f(H$|$pL RX LW$D$LW D$D$fA(DL$xH$$$D$$D$D$D$|$pJH=S $$fD(DL$xD$f(H$|$pL qW LW$D$LV D$D$ufA(DL$xH$$$D$D$D$D$D$|$pJH=R $$H$|$pfD(f(D$LWD$L V DL$xLU D$D$D$'$f(f($hIfA(DL$xD$H$$$D$$D$D$D$|$pHH=Q $$fD(D$D$f(H$|$pL U LW$D$LT D$DL$xD$fA(DL$xD$H$$$D$$D$D$D$|$pHH=P $$fD(D$D$f(H$|$pL T LW$D$LS D$DL$xD$jfA(DL$xD$H$$$D$$D$D$D$|$pGH=O $$fD(D$D$f(H$|$pL S LW$D$LR D$DL$xD$fA(DL$xD$H$$$D$$D$D$D$|$p&FH=N $$fD(D$D$f(H$|$pL R LW$D$LR D$DL$xD$fA(DL$xD$H$$$D$$D$D$D$|$p5EH=N $$fD(D$D$f(H$|$pL Q LW$D$LQ D$DL$xD$PfA(DL$xD$H$$$D$$D$D$D$|$pDDH=M $$fD(D$D$f(H$|$pL P LW$D$L%P D$DL$xD$fA(DL$xD$H$$$D$$D$D$D$|$pSCH=,L $$fD(D$D$f(H$|$pL O LW$D$L4O D$DL$xD$fA(DL$xD$H$$$D$$D$D$D$|$pbBH=;K $$fD(D$D$f(H$|$pL N LW$D$LCN D$DL$xD$LG |$pDL$xf(IzD$D$D$H$f(LJ D$L K D$D$$$fA(DL$xH$$$D$$D$D$D$|$p=H=F $$fD(DL$xD$f(H$|$pL ?J LW$D$LI D$D$fA(DL$xH$$$D$$D$D$D$|$p\$XfHnH ffɻA$fHn8HH|$h~ f(ff(HYf)H YIt$Ld$XD$fLnfLnиMH$IfEfD(D\XfA(fD(fD(Yf(f(f(YDCYY\f(YXf.HIIcA,X<f(f(f(YDKYY\f(YXf.HIcA,Xof(f(f(YDCYY\f(YXf.FIcA,Xf(f(f(YDKYY\f(YXf.EIcA,Xf(f(f(YDCYY\f(YXf.xDIcA,X f(f(f(YDK YY\f(YXf.[IcA,X ?f(f(f(YDC YY\f(YXf.ZIcA,X tf(f(f(YDK YY\f(YXf.YIcA,X f(f(f(YDC YY\f(YXf.AIcA,X f(f(f(YDK YY\f(YXf.b@IcAXf( a f(f(f(YȍKYY\f(YXf.+?McCXf(f(f(f(YYY\f(YXf.>HcA,XfDT$0fA(fE(AYEYfD(EYAYD\DXfE.2fA(f(f(YAYAY\fA(YXf.1DYT$$f(f)fA/vf(T$fTfTXf/ HfE(fE(fE.K/fA(fA(f(f(f(LcCXYDCYY\f(YXf.$GHcAX,̃f(f(f(YDKYY\f(YXf.sEIcA,Xf(xLH$MLd$XfLHf(f(fD($HH fHnf.+Kf(f(fD(YYDY\f(YAXf.u/HXXfAWfAWH9uH$HfH$)4A$A$`@\$XT$@\$`f$X\$8D$ t$X|$02|$ t$X$f(f(YfYY\fYX|$0f.EDD$P\D\f(T$f(fAfT)$f($f/A|$xE$f/$ N $YYL$XfD(f(Hf(f(D, YYAY\f(AYXf.Cfd$PHcH$)$H$fA(DL$X1DL$X$$fA(T$0|$5HT$0$Hd$PYYY\$f(f(ff(f()$Y$YY\f(YXf.5f(Ń$f)$D$xH$Hf(f(YHY$f(Y\f(YXf.Y4f|$xAtD$xAID9l$H$D$H$HA9"AE$\$8b fT$@/D$H$D$`L$x9f% |$@*t$8X$f($^fY$YY\fYf(Xf.3f(f(YY\f(YXf.fH~3X% fHnT$\$fH~3\$T$f( L$d$0X-`-f$l$Yd$0f(YYf(\ff(Y$0X$ f.2$fYf(YYf(fY\$@X$8f.2H' ff(f(fHn)-f$Yf(YYf(\fY$X$f.fD$$1$f(f)$Y vI  H ffHnfHnӽL=! fHnLp,HQ D$Pf(f(fA~ YHD$PIHD$H$)$fYH$HD$0f(\X$~% L$X)d$Ff(|$l$0$f(fTt$fTf(|$`f(d$X.+t$f/$l$0D$P\$XL$`t$0l$f(L/T$P^$l$f/t$0$Ffff/; f/$, $fAAt fA.vz,fA/vu$fA.vzfA/vu$D$xkf$D$xAFMDD$P\D\D$`f(d$t$P|$XL$03(d$f(t$XfTf/$|$xL$0D$t$PD$|$X_ $XH$LMLd$Xf(&HDŽ$HDŽ$HDŽ$HDŽ$$= $ x=t $ $fH$H$H$XD,H$PA*D$h\$ $Yu)D$H$$ADt$|$0Ѓ)Ѓu"~= fWt$t$0fWt$0DŽ$AE$pHcD$Hi~5 DŽ$DŽ$DŽ$DŽ$D$`H$8HH$I)t$D$Hf+$*lj$0X$D$XN H$89 9$` AHl$h $$$$$$$$"fH1f( hHXXf(f(9|$L|$ D$Xfd$P$$X\$8$@XT$@&d$Xff$@YYf(YY\Xd$Pf.,\$\$f(\$f(ffT)$f/$$fInE$f/$ C $YYL$ f(t$ $$T$XL$P/#t$ f(|$XfTf/$$L$P$T$X$$$p$h$ fEDYf(YYD\f(fYXfD.<f(fA(fA(YYY\f(YXf.=ft$XLcH$PH$X)$f(O%$$t$ t$XT$Pf(b)LT$P$HYYYd$ f(f(ff(f()$Y$YY\f(YXf.J=f($f)t$ )$f(f(f(LHfI~DYYfA($$YHH$\fA(YXf.<f(ǃ$f)$AD$$AD$$t`$D$@H$H$$L$8H$l$ a$$$l$ d$0D|$$$f(fA(YYY\fA(YXf.;XXft$fW5 f.t$t$0ffW5 AD$t$0d^f(fInf.KEDŽ$$IH$89D$H#$f(f(f(YE}YY\f(YXf.9Hc,XA;f(f(f(YAmYY\f(YXf.9McB,XAf(f(f(YE}YY\f(YXf.9Hc,XAf(f(f(YA}YY\f(YXf.z9McB,XA0f(f(f(YAmYY\f(YXf."Hc,XA f(f(f(YE} YY\f(YXf."Hc,XA f(f(f(YAm YY\f(YXf."McB,XA pf(f(f(YE} YY\f(YXf."HcXf(A jf(f(f(YAm YY\f(YXf.#McBXf(A f(f(f(YE} YY\f(YXf.e"Hc,XA f(f(f(YAmYY\f(YXf.S"McB,XAf(f(f(YYY\f(YXf.&Hc,XT$0L$PD$D$$f(fD(AYYEYYfD(D\DXfE.&fA(f(fA(YAYY\fA(YXf.&H$Lf($$Hf)0T$Y$f/T$vf(\$fTfTXf/fIIDD$0DL$Pd$XD$Amf.$D$*$f(Icf(f(EXYf(E}YY\f(YXf.)HcX,Arf(f(f(YAmYY\f(YXf.)McB,XAf(ff/f/≄$ӃcYZ9 ~=r fH~1)|$fI~ă$\$8T$@fX$8X$@$3f$f(Yf(YfYY\f(Xf.!$0$ \\f(|$f($ffT)$f/rT$T$f/fHnfIn %4T$f(|$$XfTf/ff/hf/$YHcT$HH$fHHTfDHH9uD$H$$H[]A\A]A^A_9$`tH$A9$p|$pH$GHcAH苜HHl$hH@HH$`$)hD$p$$`t$@d$8f= ^|$X|$ Yf(YY\fYf(Xf.[3f(f(YY\f(YXf.fI~P3X fIn$\$PfH~\$P$f(i L$P$Xit$Xfl$P$Yf(YYf(\ff(Y$X$f.2$f$Y$t$X$f(YYf(\ff(Y$X$f.2Hv ff(f($$fHn$$T|$ fYfD(DYYfA(\ffD(Yt$PDXfD._2D$PfA(D$@AfInfHnH ffL- fHnfEIc~% f(HLuf(DYfH|$hD$@YfE)$HR fLnfLnLMfE(IDXD\fA(fE(fD(^@f(f(f(YAOYY\f(YXf.3HcA,X<f(f(f(YAWYY\f(YXf.l4HcA,Xxf(f(f(YAOYY\f(YXf.4HcA,Xf(f(f(YAWYY\f(YXf.|5HcA,Xf(f(f(YAOYY\f(YXf.6HcA,X f(f(f(YAW YY\f(YXf.6HcA,X Hf(f(f(YAO YY\f(YXf.7HcA,X tf(f(f(YAW YY\f(YXf.7HcA,X f(f(f(YAO YY\f(YXf.HcA,X f(f(f(YAW YY\f(YXf.HcA,X f(f(f(YAOYY\f(YXf.HcA,X f(f(f(YYY\f(YXf.'(HcA,XDT$PfA(AAYfD(EYAYD\fA(AYfD(DXfE.(f(fA(f(AYYAY\fA(YXf.")DYT$ f(fAU$fA/vf(\$fTfTXf/[IKfE(fE(fE.AW?-fA(fA(f(f(f(IcAXYAOYY\f(YXf.-HcAX,փf(f(f(YAWYY\f(YXf.L.HcA,Xf(o$DŽ$f(ff/$f(ff)$fI~f(f(ՍhHcHDYf($$\$\$~5Z fWfDWd$8DT$@)DŽ$DŽ$DŽ$$09$HD$$D|$HD+$$HcH$H$$$h$|$PfDt$H$*$t$X$<$Ef(f(f(Չ$$D$D$D$D$D$D$$x$@$D$D$f(D$D$$D$D$$x$@(f(f(f(lj$f(Չ$D$D$D$D$D$D$$x$@$D$D$f(D$D$$D$D$$x$@f(f(f($`$X9$`$Xf(f(\$0$fA($h$`$X$$h$`$XfD(fD($fA(fA(f($Xf(DD$P$DL$0sDD$P$X$DL$0L$ D$f(f(5>f(f(H$h$0D$`D$XD$PD$HD$@D$8$ $H$hD$`D$Xf(D$PD$H$0D$@D$8$ $f(f(f(H$pf(D$8$0D$hD$`D$XD$PD$HD$@$ $H$pD$hD$`f(D$Xf(D$8$0D$PD$HD$@$ $f(f(f(H$pf(D$8D$0D$hD$`D$XD$PD$HD$@$ $H$pD$hf(f(D$`D$XD$8D$0D$PD$HD$@$ $鰾f(f(f(H$pD$8D$0D$hD$`D$XD$PD$HD$@$ $H$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $~f(f($`$X$`$Xf(f(f(f(f($`$Xf(;$`$Xf(ff(f($`$Xf($X$`f(f(f(f(f(H$pD$8D$0D$hD$`D$XD$PD$HD$@$ $cH$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $颺f(f(f(H$pf(D$8D$0D$hD$`D$XD$PD$HD$@$ $yH$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $lf(f(f(H$pD$8D$0D$hD$`D$XD$PD$HD$@$ $H$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $:f(f(f(H$pf(D$8D$0D$hD$`D$XD$PD$HD$@$ $H$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $f(f(f(H$pD$8D$0D$hD$`D$XD$PD$HD$@$ $H$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $ҵf(f(f(H$pf(D$8D$0D$hD$`D$XD$PD$HD$@$ $H$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $飹f(f(f(DL$PfA(DD$0d$@DL$PDD$0d$f(ƻT$ f(fd$` d$`t$Xf(|$0f(Ⱥf(f(f(H$p$8D$0D$hD$`D$XD$PD$HD$@$ $uH$pD$hD$`f(D$Xf(ዌ$8D$0D$PD$HD$@$ $f(f(f(Ή$D$f(D$D$D$D$D$$x$@$D$D$f(D$D$D$D$$x$@D$PfA(fA(fA($$D$D$D$$$xD$@$$D$fD(D$fD(D$$$xD$@fA(fA(f($$f(D$D$D$D$D$xD$@$$D$D$D$D$D$xD$@&f(f$ $l$Xd$Pt$ l$X$d$Pt$ fD(f(T$0\$f(f(t$pl$hCt$pl$hf(\$PT$Hf(f(f(f(l$Pd$Hl$Pd$H$f$$qf(f(f($`$X$`$Xf(!f(f(f($`$Xf(X$`$Xf(+f(f(f($`$X$`$Xf(:f(f(f(lj$h$`f($X$h$`$Xf(6fA(f(f(|$Pt$ |$Pt$ f(f(f(of(f(fA(l$ Rl$ f(f(#D$0fA(l$Xt$P|$ l$Xt$P|$ L$8ff(f(f(f(f(f(T$P$T$P$fI~{T$Xfd$P$d$P$$$T$Xf(f(f$d$PCd$P$$$T$ fD$PfD(fDff(f(lj$D$f(D$D$D$D$D$$x$@$$@$xf(D$f(D$D$D$D$D$f(f(lj$$D$D$D$D$D$D$$x$@$D$D$f(D$f(D$$D$D$$x$@lf(f(f(lj$f(Չ$D$D$D$D$D$D$$x$@$D$D$f(D$D$$D$D$$x$@f(f(f(Չ$$D$D$D$D$D$D$$x$@$D$D$f(D$D$$D$D$$x$@Hf(f(f(lj$f(Չ$D$D$D$D$D$D$$x$@A$D$D$f(D$D$$D$D$$x$@f(f(f(Չ$$D$D$D$D$D$D$$x$@o$D$D$f(D$D$$D$D$$x$@8f(f(f(lj$f(Չ$D$D$D$D$D$D$$x$@$D$D$f(D$D$$D$D$$x$@f(f(f(Չ$$D$D$D$D$D$D$$x$@$D$D$f(D$D$$D$D$$x$@(f(f(f(lj$f(Չ$D$D$D$D$D$D$$x$@$D$D$f(D$D$$D$D$$x$@f(f(f(Չ$$D$D$D$D$D$D$$x$@$D$D$f(D$D$$D$D$$x$@f(f(f(lj$f(Չ$D$D$D$D$D$D$$x$@I$D$D$f(D$D$$D$D$$x$@f(f(f(H$pf(D$8D$0D$hD$`D$XD$PD$HD$@$ $iH$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $錥f(f(f(H$pD$8D$0D$hD$`D$XD$PD$HD$@$ $H$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $Zf(f(f(H$pf(D$8D$0D$hD$`D$XD$PD$HD$@$ $H$pD$hD$`f(D$XD$8D$0D$PD$HD$@$ $$T$fD$0fD(zT$ f(f(f$d$0d$0$L$`鳟T$ ff(l$`d$0l$`d$0L$P*f(f(\$PT$0|\$PT$0L$XVDAWf(f(AVAUATUSH$N T$P8 \$xd$@$f($`$h$p$x$$$$$$$$$|$H$(T$8H$L$X$ $c $Pr $9 $XX $H$`F $$h4 $(f$p $$x4 $^)$HDŽ$HDŽ$HDŽ$HDŽ$8$@$$ $$0)$H3 fW-Ä )$ )$0)$@)$P)$`)$p)$)$)$)$)$)$ H$^fl$pf/X! $f($ ^f(fW% $ $t$`f|$XY$ XfYD$p|$hf(\d$`$f.+l$PfH$HH$@H$,H$*É$,\$Y- f(  $@$H$0Y$8Yƃ)f(fW- f(f(Y\f(Y\f.+HH@Hf(f(YYf(f(\Yf(Y4$Xf.l$=+ff/d$Xd$Xd$pL$8G H$~-3 D$0AH$H$`H$AH$H$@AH$H$ H$H$H$H$D$H$)l$ @D1)D)f|$PHcH$AAT$I*HIJ 0H$J0H$XJ40H$f(LPH$$D$x$N 0H$|$ N0TXZ|$H8d$`\$pfBX4`D$BX4hf(|$ffYf(Yf(YY\f(Xf.$HH@\H\f(l$ t$@f(ffT)$`f/|$DDf/$IH$$IB4LH$oH$$B4 G$$f(\$fI~f(E  $f(|$ YfIn\\ XfTf/|$@ff/o!f/$`!4$f?| El$f(YXYf(\f.&D$0At6ff.ef/ef.ef/efDD$0D$L$$AD$H9D$8!AfDff/ f/$ f$$t$ d{ EX{ YY\Xf. #D$0A]ff.mzf/muf.mz f/m9fUD$0D$L$$+@B4@B4HB\4`B\4h+|$}EuH6 -z Hz ( Yf(YY\f(YXf./#H$\f(f(ʿHH$T$H$$$覷$H$$$H$X$f(f(;>y HD f(5y D$YfHnf(D$$YY\f(YXf.!HfD(f(HDEYf(YAYD\f(Yf(XfD."HfA(fA(HfA(DAYYAY\fA(YXf.@"H,$L$DXXf(f(YYYY\Xf.!f(fA(f(YYY\fA(YXf.:!fMcH$H$)$p$h$$@$H$`$$-L$$p$HYYY$f(f(ff(f()$`Y$xYY\f(YXf.f(f)$pAp ff/|$XrfW-y $xD$If($pB4B4YHf(YH$xf(Y\f(YXf. ,$fov Ed$f(YXYf(\f. |$tDD$L$$kt$PD$0AAAt$fDD$8$D9Al$\$Xv fT$`$L$$L$9l$8+D$8D$(1fH$H$EXH$@*HXd$XH$PD$x$$f(L$L$d$0KAYAZ|$Hd$ \$pfX$T$`X$f(d$ ffYf(Yf(Y\f(YXf.$$\$\~5Sv d$@f(ff()$`fT)t$ f/C $$f/z AE\$8t$H<$$Hd$)HHcH$$YHDDYHH$$`HH$$pLt$h$x$f.$f(|$ D$D$f(fATfATf($$f($D$D$f/$$$$$D$D$*AmMcfA($BfA(fA(D$D$Y$t$YY\fA(YXf. f(f(f(LHDDAYAYAY\f(AYXf.ffA(fA()$`AYfA(AYAY\fA(AYXf.;f(IIF,fF,A)$pL9f(f(f(D$pD$xYYY\f(YXf. X$`X<$D$`X$hXd$D$h$pfD(EYf(fD($xAYEYD\f(AYDXfE.$t$EE^A"If(f(L9DD$(E!5t t L$Xf|$8$,=,p H$\8H$f(fTfTfU<$Y$fVt$<$$Ht$$@)ЃufW%r fW-r $0$8fWur f(Yf(YY\f(YXf.)HH@HfWr f(Yf(Y\f(YfD(|$f(YX$fD.DŽ$PAD$$D$8HcA1$$IH$H$A~=lp ID$0J,D$)|$ Il$fD)*$Xd$PyH$9W;$J$|$H$$$X\$pXT$`f($$f$f$$$Yf(f(YY\fYXf.\f(d$ \fTf/d$@f(f)$`tff/NCf(f$HfH)$pfD(DAYff/l$XrfDWo D$xfA(f(fD($pAYAF$xYHEYH\DXfA.f(ǃ|$HfA)$pAD$$`AD$$htv$D$`H$PH$p$L$XH$`$$AD$0$pD$x$$d$D$$$`$hf(fA(YYY\fA(YXf.XAX<$fW=Vn d$<$|$fW==n f Ik AD$;k |$$YYX\f.ff. f.AAIH$D9f$D$Nf$$ $$$$$f($fI~f( $f(l$ d$@YfIn\\ XfTf/ff/ f/$H$HfHDHH9uD$8D$0D$0HĈ[]A\A]A^A_fD$f(|$ $$f(fTfTf($$f(Խf/$$$$$$$$f($^T$x$$f/$ff/ f/$ $$fh El$f(YXYf(\f.]D$0Aff.mNf/mCf.m8f/mf(fff/EAAf/EAAaf.AA;$ AGH$HHH$$ $$@$$`$$$$D)$A($ADf/$$$$$$$$$f($$f(߸ $$f(|$ Y\f(\ XfTf/|$@ff/ Cff(͉$HfH)$pfD(DAYd$hfW%h d$hl$XL$pd$`$ c$$l$D;$T$8D)~Hc$$$`H$H$h$$,|$ft$$p*$t$x$x<$Hc$H$Dt$0Dl$HHHlL$BHH)Gff(f(l$pd$hT$H\$@DD$P|$ |$ DD$PD$8fA(f(|$0DD$ pT$Hf\$@DD$ |$0fD(f.d$hl$pEf.t$8Etff.DȄ9fA(f(l$Pd$H\$@T$8DD$0|$ F|$ f/$DD$0T$8\$@d$Hl$PDŽ$PfEAfE(fA(fA(f(f(f(YfD(YYDY\AXf. AXAXfW%e fW-e fAD$fA(f(fT |d l$0fTnd d$ DD$@|$8Vf/D$xd$ l$06D{Hc|$$`DD$@$hf(t$xt$Yf(YY\f(f(|$8YXf.:f(f(fD(HHDYAYEY\f(YAXf.dffA(fA()$`AYf(YY\f(AYXf.Hf)$pD|$t$IL9#$X $$$p$xYYL$f(fD(Yf(YDY\f(YAXf.X$hT$$hX$`4$$`\5T` f($xY$pY4$t$f(YYfD(\DXfA.AT$A\$AfE(fD(AhC$H$\H$T$$HʿH$eH$$H$X$$$$D$D$f(f(f(D$$AYAYAY\f(AYXf.f(uf(fA(fA(D$$AYYAY\f(YXf.vXXD$|$$$fA(Yf(f(YY\fA(Yf(Xf.ef(f(f(YYY\f(YXf.pfH$H$)$p$hJ$@$H$`$$XHc$$$pHHYYY$f(f(ff(fD()$`Y$xDYY\f(YDXfA.r f(fA)$p\Hf(DAYDDd$8'Dt$02fD9$H$H$f(1H$HH$PD$x$$L$L$$:3XZ$Hf.D$ f(l$Hd$@DD$8\$hT$PҮDL$ |$0f(DD$8$ \D$`d$@l$HX$fW ^ f/T$P\$h$DD$Hf(f(|$@DL$8d$pd$`\\d$X\\D$0L$ $P\$ T$0DL$8f(|$@DD$H$d$pf5_ ^ $$\$\$tD$0$f(|$ D$f(fATfTf($$f(f/$D$$$1$$D$$f(d$x$^f/ffDŽ$f(fD(fD()$pff(f(>|$8w$D9AD$0AD$L$$ff/ۃf/Ѓ${$ffEDŽ$D$YBfd$xfEDŽ$Y\$XFY fT$`$L${$A1DŽ$D$0gT$ff( f(f(f(f(l$@d$8t$0|$ תl$@d$8t$0|$ f($f(f(蠪$f(f(HW f(f(fHnHX fHnef(f(DT$PD\$HDD$@|$8d$0l$ ,DT$PD\$H|$8d$0f(DD$@l$ L$f(D$l$0d$ ۩l$0d$ f(fD(3HW f(D$$fHn虩D$D$$f(f(H0W f($fHnQ$f(f(fA(f(f($ $f($L$$$D$$$D$f(fA(fA(fA($$D$荨$$D$f(kD$f(fA(D$$=D$D$$fD(f(zU L$f([f(f( ff($$ŧ$$f(f(U L$f(菧HT L$pf$ fHnfD$h$9fA(f(fA($$-$$f(fD(5D$fA($$D$$ئ$$D$$f(襦$L$$HT f(fHn}$f(-HT S f(f($$fHn>$$fA(fA($$$$$$D$DL$ѥDL$$$fD($fD($$$D$uf(f(f(D$f(t$D$D$D$$$$t$D$D$f(D$f(D$$$$CfA(fA(fA($fA(|$蟤|$$f(f(fA(fA($$D$D$D$DD$=DD$$$D$D$D$f(f(fA($fA(DT$$D$ǣDT$$$f(f(D$f(f(fA(l$@d$8DD$0|$ DL$t$_l$@d$8|$ t$f(DD$0DL$5fA(f(fA(l$f(d$ l$d$Cf(f(fA(D$$fA(ҢD$$f(f(AfA(f(fA($$荢$$f(JO L$f([ff(f(Ef(Gf(f(H$'H$f(fD(cf(L$D$l$@d$8DD$0|$ l$@d$8DD$0|$ f(vf(f($$$0l$蠡l$$$l$$$耡l$$$D$$!D$fA($$?$$f(^f(f(f(f(vf.AWf(f(AAVAUAATIUSHU l$Xff/L$H U T$\$ $$$$$$$$$$$$$$ t$(f(HM t$fHn蔦t$fT5O Y5ν f(D$HfTlO f/At#fD$*X\:M =f(\$(f~=7P t$Hf()|$`fWf(YfWXf(L$xfY\f.L$pfff/|$Hf(ԿAH$H$H$HH$P\$0$$L$L$M#$\$$\$$D$$T$ 趪$D$`$Y^T$Aud$\d$H\T$(d$Au~N |$fWfW|$T$KT$f/$f/T$X~ N $fWf/#|$XfWf/A~%dN ,$HcAHMcfWL)d$`E1l$@f*Xd$A=J f(5- ffl$(^)$t$HYf(YYY\Xf. f(f(YY\f(YXf. X}J |$8d$\$@$i$\$@f(JJ  $l$0XN蹞d$4$fD(l$0f(YfYf(f(\YfAY|$Xf.|$8m L$ff(Y)$fYf(f\Yf(Y$Xf.o $HI f(f(|$0ff)$fHno|$0f(f(fYf(YY\fYXf.B f(BYYf(f)$$\T$$s$Au\T$(f/T$L$XfWL$`$f/.f$XACf/T$T$q$й ^D$ $$לT$f(f(\$ޡ\$f(f^d$ d$@Yf(\$8\$8D$0f(L$薦T$0L$d$@XYYfTI fT%I f(T$f(d$0Of/$$w&T$L$0f(莠$^\$ f/wmHD[]A\A]A^A_~(ELfHIDfHH9uA|$pfW|$`|$pCfAHw@H$H$f(ԿH$HH$P\$0$$L$L$u$\$$$T$D$`XZ$v@D$P$Yط $X \f/T$ $j ^D$ $$T$0k$L$$NY f \$T$0\dAt#fD$*X\E 苞f(t$(|$Hf-gE f( Yf(^)$fYYY\Xf. f(f(YY\f(YXf.MXD l$@d$\$0T$\$0T$f(D L$0t$8Xř0d$f|$0Yf(Yf(f(\YfYl$f(Xf.t$l$@t$8fD$fY)$f(Yf(f(\YfY\$0Xf.fH~D$0ff(f(fHnHC l$8f)$fHn٘l$8f(f(fYf(Y\f(YfYXf.Gf(AzAEfHn\d$HD$pHHD$xYYf(f)$T$0\T$d$~ F fWfWD$(f(|$HHT$襕T$XARf/$WA>E13T$0\$_T$0A\$Xff/T$0&$ij ^D$ D$$ʖXL$T$0f(L$0ϛL$0D$f(躛T$f^T$ YfTC f(T$0菖f/D$D$nT$0ff(ʚ\$^\$ f/ExELfHIDfHH9uKD$PT$.Y T$X \~ELfHID@HH9uD$PT$0ΓY T$0X \$\f/v$7 ^D$ D$$T$87$L$0$T$8f(L$0XL$Y \5fA(f(ft$@l$8|$0$$ʒt$@l$8D$|$0$$f(Df(f(f|$@f(t$8l$0}|$@t$8l$0$Nff(f(PL$Hf(ff(d$<$)d$<$f(f(f(f(|$8d$0\$$|$8d$0\$$f(f|$`t$@l$8d$0謑|$`t$@l$8d$0D$L$f(f(fl$`f(|$@t$8\l$`|$@t$8D$0fH~f(f(l$8d$0\$T$l$8d$0\$T$qHi> f(fd$fHnِd$D$xL$pdf(f(ff(譐f(L$Hf(ff(d$l$聐d$l$f(f(AW1AVAUATUSHt$x5= |$tH$^$HH$HH= D$Pf$$l$hH$L$AH$HH$hL$(d$$P$`)$)$$@$pW f(f(^fHnHW= H$H< fHn$^$$觕|$(\$Pf5< f$Y^Y$$Yf(t$Yf(\Xf.f(f(YY\f(YXf.{X< \$ T$\$ T$f(; L$ t$0XK4$fYf(YYf(fY\f(t$0|$Xf.|$ $fYf(YY\fYf(Xf.|$td$0fd$0l$ l$ \$(f(T$P$XX$$Y\d$f(fT< f/D$hvNff/qH$$H$fHHHTHH9uL- $N$\HcfL$*HL$X$H$I$@fT$P$*\$(\f(|$=9 ^Y<$\$YX$f.f(f(YY\f(YXf.L$ nX9 L$ T$0\$fH~l\$T$0f(L9 L$d$8XO躍t$fl$Yd$8f(YYf(\ff(Y|$HXf.\$0t$fYf(YYf(\fY|$@Xf.t$8H8 ff(f(fHn蕍<$ffEYDYfD(DYYD\DXfE.Dt$,fA(fA(Dl$`.\$ fHnH8 ff)$fHnHl$ ~P; f(ff(HYfH7 )$YLt$XfEDl$`fLnظfE(ӉfD(D\XfA(fD(fD(jff(f(f(YDKYY\f(YXf.HcAlXCf(f(f(YDSYY\f(YXf.IcAlXf(f(f(Yˍ{YY\f(YXf.McClXf(f(f(YDKYY\f(YXf.ZHcAlXf(f(f(Yˍ{YY\f(YXf.2McClXf(f(f(YDK YY\f(YXf.HcAlX [f(f(f(Y΍{ YY\f(YXf.McClX xf(f(f(YDK YY\f(YXf.HcAlX f(f(f(Yˍ{ YY\f(YXf.HMcClX f(f(f(YDK YY\f(YXf.HcAXTf(  f(f(f(Y΍{YY\f(YXf.McCXTf(f(f(f(YYY\f(YXf.HcAlXfDT$fE(DEYf(AYAYD\fA(AYfD(DXfE.Q f(fA(fA(AYYY\f(AYXf. DY$\$Hf(HfA)fA/vfTF5 fT >5 Xf/HHfE(fE(fE.A{A fA(fA(f(f(DKHcAXDYˉYf(Y\f(YXf. HcAXlf(f(f(Y̍{YY\f(YXf.vMcClXf(`DffHl$ X$Lt$XX$X$X$FX$X$+X$X$X$X$X$X$X$ X$(X$0X$8X$@X$H X$PX$X trX$`X$h t[X$pX$x tDX$X$ t-X$X$tX$X$@Do |$tD a DY$DY$\$8T$@fl$XXT$PX\$(d$ D$DL$D$g|$fD$f(DL$d$ Yl$X\t$HY\L$0XL$(XfD(f(fT2 f/D$hHDDf/D$xA_t$8fA(fA(fA(YYY\fA(YXf.fA(L$ HcH$8H$0|$t$0̈́$8$04$t$0T$f(T$@|$L$ YYY$f(f(Yf(YY\f(YXf.AHf(HIfH)`YYfA&9$xD$A}Hw. \$(fɻT$PfHnpAGfH$H$D$D$D`L$HĀAED$*H$HLd$$XYY\$f(AYf(f(YAY\f(YXf.f(fA(fA(DAXX)\={- Yf(AYf(fA$Af(f(fT O/ l$HfTA/ d$@DD$8DL$0t$(|$ T$\$fHnt$(DL$0f/DD$8|$ d$@l$HAYIcA\$@EYT$HĀD`YYfE(DYfD(fD(f(YA9jIs9$QH$HHHlf(f($$f(DD$HDL$@HXt$8|$0d$Yl$Y\$fD(fD(DYf(YDYD\f(YD\$(DXf(DT$ +~DT$ D\$(f(DL$@t$8fA(DD$Hl$Ad$|$0\=X+ f(fTfTfAUfAUfVfVfA(AXXfA(fD(f(YYfM9$H[]A\A]A^A_fA(fA(t$8l$0d$ DT$DD$D $Kv}t$8XD$8fT, f/D$hOHD $DD$A_DT$d$ l$0|$8ff/Ӄf/EAAiffHl$ X$X$Lt$XX$X$t$@DT$8\t$HD\T$0f(f(d$fT+ fT + ,$f(\$ L$0D~,$d$f/$D$\$ L$0l$$$f(dT$$$^T$f/l$ft$8ff/H$H$fL$$DAl$x|$tھd$h\$$D$PL$(CxcA)É$f*X$\( f/$H$mfDf(wt$8H$@fD(fE(f(fD(\d$7ff(f(lj$f(|$`D$D$D$D$D$D$$$8z|$`$A$f(D$D$D$D$D$D$`L$fA(fA(fA($$D$D$D$$$Dl$`wyDl$`$$fD(D$fD(D$D$$$fA(fA(f($f($D$D$D$D$D$DD$`xDD$`$$D$D$D$D$D$xf(f(f(lj$$D$D$D$(D$ D$D$D$D$$|$`w$D$(D$ |$`f(f(D$D$$D$D$D$D$$Ef(fA(DD$8D\$0DT$(|$ t$DL$GwDD$8D\$0DT$(|$ t$DL$T$f(f(fl$Xd$vl$Xd$D$@L$8T$fl$8d$vl$8d$D$HL$0Fd$HfA(fA(DD$Pt$H|$@DT$0DL$(D\$ Dd$EDD$Pt$H|$@DT$0f(f(DL$(D\$ Dd$f(f(fA(DD$PfA(Dd$HD\$@DT$0DL$(d$ l$3EDD$PDd$Hd$ l$f(f(D\$@DT$0DL$(Zf(D$(L$ Df(T$HL$ fA(d$hD$(l$PDd$hl$PUfA(fA(DD$@|$0t$(DT$ DL$pDDD$@|$0t$(fD(fD(DT$ DL$ f(f(fA(DD$(fA(Dd$ D\$DDD$(Dd$ D\$f(f($\$(d$P$T$ l$HCd$Pl$Hf(f(bf(f(f($t$(|$ Ct$(|$ f(f(b$f$f(LCf(f(2fc $l$(f(d$ Cl$(d$ f(f($0$8Bl$ d$D$L$($0$8BD$L$T$pff(B[\$xT$hf(L$ mBH f(ffHnOBf(f(L$ D$(l$Pd$H%Bl$Pd$HD$x$T$(f(f(l$Pd$Hf(Al$Pd$Hf(f(!fA$$~fA(fA(fA(DD$(fA(|$ t$}ADD$(|$ t$f(f(f.AWfD(fAVAUAATIUSHh)$ )$0fA(\$0|$D|$($d$8l$t$L$ L DD$ D|$(f(f/s>ff(D + *X$YY _ A\f(AXf/l$$LDfA(fA(Ad$\$|$@D|$(DD$ AA1A)E)<E3fDD$ D A*X$D|$(|$@A\t$0f/fD/(l$$LDd$\$fA(DfA(ȾDL$H|$@D|$(DD$ 艞DD$ D|$(|$@DL$HkAA)jAFfD$d$8*D$HDXl$PfD/w f/@D$8fA(fT HDŽ$A\,f)$@)$P)$fA(fTL X\ ƒIf/* *fE\$8Dt$D*l$d$fA(fA(H$H$@L$D$`DL$pDT$@EX|$hD\$XfA(DT$8D|$(DD$ 軭DL$pD$`|$hD\$XDT$8D|$(DD$ $D$HD$X$@D\$xfA(DD$pf(D|$hD$D$|$`Dt$(t$ Id$Dt$( C\ D$Xf(^{] |$`D|$h^DD$pD\$xY D$D$T$8$$f/fA(fA(L$8^^t$Xl$`l$ YAYf($P\$Xf$XfD(fD(DYf(YDYYD\DXfE.>fA(Y\D$ YXf.>D$xH fA(ffA(׉$fHn$D$D$D$$$$D$DD$pD|$hD$F>D$xD|$hDD$p$D$ L$(D$$$$D$D$D$$ D$$L$AD$fA(DD$@DT$`D\$@D\$X$D$ fA(fE(fE(YDYEYD\f(YDXfE.pfA(fA(fT  $fT D\$xD$D$$DD$pd$h|$`Dl$XD$D$@f/D$8Dl$X|$`d$hDD$pD\$x$D$D$$[f(fA(fA(IcYAL$D$D$YY\$8\f(YXf.DY\$fD(f(YfD(fE(DYEYE^D\f(AYDXfE.fA(fA(fA(YAYY\fA(AYXf. Ã9\$@AXT$ YY\$(f(f(Yf(YY\f(YXf.-DXAXE\fE(AfD(fA(fD(f(rfDfD/sYf(Xf/[t$$Ll$DfA(fA(d$\$0?$y t6AHhD[]A\A]A^A_AE1DuA\$$LDfA(fA(^vyt$l$fA(fA(d$$H$L$\$8LDDDL$H|$@D|$(DD$ DD$ D|$(|$@DL$H$ADžD$El$0f/"l$d$DH$ \$$fA(HfA(ȺDL$0D|$(DD$ DD$ D|$(DL$0*DL$ _l$$HDd$\$fA(fA(ȾD|$DD$&1DD$D|$DL$ $fA(LD\$fA(DL$D|$D$AD$D|$DL$ fA(H$H$DL$(D|$ DD$X8DD$$D|$ DL$(4$$t$f$0t$@D$8DL$8fA(f(DD$0D|$(|$ DT$ A S d$DT$|$ ^D|$(DD$0DL$8t$@f/fA(^fD(l$AYDYf($ \$$(f(fD(Yf(YDYY\DXfA.vfA(f(YYD\XfD.E$A|$f(fA(f(YAYY\fA(AYXf.W XAXfA(fA(fA(YYY\fA(YXf. f(t$@DL$8DT$0|$(T$ L$?DL$8L$fW T$ D^t$@|$(f(DT$0YfA(fA(YY\f(YXf. f(fA(fA(YYY\f(YXf.s ,$d$f(fD(YYDYYfD(D\DXfE. l$fA(Yf(AYAY\fA(YXf.Y fA$A^XAFI\$fA(D\$HfA(Il f(f(f(f(f(YAYY\f(AYXf.f(fA(f(DY{YY\fA(YXf.fHCH9q@t$l$fA(fA(d$$H$L$\$8LDDDL$H|$@D|$(DD$ DL$H|$@D|$(DD$ fE\$8Dt$D*l$d$fA(fA(H$H$@L$D$`DL$pDT$@EX|$hD\$XfA(DT$8D|$(DD$ QDD$ D$`D|$(DT$8D\$X|$hDL$pQE~!AFfHIDfA$IL9uEf.D\$XD$D$$L$DT$`D$D\$@\$`f(IcYHf(IDYY\f(YXf.0 fAxL$HlHcI\D$Dt$PHD|$`D$fE(MtDl$X$HfA($H)T$ YY\$(f(Yf(f(YY\f(YXf.DXAXfE(fA(fD(fE(YDYDYD\fA(AYDXfE.fA(E\fAAfA(fA(fT $fT DL$xD|$pl$hDl$`Dt$Xd$PDD$H|$@D$D$f4f/D$8|$@DD$Hd$PDt$XDl$`l$hD|$p$DL$xf(f(f(HcY΍ED$D$AYAY\$8\f(YXf.?DYl$f(fD(YfE(DYE^fE(DYD\fA(YDXfE.ifA(fA(fA(YAYY\fA(AYXf.R IL9t)$AXffD(fA(fD(f($$D$D$lD$if/D$8rrfA(f(^t$Xl$`l$ YAYTfA(^f/rTf(fD(AYDYf(PfDL$4$l$ fA(DL$`DL$XfA(fD(DL$f(f(fA(D$fA(l$xDl$pDt$hd$`t$XD|$P|$@Dd$H@+l$xD$Dl$pDt$hfD(fD(d$`t$XD|$PDD$H|$@f(f($DL$xDD$pD|$hDl$`Dt$XDd$Pd$Hl$@*DL$x$DD$pD|$hf(Dl$`Dt$XDd$Pd$Hl$@f(f($D$D$D$D\$xDD$pDd$hd$`l$X *D\$x$f(d$`D$f(D$DD$pD$Dd$hl$X)f(f(f(HfA(DT$(|$ t$D\$l$$$v)$$l$fD\$t$CH9|$ DT$( Kf(fA(t$D$!)t$D$f(f($T$f(fA(fA(DT$(|$ t$DL$D$(DT$(|$ t$DL$D$I$T$t$(DT$ |$(t$(DT$ |$fD(fD(f(fA(f(DT$(f(|$ t$<(DT$(|$ t$LfA(f(f(t$ DL$(DT$0|$(t$ DL$f(f(f(f(fA(t$0fA(DL$(DT$ |$'t$0DL$(DT$ |$f(f(fA(fA(t$Pf(DL$HDD$@D|$8d$0Dd$(|$ DT$>'t$PDL$Hd$0DD$@f(D|$8Dd$(|$ DT$f(f(f(ʼnD$HfA(DL$pDl$hDt$`D\$XDT$Pt$@&DL$pD$HDl$hDt$`D\$XDT$Pt$@Lf(fA(ՉD$PDL$xD|$pDt$hD\$`DT$Xt$HDl$@I&DL$xD$PD|$pDt$hfD(fD(D\$`DT$Xt$HDl$@D$ T$Xf(fA(Ή$D$hD$D$D$D$D$D$|$xDd$pt$(%$|$xD$D$hf(f(D$t$(D$D$D$Dd$pD$T$Xf(މT$xD$hD$D$D$D$D$$$D$|$pt$($T$xD$hD$|$pfD(fD(D$t$(D$D$D$$$D$T$f(fA(f(DL$@DD$8D|$0D\$(l$ t$ $DL$@DD$8D|$0l$ fD(f(D\$(t$T$f(DL$PDD$HD|$@d$8Dd$0DT$(|$ t$#DL$PDD$Hd$8D|$@f(fD(Dd$0DT$(|$ t$T$`f(f(f(ʼn$H$D$D$D$D$D$$Dd$xt$pd$hl$@"$D$D$t$pD$H$D$Dd$xD$d$h$l$@f(fA(fA(ˉD$PfA(DL$xDD$pD|$hDt$`Dd$Xt$HDl$@"DL$xD$PDD$pD|$hf(f(Dt$`Dd$Xt$HDl$@!f(fA(fA(ωL$hfA(t$`D$D$D$DD$xDd$pD\$X!DD$xL$hDd$pf(f(D$D$t$`D$D\$XWf(fA(ӉL$hD$D$D$D|$xDt$pt$`D\$X D|$xL$hD$Dt$pfD(fD(D$t$`D$D\$Xf(f(f(ʼnL$`fA(DD$xD$D$D|$pDt$ht$X^ DD$xD|$pD$Dt$hD$L$`t$Xf(f(fA(D$fA(d$x$D$D$t$pDT$h|$XDd$`d$xD$t$pfD(fD($D$DT$hD$Dl$`|$XfAVGAUIATUSH@vAEE1H@D[]A\A]A^@~fT$f/wAHD$L$+u? f/CfDT$d$*\$AXf/>? 1H|$8Ht$0d$f/fA(\$DT$f.fɍ@GA,AEAA)D)*\Y+= 6!DDL$0DD$8~- DT$D\$d$Ѓ)ЃMf(f(ffWfWfYYX\f.ff/-= l$(Hx< =`= DH5J= fA(DD$% > <= fHnDL$#DL$DD$A)ÅCHH\Y H; Yy fHnfA(f(fA(YAYY\f(AYXf.|Yt$(Yff(EAYfAYAY\fAYXf.HH9EfD(fD(U]DD$ DL$f(f(fT \$fT T$"=< T$\$DL$f/DD$ H fHnfAEE1H@[D]A\A]A^D=H fWfWfDW|$(fDWfDWtAEE1OAEE1<\$(ffA(fA(ofA(fA(l$DD$DL$Gl$DD$DL$H ff(f(DT$ d$DD$DL$~- DT$ d$DD$DL$fAWfD(fD(IAVAUATAUHSHD$P L$H $$f$$fA(fW )$@)$P)$`)$p)$)$)$)$)$ fA(fW T$|$(L$0D$ 4$l$AŅy)ADEHD[]A\A]A^A_4$Nl$(\$H$@T$D$ f(L$0wAŅu$@% $H|$`\$XEx% d D$HL$H$d$LH4$fd$$f(t$hH4$$YYf(Yf(f(\f(Y|$@Xf.L$8D,d$fD$LA*\YND$$A<$At$A)AufW5 f(fW- t$,$D$`DŽ$fD$X)$A$AG$6 f(^T$$, \$(D$ H$H$L$0H$M$$AD$8d$@$$f(f(YYY\f(Yf(f(Xf.L$T$f(f(YYYY\f(Xf.XXfAAGD$f($PDT$$AGfDW. fDW% )$$P$X$\$(D$ H$H$$L$0H$$D$D\$xl$pјl$pD$D$D\$xAD$$D$D$L$@|$8$$f(f(YYYY\Xf.fA(fA(fA(AYAYAY\fA(AYXf.OXX$$fAgT\$0T$ f k |$T$D$p$f(f(^$$^X$($H L$xt$0YH$0$pYf($$D$f(T$ $`$$B t$0$$H $f/D$XDd$`fD(f(DYA$YDYY\$hL$XDl$`YDYD\DXfE.) \$hf(YYfD(D\DXfE. El$hMw HIl0l$0ffE(fE(fD(f(fD(fD(\$8T$@f(f(AYAYAYAYfD(\DXfA. $T$f(f(AYYYAY\f(Xf.XAXt$Xt$Xt$p|$`|$fW= ft$t$ Xt$xA&$$fW% |$t$ $$AfT- fA(fT D$D$D$f(D$pf/$D$D$D$D$B |$E|$$t$0f(f(AY|$`AYf(AYAY\Xt$Xf.t LfD(f(HfD(`hDYYDYD\f(YDXfE. f(fD(f(YfD(DYYDYD\DXfE.] IB$B$Mct$|$0II9|$ l$f(f(AYAYAYAYf(\Xf.AXAX|$l$0f(f(YYYY\Xf.A.Aff(f)$fD(fD($$$l$`d$Xf(f(D$D$$$$$l$`d$X$f(f(hl$h$$f(D$$f.$D$D$Ef.EtfD.DȄfD(f(f(fA(D$D$D$$$$\$`T$XT$Xf/$$\$`$$D$D$D$d$hffE(fE(AfD(fD(DŽ$fD()$f(fD()$fD($$Dfd$8L$H$t$ht$@D|$Xt$`|$hfD(fD($$$D$D$&$AD$$DŽ$HHfD(f(h`YDYYYfD(D\DXfE.f(fD(f(AYfD(DYAYDYD\DXfE.fA(f(D$$A@f/$r]\$fH~D$XAHD$Dd$`H# Yf(f(DYfD(DYH$Y6HD$Dd$`f(fD(D$XfHnADD$XfA(D$D$$$$T$` t$PfD$$d$X)$f(T$`$$XD$$D$Xl$(fW- f/'D$fA(D$$$$$$ t$Hl$PXXXXf(fL$X)$f(l$`~$DT$Xl$`fD($$$$$D$D$;fDfE(fE(fD(D$$fD(@Dd$hfE(fA($T$fA(f(D$D$D$D$D$$$$DT$`l$XO DT$`D$D$l$XD$D$D$$$$IL$8D$@fA(fA(D$D$D$D$D$$|$`t$X|$`D$D$t$Xf(fD(D$D$D$$WL$0D$D$D$\$`T$X\$`D$T$Xf(f(D$\$ T$fA(fA(D$D$DL$`DD$XDL$`D$DD$Xf(f(D$f(f(f(Dl$0f(Dd$LDl$0Dd$fD(fD(cf(f(|$`t$Xl$0d$ |$`t$Xl$0d$fD(fD(L$0D$fA(fA(|$`t$Xf(f(Xff(f(Dl$Xf(Dd$0Dl$XDd$0fD(fD(L$XD$`f($D$$$d$0/d$0$D$fD(fD($$]fA(fA(fA($fA(l$x$d$pl$x$f(d$pf($OL$8D$@D$D$$D$D\$xl$pND\$xD$l$pf(f(D$$D$$T$f(f(d$xl$pd$xl$pL$8D$@|$xt$p|$xt$pf(f(~f(fHt$$$$$Ht$D$@L$8fA(f(D$D$D$D$DT$`l$X-DT$`D$l$XfD(fD(D$D$D$d$\$`$D$D$D$$T$X\$`D$T$XfD(fD(D$D$$f.AWFAVAUATUSHH$fL$)$)$v%ff(H[]A\A]A^A_D1Aw$%E fEE*fD(f/Df/<" f/6" L$D$$Dd$@ ,$t$f(D$Xf(DL$fD(Dd$L$`DYf(YYYfD(D\DXfE.]fEfD/4$! DYDYrl$fA.zu fD/4$ =v! fA(fT 9 f/L$H 5Z HD$t$05/! fE/ fD/t$- l$w-Ͳ l$~߱ fDWfDWH! l$0L$ fA(fA(LfHnH Dd$PAX|$H^v fHnt$@T$8DD$(DT$ zT$8fEDT$ DD$(t$@|$HDd$P&fA(fA(D@q%( f/d$0f(fA(A^AYf/ 4$|$f(f(YYYf(\Xf. <$t$f(f(YYYYf(f(\X\$8f.fI~ AYfE(D3  DL$PEXAXDd$E\EXfI~E\DY A\DYfA(DT$@fA(DD$H^Dd$DY% D5 H fD(D- DL$PHD$DT$@fHnfHnHD$(fLnDD$HEXE\fED$Dd$fA(Dd$ g@Dt$`Dl$XDX5 DT$HDX- DD$P|$hT$p$l$xifD(f(f(f(T$8f(f(f(fInA^A^YYY\f(YXf. \$(D$8|$ XA^X\$(fIn|$ A^f(Yf(f(AYY\f(AYXf.fInd$EXEXA^l$xXT$pfA(|$h$d$d$Dt$`XDl$XDD$PDT$Hd$DYfA(D|$@7D|$@fD(D$0AYfA/ED$A1l$$$t$|$f(f(YYYYf(\Xf.  % D$(YYY\$ YXXf(\$RL$D$$,$t$f(Dt$f(f(YYYY\f(Xf.P Y D4$fVy D4$f(fA(YYL$fDD fA\Y DY% AX}@t$fA.Hڨ - fE(= 5 HD$l$0DH fl$HD$HD$(l$ f.fA(|$0DD$(DT$ Dd$L$Y fE5h Dd$DT$ DD$(|$0Xf/fA(fA({ffDV fYT$L$L$|$HLLt$@DD$8DT$(Dd$ f( t$@fE$$Dd$ f(fD($$f(DT$(DD$8Y|$HYDY\f(YAXf.l$f(AYf(YYf(f(AY\f(d$ Xf.\$(l$0fA(LH fA(D  DD$8fHnH E\D^ fA(DL$@fHnDT$0詷l$$fE$DT$0f(f(DD$8DL$@Yf(AYYAY\Xf.f(t$D$f)$f(fA($AYYAY\f(AYXf.>fA(fA(fA(|$8AXt$0DL$@YYf(|$8LLDL$@t$0D\ Z XD$XAY|$8t$0|$8$$t$0f(Yf(f(YY\f(YXf.XT$ X\$( YYApl$`t$Xf(f(YYYY\f(Xf.t$^^fD/4$pDt$HQ - =y 5i HD$l$0*fD/L$0 1 d$l$YY<$\$f(f(YYYf(\Xf.!|$ \$(f(f(YYYY\f(Xf.  p YYYYXXucf(f(fDt$,$f(f(YYYY\f(Xf.Hd$^^@$L$l$d$,$t$f(d$f(f(YYYY\f(l$Xf.Y l$fV $$#$$l$f(YYf(- l$0l$@f(fA(f(D\$xD|$pDt$hDl$`DD$XDT$Pt$Hl$@D\$xD|$pDt$hDl$`f(f(DD$XDT$Pt$Hl$@f(d$xDd$pD\$hD|$`Dt$XDl$PDD$HDT$@d$xDd$pD\$hD|$`f(f(Dt$XDl$PDD$HDT$@L$$f(DL$Dd$DL$Dd$fD(fD(df($L$el$d$15  H fE(= t$05 HD$$f(f(DL$ Dd$f(l$DL$ Dd$l$f(\$L$f(f(f(\$$f(DL$ Dd$l$DL$ Dd$l$D$8fI~T$(\$ f(l$d$Jl$d$f(f($f(l$d$f(l$d$f(T$fA(fA(d$PDD$HDT$@DL$8l$0d$PDD$HDT$@DL$8f(f(l$0^T$fA(f(DD$@DT$8DL$0qDD$@fEDT$8DL$0f(f(T$fA(|$ht$PDD$HDT$@Dd$8|$ht$PDD$HDT$@D$ Dd$8L$(f(f(|$Ht$@fEDD$8DT$(Dd$ f($L$Dt$L$`D$X~kf(f(f(f(df(f(L$$GfAWfEf(f(AVfD(AAUAATAUHSHxfD/w$fA.ADEfA.EA!ECvAE1HxD[]A\A]A^A_AEwE~EuAffD(EYA)fD(EYD)*fW D$8f(D$@YYDXD\fE.f(f(L$DL$ D\$0DT$: L$f/AGfDL$ DT$*D\$0fEAXf/O 1f/f. @Gf/A25" fA//f/  ia 59 f/t$Hf/% - fE/w`fE.zu ufE/wK\$HHDDfA(fA(fA(D $D $Al@A@Ha f(Hl$HD)f(Dx fA(fHnDfA(fA(D $LD$D $LD$DA@fE/fE.оz9u7fE/s0u+fDfE/vfDW fDW fA(LD$HD~= DfA(5 - D $fA(%} fTfATt$Hf(Yj f/fA(FLD$D $Aă|$8%L- H  E,fH|$hHt$`DA)D)*D\fA(YDfInfHnYl$`Yt$hDЃ)ЃufW- fW5 EAG~=Z HH\@Y DL$HY f(f(f(YYY\f(YXf.AYd$@f(AYAYff(EYf(AYY\f(Xf.yHH9Tf(f(U]t$8l$ f(f(\$0fTfTT$)<$cf(<$fE1 T$l$ f/t$8\$0H fLnfD#D $LD$f/Af/D$HDL- H  DD)fE. D5 % - t$HDwA\$HHDDfA(fA(-j %Z fA(L$l$Xd$PDL$ DT$0D\$HL$A)D\$DT$0fEDL$ d$Pl$XfE/AcY LD$PDL$ D\$0DT$ $I $fW fE% - YDT$D\$0DL$ LD$Pf/pB\$@f(f()<$fA(f(<$af(f()|$ DL$0l$4$pf(|$ l$fEDL$04$\$@f(f(fA(LD$ DL$0d$,$LD$ d$,$fD(fD(DL$0fAUfATAUSHH8f/w&f.ϹIEf.E!ЍWv1H8[]A\A]~uT$D$ $* f/AD$fT$ $*DD$Xf/ 1f/f. @Gf/؉5 f/f/%e  f/e f/Cf5_ fD/-Z ff/f(f(L5 DfA(FH fHn@H81[]A\A]ffD/tH81[]A\A]f1fA/vf/F~j LDfA(- %u fTfTYm f/q fA(s*Ej1 f5 LDfA( $-  f(t$ l$(\$T$DD$DA) $DD$T$\$t$ l$(ffA//f 5d fD/-_ f(LDfA(fDY \$ T$L$DD$$$$$fW%ؔ 5 DD$YL$T$\$ f/ffD/- ^Tf. f(fT\ f.@ff.,SH f/w fW < f(H|$L$D$L$f(E YX? Y\; YX7 YX3 HcHiVUUUH )׍ )Ѓu Y L$L$% f(f(Yf(^f(\Y\f(Y^f(\Y\f(ʃufW 6 H f([@f(DYh kǺHH! ))ƒtt 9fY( !Y ff(f/vfW 5 f(Yf/r, f/*Y% J \DHH$ f(P \$H|$8Ht$0- ^%\   YXX Y\%@ YX  YX Y\%$ YX  YX Y\% YX  YX Y\% YX  YX Y\% YX d YY\% YD$Yf(YX L$(Yd$ X YX YX YX YT$\5x f('L$(f d$ T$XXD$\$\%I XI f.^y ^YL$0^YYd$8\Y  Q^HHf(fD f(f(\ \ YX YY\ YX Y XYX YX YX | YX x YX t YX p YX l ^f(L$L$f(fHH-T f(f/&ff.(f/Nf(  " \$YYX\ YYX  X YYX \ YYX X YYX \ YYX X YYX \ ^D$f(\$D$f(L$Y b f(f(YXD$HHf( = H|$8Y % Ht$0\$^, YXX Y\ YX% YX Y\ YX% YX Y\ YX%t YX Y\ YX%X YX Y\ YX%< YY\ YD$Yf(f(Y\= Xz d$(YT$ Xj YXf YXb YX^ Yf(L$ d$(T$ L$XXD$\$\! X ! ^U ^Yd$8^YYD$0XY% ff.wiQ^HHf(fD1ҾH= 1EU HH1ҾH= 1È HHf(d$d$f(fHHf(f/ f/^T -| H|$85 % Ht$0T$f(\$(YYXX YX-: YX% YX YX- YX% YX YX- YX% YX YX- YX%z YX YX- YX%^ YYX- Y$Yf(f(Y\5 X d$ Yl$X YX YX YX Yf(L$Vl$fX-l L$X f Ɔ d$ \$(T$^XX$ o f.^YY\$8Yd$0\YQ^HHf(Y  XYX YX Y\ YX YX YX YX YX YX | YX ^f(\ x \x HHYYY~ fWf(~ HHfWf( $ $f(f.@HHT f(f/&ff.f/>f(  T$YXY\ YX YX YX Y\ YX YX p YX Y\ YX| YXx YX| ^f(Y $T$D$f( A T$YD$^\YU X$HH^ %$ H|$8=O - Ht$0T$f(\$(YYXX YX% YX-v YX YX% YX-Z YX YX% YX-> YXj YX% YX-" YXN YX%r YX- YYX%^ Y$Yf(f(Y\=u XE l$ Yd$X5 YX1 YX- YX) Yf(L$d$L$X% X  r l$ \$(T$^XX$^ff.YY\$0Yl$8XY wcQ^HHf(1ҾH= 1Ue HH1ҾH= 1+Ӂ HHf($$f(DAVf(fAUIIATUSH D~ Dف D$f(fAT$,$fAT\,NE1f/f(fW=K YAf(d$1f(XH D fD(D6 fLnf(AXf(fD(DYYYDYAXDXf.E9@ǃ@JfA(^f.z f/1fA(\^fAT=UfD/fE(fE(fETfD/-Y fD(>fD(f(f(fA(fA/9fD.H fHn$\ fHnA>- DD$f(XX f(f(\ YA\AYf/\f(A^wυt#f/rfATfDTfA/v Xt f(AH []A\A]A^fD=UfA(fATf/ K w!fD(f(f(fA(:f.H  fHnH E fLnAYAYf(fA(AYfD(f(AYDH$fHn\~ $A P f(fATf/AUAf(XfD(11Ҿ|$H=# Dl$豽AuDl$H~ |$D~ > 4$ffD.fLnH$fA(fHnC~ H$H} ^fDAV1SH(-} D%~ L$Y ~ = DY$D~ D~ fH~fI~f(=} f(fD(f(D- fD(DYfA(\^f(f(XfE/XXfE(fAWfD(DYXE\fE(DYXE^fD(DYDYf(AYXfA(A\fE(DYA^AYfD(DYAXfD(D^fETfE/RfE/fH~fI~fE(FD$$ e fDY%P| t$DX% f(DYYA\^f.w]Q<$H|$Ht$f(fInfHnYD$YL$\Y$H([A^f.fE/bf(T$!T$$@AUf(ATUSHfT} | f. ff.Of/f(wfW%~ f(H|$p\$L$T$$$D$p$$f( T$L$\$YXk Y\g YXc YX_ !HcHiVUUUH )׍ )Ѓ,u Y- D\$L$T$$$$$T$f(L$\$Yf(^f(\5 Y\f(Y^f(\Y\f(f(\f(^fT%| f(%* f/@ ^-y f(f(Y\f.f/@f.f(Qt$f(X\$(T$ |$^Pf(\L$Y y f( $Y $HXy |$T$ D$\$(fHnf(|$@f(H-. ^\$H$fD(|$fDT { DD$8$D$ f(T$0Yf(4$ht$HL$hHT$`D$(Ht$XH|$PYf(|$@HT$pHx \$ fHnHD$pfHn1^f(f(YL LYX ^D$x Y\ YX ^$ YX Y\ YX ^f(YY$ Y\ YX Y\ YX ^Y$ YX Y\} YXy Y\u YXq ^f($` Y\\ YXX Y\T T$0Dv DD$8fD(YfE(X0 Y\, YX( ^Y\$H\$fD($ YX Y\ YX Y\ YX Y\ YX ^$DHQf(5 YbXfD( Af(tf*Y u T$f(f(YAYY AXϨ Y%e YYbAYXfD(pf(̓ Y e f(YYJAYAXϨuf*Y%B YYbAYXfD(tJfE%! D*AYYYbAYDX% AYYYbAYDXYA1f(f(fWw ^D$ AXYf(fT v fD/vXD$fD(ѾD$ f/wHH^4$AD$Y(u fA(^f. Qf. Q$DYL$Pf(T$DL$T$YT$(f(D$DL$YD$XD^^AXY$Hĸ[]A\A]D  X˅R Do fET$D*EYf(DYZYDX G AYYYJAYAX˃tw* AYYYRAYX  YYJAYXʃt9 YYRAYX AYYYJAYXYf(fTt fD/fD(fD(DXɅ$f.y D:DZfA(XèfEf(D*DY ( RAYDXYXf(AtfA(Y AYAYD|$f(fA(AYAXtD DzEYDYEYAXfD(ݨtfE(DY DPADYAYDYRDX%z AYYYXfA(uf(Y%v YAYDYfA(AXD4 DzADYEYDX 1 YAYY  YYJXAXD EYDYAYEYfA(XfA(McAfD(E)BYTE)McF\pEAAYAYXt fED*GY Y\: Y\6 YX2 Ð=I f.f.Ef/tf.-nI f.Eքts f/r f/[ YXW YXS YXO fD Y\ Y\ YXYXf. H f.-@t9 Y\ YX Y\ YX f.-A A@f.AEt2@t-h YXd YX` YX\ f. ۰ AAEȄt=t9> Y\: YX6 Y\2 YX. Ät1t-% YX! Y\ YX f.  AAE@t=t9 YX YX Y\ YX @t1t- YX Y\ YXܽ f. E΄t=t9 Y\ YX Y\ YX Ä Y\ YX Y\ YX fD,f(f*f.zZuXf/>  0 v9 > \,҃~$ff*Y9uf(-P> f(fT%L@ f/,̅Qf(ݸf.ff(*ȃ\Y9uff(*\H ~ H@YHHX@H9uYf/f(^@Yff/.Hf(Y{A L$$軏$L$Yf( XA HY^f(f(f(Ff(-fAWfD(f(f(AVAUATUSHHx%= D~ > $\fAT,DmDef(f(Ը@f*YD9A9u,ff(fATfE*f.z u fD/ D,fA*f.AfA(¸@fEfD(D*؃E^AXA9u\ fI~fD/H|$h? Ht$`DT$@Dd$8YT$0\$(|$ L$l$t$"t$fInH; ? YD$`fLn^D$hDT$@Dd$8D^T$0\$(fHn|$ L$AX\fI~l$f.f/E E AfD(ĸff(*ȃ\DYD9uf(\H  H@DYHHX@H9uYf/f(^vAYfD/ -) fI~ $f*fA/f(DT$@\\$0|$ t$(f(d$PDd$8T$wfA*D$ : KT$fYT$Dd$8*Dd$^D$fA(|$ \$0t$(H9 ^Dd$D~ ; DT$@t$fHnY\$ DD$f(fInfA(f(fA(Ҹ=v f(fɍ(fD(*AX\Yf*AY^Xf(f(fATf(_f(f(]Y f(f(A\fATf/tf(DT$Ht$@Dd$8D\$0T$(\$\$DT$HT$(t$@f(fA.D\$0Dd$8D~ : fA/fATɸfA(DT$@,t$8D\$0T$(Dd$)ЉT$(H&8 Dd$D\$0Yt$8D~ : fHnDT$@T$( ,$fA(fA/fD/$,ff(*Ѓ^\A9u$fInD}fMnfE(D7 X-d fA/DAXl$f(<f(fA(ڸXfDf*f(fD(XDX\E\YD^A\9uȅfA(fff(*^X9ufX\$A*XT$D\\YfA*AY^YXf(fATf(A]A_fD(f(A\fD(t ^fATf/aL$fD(DAfA/f(fA(ڸ\f*Ѓf(X\Yf(^X9~fA(¸ff(*^X9uf(A9{5 fEX,D*fA.f(\L5 ,ЅfE(¸ffD(*X\D^EX9uEXD\t D\۳ fM~fA(!fDfA(Dl$0L$Dd$D$ D$Dl$0H4 Dd$f(fE.L$D~ 6 fHnfE/fATA,A)D9#~D#fA(څtUl$Pf(f()fTf*X\Yf*^AYX؃uXL$(YL$Y\$ fA.f(XfA/fA.1fA/YfD/vA)DA1A)D)#Hxf([]A\A]A^A_f(DT$HXT$@\$8|$ f(t$0d$Dd$(l$fA*D$)3 Tl$Dd$(fI~f(fA(4|$ T$@fInH2 \$8^\$\$ YDT$HD~ 4 Dd$(fHn^f(Yt$t$0t$PX-! fI~fA/fInf(\,Ѓf(f*Y9ufD/f(ܸ\ff(*ЃX\Yf(^XA9uSfDTDT$fA(\$L$$$L$,\$DT$f(DT$Ht$@Dd$8D\$0L$(T$DžL$(DT$HD~ q3 t$@\Dd$8D\$0T$f(DT$fATT$\$ $hT$\$D,DT$ $D~ 3 "fA(DT$0Dd$T$ $T$H0 DT$0Dd$\ $fHnD~ 2 f(\ff(*Ѓ^\f(X\Yf(^XD9u f/\fE(,Ѕ~*1fDffD(*XD^EX9ufED*DXf(fD(-l fI~fI~Af(DT$0Y3 Dd$(T$ \$|$t$ށt$|$- \$YT$ Dd$(DT$0fI~Y=S3 ^fD(fE(fA(fD(DT$XAYt$PDd$HT$@\$8DD$0D^fA(|$(L$ l$D|$D\$裁D|$D5. D\$DD$0E^H. DT$Xt$PDd$HT$@\$8fHn|$(L$ l$A\fD(H AY\S AYXN AY\I AYXD AY\? AYX: AY\ AYAXA\fI~fD(f(f(A4fA() fI~{ fI~fD(f(f(D,AWfD(fD(AVfD\f(AUfD(ATIU*fA(HSHfA.D:- L$AXt$ffA/$AL$f,*f.t$c]4$f/D$~. A - AYfT^f/- Af/s E1f/]f/ i v f/}f/v fD/LA,fDŽ$fD. $*øEfA.E!fA.V1fA/fEEfE/t EfA(H$fA(f(A$f($EHĘf([]A\A]A^A_fD1fE1$bfE/-tfA(H$fA(f(A$f(xD5+ fA/AfAXfD.DCfE/x+ AXfD.DCXDfA(T$wDt$h|$xDD$@DL$ DL$ D$0fA(DL$8DD$@Hc* DL$8D$ fLnfA(DD$`AXDL$@f(A\cDL$@=* D$8A\DL$Hf(9DL$H=- D$@AYf(&|%- |$ Y|$8H) ^DL$HfHnA\L$8f(d$X^|$xf(|$ \$P觀d$X\$PD$$H5a) Yd$0f(Dڢ Yd$@Dt$hfE(fLnD=B L$8|$ DD$`DL$HT$w~ + ^\=fD(ffA(*XA\YfA(XA\Y^fA(XYf(XY^Yf(Y\Xf(fTf(A_fD(f(A]AYfD(f(A\fTf/LfA(ĈT$XDt$PD\$Ht$@|$8DD$ DL$0V|$D\$H|$8t$@f(fD.H' DL$0DD$ Dt$PT$X~) fLn fD/f(f(,$f/O A$\,ȃEyDL$DŽ$fA.z8u6 $fA/r*t$f.t$fA(fT,zFuDf/L$s.:L$f.L$ $f/L$t$fT,օ:~ ) fA(fA(¸ffA(fW*؃XA\YfA(XYY^X9ufAWf(4$}4$A$Yff(\fA(fA(~ 9) D=0 AXA\fWYD$^fD(fDT@fA/fD(s\fE/wUXtIffA(fW*XA\YfA(XYY^f(fTڃfD(ffA(d$0L$)L$ DL$DD$<$t$8yf(L$ <$~K' DD$fTfAWf(,‰$G|d$0$A$YUL$<$f(DD$DL$9H$ fLnA$t$8$@fA(ÈT$ DL$XDD$P|$Ht$@L$8Dt$0xL$8T$ Hi$ Dt$0f(t$@|$H\DD$PDL$XfLn~;& fDfA($ fA(H$A\DL$A\|$\f(H# DL$|$$fHnA\f(z4$A$Yf(~ & fA(D,f(f(ffTx% f*f.z u f/,fHH*f. %# f(Ƹ@ff(*^X9uf(\ Y f/v[H|$8& Ht$0L$\$Y,x" \$& YD$0^^D$8L$X\f(HH h" fX,*f.zjuh\H" ,҅ D" f(Ƹff(*ЃX\^X9uX\q f(\ ՠ  P f/vb\f(,хK ! 1@ff(*X^X9uf*X f( ! f(f(f(t$(Y\$ d$T$^f(l$ tl$  =! T$Yd$t$(\ ^\$ YX Y\ YX Y\ YX Y\ Y\X\ r D X  fDAVffD(AUf(ATU,S*Hf.D\E„tf. * E„ fEfD(fE.)ޅf(ߍLX)f(˸- f(Yf*\Yf*ЃYf*^f(YX9u] f(d$D$xvD$d$AYYHĐ[]A\A]A^fED*DXDYƃ~8f(ָYf.ff(Ѓ*\DY9uf( fEYf(\fD.Q- Sf(øYf*ЃY^9uDYfE.cf/ ] 7fEf(f(-* D*fD(fD(˸D\~ ! fA(EX\5 fetcYfED*fA(X\YfA(AXYf*^f(AYX ~f(^fTf/v} fA($$DD$tDD$$$HĐ[]DYA\A]A^fA(YD8  HĐ[]A\A]A^! DL$(\$ YL$DD$t$f($&o$^ D$pf(qt$DD$L$\$ $DL$(wf(DL$(\$ L$DD$t$X̌ \$ t$H ^$L$DL$(X-" DD$XfE(fE(D$Xf(^L$@Xf(YD$H|$@fA(D$Dc\\$0YT$(DT$ DD$D\$t$f(d$8fI~,$Qn\$0DT$ DXT$Ht$f(^L$8,$D\$T$(DD$f(t$`D\DXD$l$hDD$xfA(D\$PXf(XYD$XEfEl$D$8*Y|$hAX\Y|$PXYf*^Y|$@|fA(Dff**fD(\DXYD^AXA9ufA(Dff**\Yf(^X9ufIn|$ L$l$d$$T$0DL$(ll$$Yl$Xf(fL$XL$H|$ A*\D$`d$Xf(^\- XYX^fT  f/wADL$(T$0feD$pDD$xYDY$HĐ[]A\A]A^AXÐfA(f(f(X\^d$@fD.}f(QɅEkf(Df*YY9u{- f(f(DT$@)fYf*f(X\\Yf(Yf*^f(AYXuD$pfWV fEDL$0D*\$(Yf(l$ DD$t$D\$A^Y$fXN \$(t$  ^ $D\$DD$Xl$ DL$0Xf(^XD$Hf(fE(ѸYfDff**f(\XY^DX9uWf(D$pfWG DL$ \$YDD$t$$f(wX_ \$t$  ^ $- DD$fD(XDL$ Xf(^XD$H fED$pfW DL$(D*\$ DD$t$A^D\$$f(X \$ t$DL$(-! D\$f(f(fE(DD$X Y^$Xf(^XD$Hf(DL$0\$(L$ t$DD$DT$<$ l\$(<$L$ DL$0f(t$DD$DT$DL$ \$t$DD$kDL$ \$t$DD$f(IfAVAAAUf(N ATUSGD- fEAfA(fA(9f(fW% fA(ЉYfDf*XXY\Xf(^9uAE@!AAA!A@AAA!A@fX-\ *XYAAA!Xf(fD(DYAXAX\fD(9~- <ZfEAD- fA(fA(9fA(AAfA(\X~- fD(fDWDYfA(^A9?D[Df*X\\Y\XfA(^D9ufEAD*AA!EXDXEYAXX% Y\fD(9.fA(AyAfA(\XfWYfD(D^A9dD[DDf*ƃX\\Y\AXfD(D^D9u fE5 AD-B fA(SED5N % DYf(\XDYD^D\fE% A~- D*AYA!EXDXEYEXEXD\fD(׉fA(fDWDYff*ƃXXY\XfA(^9A@XE8\fE(D~%? AXEYnD5 sAXfD(fDW' f(\fA(f(ă\fA(^\f(^\9fE(fA(DYfDf*XXY\XfA(^9uA@XEb\fE(AXfA(DXf(D\^\fATfD/fE.wf(fD(D9kfA(f(DAAAfA(\\fE(DYfE(D^A9XDDf*X\\Y\AXfE(D^9uEt>D5 * fE(DY\XDYfA(^\  EXfE(A \.fA(\XfDfD( DX\DYD^AXfDfA("[f(]A\A]A^EtP DM YfA(\XYf(^A\fE(Et%XfD(HEXfE(f-; Af(*AYfD(DXDXEYA \~- AXfD(EXD\AfA(\\Au7fA(\\f(%U X\Y^XAuP. \D f(XD\Y^AXvAuJ \fA(UfE(fE(fA(! fA(fA(HAVfAf(AU*ATUSH` 5 f(Yf/r@ff($*>$ff.f/H`[]A\A]A^ÉfED*fA/wf(fA(f(\$ \\\f/Y^w| f(f(D fA(^Xfl$\= DT$ADYT$H<$D^,f(DkA*^fA(D\$@d$b%0} DT$D@ l$YfE( i fA(E\\G} Y$DT$0Yl$(DL$XA^D$f( [| YXf(L$fA(d$8!bl$(% f(D\$@T$HYl$PDT$0\$ Y | H T$@\$(f(d$8DT$8YfA(YYd$XX |$Hf(YAXDL ^D$YfHnDYD^$D\$ XfA(YAXd$0FaY{ DL$XH l$PfHnf(f(A^<$aD\$ E4$f(\$(DT$8fA(d$0T$@YY { Yt$f(|$HYX^D$DXX YAXYDXDl$fD(f(f(f(l$YD$AAYXDT$l$\fA(\YXf(\^f($DT$f(fA(A9seff($*p$f. E„t$At(f(Df(H`[]A\A]A^@Af/ f(Ⱦf(f(D$D> ^f,DcA*^L$f(A\Yf(L$(軶D$DD$ fA(DT$虶$EmDfL$(\$ EV De*H D~- DiDT$4$AfED% EFnfLnXD$fA(f(\DT$Yf(D\T$Y\fE(fDW=G EY\f(AYX^׃A`fA(fA(AA9gDfA(f*؃XXY\XfA(^9|ԃNfA(\AXfA(߃D^Df*X\\Y\XfA(^9uD\$-Q DXYEYAXX\fD(A9DfA(f*ƃXXY\XfA(^9uԃ!fA(\A\fA(D^f*ƃX\\Y\XfA(^9uAXDf(X\@f(fA(\D^A\^f(\9RfA(f*ЃXXY\XfA(^9uԃfA(\A\fA(D^f*ЃX\\Y\XfA(^9uf(AXXfA(\^\fATfD/fA.f(fD(D9tyf(f( \OffA(\AX:DfA(% AX\AY^X fA(yAL$$A9G$f(:upDfA(fA(A9AH fA(AfHnA9sfA(fA( AX\AY^XfA(fA(A9fA(AufA(\A\m% \S \fA(\AXfA(%m AX\AY^XfA(fA(fA(AvffA(fA(fA(Sf(H0f.' D$(- f/l$(^ff/f/ L$(fW  f(1$L$X$~- L$f()l$X d$ L$f($Xd$ $f(=q L$X^fT\$f/~-9s f/sf(\$(\) HJ6 YH  HP`^fHnX Y\f^|$(5 q f(XYf(Y^X^fT\$f/$X ^HXX f(YH9uf.~-x H f(f(fT)l$f(f.v3H,f-< fUH*f(fT\f(fVf. l$(d$f(f(fTf.v3H,f= fUH*f(fT\f(fVl$(f.z f/1ҾH=\_ 1>% H0f([f.W%J H0[f(=P \|$(f($f(`V$L$(\ % % X H0[^^XYf(1ҾH=^ 1->% <@ f(fT f.sf.z f/ v6D f/w f/r v(HX\o HfX f(|}  } YYYXh} X p} YYX X `} YYX h \^Xf.ATfD(USH@ f.D$0 D$8zbfD.fD(zVfEfD(fE/wdfE.úEfE.E„tUtQ1ҾH=1] 1<f(c )D$0D$0L$8H@[]A\f.fDW G DfE/wfA(fA(DL$DT$D$[D$ 0p fEDT$DL$f/[fA(AXf/G o 1f/@f. n lmGf/5o fA/f/p 2 f/m f/%nn fE/{-cn Ld$0fE/ظf(f(f(fA(LAfA()n DFHn fA(D$fHnD~3D$fEۅ1ҾH=`[ 1D$:D$fEۃ@1fE/~c fA(-m HL$0fA(%bm fTfATil D$Y Kn f/fA(fA("wD$fEۅ7ujf.1ҾH=Z 1D$:D$fEf(` )D$0fE/C;~a )D$0)1Ҿ@{D$fEdfE/ؾFxk EHM D$E11DD$H=Y G9AD$fEuf(` )D$0JAD$<@-k Ld$0fA(LD$fA(fA(GD$fEۅ@Ld$0fA(º-k %yk j LfA(fA(D$l$(d$ \$DL$DD$自D$fEۅDD$DL$)\$d$ l$(fE/ Y \$ DD$DT$DL$$JK$fW fE%j DL$YDT$DD$\$ f/bfE/Of.Hf.f(ff/f(fT f/ f(Rx *x YXYXx YX2x YXx YX"x YXw YXx YXx YY x X^Hff(gf(3 H\f~8 fWf(~# HfWf.1ҾH=V 1;6 냐Hf.ff(f/wd5 f/fW Jw Yf/11 $H=EV 5 $ff/wPf(Hff/H ~` f(fWYv f/v,1ҾH=U 1k5s HfDf(L$$O$L$ff( f/f(k+w Yv Xv XYYXv Xw YYXv Xv YYXv Xv YYXv Xv YXv Yf/^v \f(f.f/}H@fT f/ff(Bu Zu YYXX.u YYX>u Xu YYX.u Xu YYXu Xu YYXu ^\Hf(D%Pu Yu Xu XYYXt X%,u YYXt X%u YYXt X% u YYXt X%t YYXt X%t YYXt X%t YYXt Xt Tf(4$4$f(\f(G~o 5O f(fWf.1ҾH=R 1{2# f.@Sf(f(A\^ƹ1H0D H\$hHDD$`H^AfED$fA(fA/fD/= ~ fA(Di %b |$f(AYfD.QYDL$@)\$0DT$d$ t$Pl$MDT$1H DL$@H5 l$AYt$PD Hd$ f(\$0fLnfA(D$fHڸ3fYXfTf(fTYf/w-HHHt9}BYfAYf(fTfA/w4Xf(fTYf/wD^HH9t fD([D$DL$P|$Yt$YYJt$Y$Y5 DL$P|$YfD.Q^D$H0[X~ f(D fTfD/fD(fA(%` fDW fDHH=t0AYfH*f(^XfTf(fTYf/v=l |$Y6 fD.-f($QY=  fE<$!f(bq AXf/f/ Eq -mq f(Y= YXX%q |$YYX-?q Xq YYYX-+q Xp f(YYX-q Xp YYX-q Xp YYX-p Xp Y^YXX\%_ ~ f(D fTfD/fD(fA(Ѹ~= %^ fDWHH=t0AYfH*f(^XfTf(fTYf/v- l$YN fD.f(Q$f(fWYDL$0)\$ DT$Pt$L$@5! L$DT$Pf(\$ t$DL$0t$f(:o AXf/f/ o -Eo f(Y= YXXn |$YYX-o Xn YYYX-o Xn YYX-n Xn YYX-n Xn YYX-n Xn Y^YXX\~= %\ pDL$0)\$ DT$Pt$L$B?5 L$DT$Pf(\$ f(t$DL$0t$DL$@)\$0)|$ DT$Pd$t$uBDL$@f(\$0f(|$ DT$Pd$t$f(<$l$d$ H \\ffHnl$d$ f(f(|$8t$0f(f(YYYY\f(Xf.fALfW Y T$(*l$|$\$ f(YYX^^Xf(l$X|$GL$D$D$qGYZ f/D$wH\$ T$(HD$L$H[]A\Hf(f([]A\\$8T$0:f(f( fDAVATUSH8 fj  Xf(fT6 f/ =,j fW , H- fI~= L$ |$l$Yl$ E1Hi fHnl$f*f(fW l$( $>Hi  $f(fHnX% T$L$f($$>T$$$f(5W L$X^fTD f/AA~=Y f/sf(\$(\ H) YH ^fX Y\fHn^|$(5W f(XYf(Y^X^fT f/w-X ^HXXy f(YH9u@YT$fInW XfTQ fI~fT=D Yf/w dAH8fIn[]A\A^Ðf. wHf.zBf.p zu= H8[]fI~A\fInA^f. {$H8[]A\A^H8fI~[fIn]A\A^u1ҾH= 1$$~ $fWfTfVL fI~EfDH(\ ff(\f/f/<\g L$YXRg YXNg YXJg YXFg YXBg YX>g YX:g YX6g YX2g YD$f(w7L$=g f(g H YfHnX\$XYXf YXf YXf YXf YXf YXf YXf YXf YY\f(H(fDf(f(^\f(\f/f/e L$d$YXe YXe YXe YXe YXe YXe YXe YXe YXe YD$f( 6d$f=e f(e H YL$fHnX\$XYXe YX{e YXwe YXse YXoe YXke YXge YXce YY\f.Qf(YH(f(f.z]1ҾH=1B 1!W H(f(fDf.zt1ҾH=A 1L$u!L$f ofDf(L$^d$\f(wd$fL$f(f.w+Qf(Yf(\$7\$D$f(L$7l$L$ff(fHf/f(J f/vTf(fT @ f. ^$$ff(f.Q^f(H@f/(Q wnf.1ҾH=@ 1  1ҾH={@ 1 HfDf(H 8c f($YX +c YX 'c YX #c YX c YX c YX c YX c YX c YX c YL$2$L$f(b X 5c YXb YXb YXb YXb YXb YXb YXb YXb YXb Yf(XA HY\@f(1  Yb \!$f(d5 $f(fDf(fD(YYf/Ob vf(fW fA/AWAVSH*b f/fD/_b fA(Y D f( $\A^f.t$D$$$fA(f(d$ l$D$ D\$HD~/ DL$@X\$`f(X^ D$(XA^f(f(|$0\\fI~fATfATf(6|$0D~ f(f(\\$ f(fI~fAT6|$0DZa D~ L$(DYf(DL$@D\$HfATfD/fEl$1d$ D$$\$`fE(5N efD.f(QfD.fD(EQfD.8f(QDYf(ƒAYYDYXfA(DYAXXXXXYYYYY^f(XXA^DXf(fATfD/vf(fATfD/- f*fInfInD$^fD.^^^f(XYf(Yf(\~% fWf(-_ Yf(^2L D\f(^AXfD(DYD^ AYAXY^5w_ \DYQt$(D^D$fD.=L f(\D$ \t$^^^^f(fD(AYXDYY5c fWA^fA(YfD(DYYDY\5L A\YYfD(EYYD^f(^^ Y^5^ ^f(YE\DXfA(\DYAXAYDYYYAYAY^-]^ \AY^%\^ \XYT$^^>QDYL$Hİ[A^A_EY^D\fA(A\f/ ] L$`D\$ 0, D D\$ f( $L$^DL$(f(A^^fA(l$\$0{.D,$\$0L$DL$(D^f(\d$fA(^f.l$ E„f.E„D\$ff.D^DX$@l$fD(EQHİfA(A^[A^A_fA(f(YY^/J ^ wU AY^J \\AYAXf. ~% f(fWMQD$fA(H$)d$H$L$ D$- D$$L$ fA/f(d$$fD/ EYz[ 5B AY\m[ AYAYXc[ AY\^[ AYXY[ AY\T[ AYEYXJ[ DY $fD(AXt$ f(DX)d$0Y* L$(YD$l$$A^ *l$$L$(f(f(d$0^fD(D^DXZ D\DYYR D^D^fA(D AXfWDYD^D\\$ DXD$Hİ[A^A_AYf.KDX\$fD(ff(D$AY1@h f(\$fD(t$ fA(fE$fE(f(L$xD$D$\$pl$hDt$PDl$`Dd$HDD$@d$04,H}G D$L$x\$pf(D$l$hfHnDt$PDl$`D~ Dd$HDD$@d$0rf(\$xD$D$$d$pDt$hDl$PDd$`DD$HT$@l$0t+HF D$D$\$xfD($d$pfHnDt$hDl$PD~ Dd$`DD$HT$@l$0f(d$xD$D$$$Dt$pDl$hDd$PDD$`D|$HT$@\$0*HE D$D$d$xf($Dt$pfHn$Dl$hD~ Dd$PDD$`D|$HT$@\$0D$ D$*D$fD(f(DL$pDl$h)d$P\$`L$HDt$@D\$0)HIW DL$pf(d$P\$`f(Dl$hL$HfHnDt$@D\$0)d$L$ D$w)f(d$L$ D$D$f(DL$(Dt$ D\$$7)DL$($Dt$ D\$f(@f.zrf/ f(f( v~%  f(fTf.wf(fTf.wff.z*u(f(fW` f(@ AVf(f(ATUSHh5 ^fC f(fTf.4 \ D$fTT$\$+f. \$T$zu= X|$|$B YD$ff(\f/-| \f/f/-f T$ \$tS l$YXjS YXfS YXbS YX^S YXZS YXVS YXRS YXNS YXJS YfH~f(#l$fHnX5 f(fS \$f.T$ YX S YXS YXS YXR YXR YXR YXR YXR YXR YY\t$PDf/- T f/1-S  T f(f(YfW |$YX-S Yf(^%T X S X%S Y|$PY\-S Y\ S Y\%S Y|$X-S YX S YY\-sS YYYXYXf(^ K X S ^o@ YYXYXYYXÃufW XD$Hh[]A\A^fH,f= fUH*f(fT\fVf(f.f( {ffWx fD H @ l$^\l$f\$T$ f(f.Df(f(QYf.D$Pf(f(d$Yd$Pd$Df(T$(l$ \$"l$ f\$T$(~% D$f.f(f(Q= f(fTf/v"Y I ^f(fTf/ff.QfTE1H HD$f/B= fHn= l$X|$@|$HX= Y^> XA^|$D,f(ff(Y\Y z f.|QfI~Xf(L$0YO \$ T$(L$0T$(~%B \$ Y^XD$D$fTf/ T< fInf(L$\$8^t$0T$(Y|$Hf(L$ "\$8DD$@l$L$ Xf~% T$(A*Yt$0AYX \f(fTf/ O f(t$0T$(\$ 4 D$ "\$ 5 f(T$(f(\ O ^D$@fTf.t$0v;H,f= H*f(fT=XO \fUfVf(D,fD1ҾH=}* 1T$ l$\$ % \$l$T$ d$P[@l$Xf(T$(d$P^D$d$ !T$(|$Y|$Pf(fA*YD$@|$Xf*Y^YD$ XD$d$Yd$Ud$Yd$:f(T$ \$e \$D$f(d$D$f(L$T$ f(d$Yf(Yf(X\$P\$t$\$Yt$P\f(t$(% d$@t$8T$0\$(L$ ?t$8T$0\$(L$ fI~ND$ f(T$(\$l$T$(fL$ \$l$f(T$(\$ l$~%h T$(\$ l$f(|$f(t$(l$ \$|~%$ t$(l$ \$f(ff(fD(YYf/OK v~ f(fWfA/AVSHh;L f/fD/`K 5 f(\f.f(f(f(t$0D u ~=e XDD$(T$ l$X\$A^f(f($$\\fI~fTfTf( $$\$~= f(fD(d$D\fA(D<$fTYJ d$~= H D<$\$l$T$ fLnDD$(t$0fD(f(fTfD/D8 1fEefD.fD(EQfD.f(QfD.fD(EQfA(fA(ÃYAYAYEYXf(XXXXAYAYAYf(XXA^f(fTfD/O f*D^fD.fIn^D^^fA(XDYf(YfWs fA(DY\f(^5 \fA(^I Xf(YAY^/ XAY^ H \DYCQHhfA(^[A^f.f/ `I  $+fA(DD$5 DD$Yf(t$^fA(l$kt$l$Y $f(f(\^f.E„f.E„mff.f(fD(QHhfA(^[A^ÐfWAYAYf( ^ 5 YY^65 ^~@ XXAYAXf. ~% f(fWQ$fA(H|$XHt$PL$\$XT$P-c f(\$Y XT$Y$^\$T$~%= L$D4 ^^X \fWDYD^AX^$Hh[A^f.MDfD(FfA(f(fEf(Dl$@t$8DD$0Dd$(l$ \$D\$D|$$t$8$Ha Dl$@f(~=F DD$0fLnH3 Dd$(l$ \$D\$D|$fLnf(Dl$Ht$@DD$8Dd$0T$(\$ d$D\$D|$,$t$@,$H Dl$HfD(~= DD$8fLnH&3 Dd$0T$(\$ d$D\$fLnD|$;f(Dl$8t$0DD$(Dd$ l$T$D|$$it$0$H Dl$8fD(~= DD$(fLnH2 Dd$ l$T$D|$fLnzf(D$D$f(L$DD$L$DD$$f(4$4$f(fD(2@f.f/ 6 f(f(. v~% f(f( fTfTf.v:f.v f.rf. vf.fH~fH~HCfHn@f.wff.<ATfUSHP- \f.zFuDf/0 1ҾH=O 1A HP[]A\X = f(f(^0 f(fTf.v5H,ffUD H*f(fAT\fVf( M D$@fTT$\$l$f. l$\$T$zu5 Xt$@t$@|$@ff.f/HD$Hf1f/v fWo f/-J nff.f(Qf(T$t$\$l$ ~% \$f(f(O. t$fTT$f/v2fD(=̽ l$ DYA^fD(fDTfA/.ff.QfTE1H f/- fHn%=_ |$0@|$8X=J Y^. XA^D,f(ff(Y\Y- f.QXY ^fTf/-$- f(f(\$(^t$ T$L$f(|$8Yf(l$e\$(DL$0l$L$Xf~%| T$A*Yt$ AYXN \f(fTf/-@ f(t$ T$\$D$\$5 f(L$~% f(T$\-X@ ^D$0fTf.t$ v=H,fD H*f(fAT\=@ fUfVf(D,Off(Df(?HP[]A\5: t$0f(T$fT$A*f(D$0YXf*Yf(^ʃufW  D$HYD$@Xuf(f(f(f(T$\$l$@\$l$D$H+ YD$@T$\f(T$l$,t$@fl$T$f(f.{f(f(L$H\0uD$f(T$\$D$Ht$(T$ L$\$l$8t$(T$ L$~%λ \$l$f(\$t$L$~% \$t$L$f(f(T$\$l$T$\$l$f(fAWfAVAUATIUHSHHf/HT$ L$@f/ 2f.(f(2 f/D$f(f/-i=  \fH f.HD$`-Q|$f.Qf(-( 1$fTn N f/%L 4 ff.\Y$gf(QX  Y^L$hfT% f/f(f(fY\Yf.$QXY^L$pfT% f/f(f(fY\Yf.$)QXY^L$xfT%a f/{f(f(fY\Yf.$QXY$^fT% f/tf(f(fY\Yf.$QXY$^fT% f/-f(f(fY\Yf.$XQXY$^fT%_ f/f(f(fY\Yf.$QXY$^fT% f/f(f(fY\Yf.$XX: Y$^fT% f/11Ҿ\$(H=g T$L$L$T$Y 9 \$(YLcL$Lt$`fDf(\$T$kCYC^*IT$\$Xf(f(YEuf(H|$XHt$PL$(T$Dl$01 T$D$XL$(\$Pf(\A$\$<T$\$% f(DD$0fTw f/%^HD$ UHD[]A\A]A^A_fDY % f(T$L$T$D$f(T$(xT$(= ^|$D$f(|$H t$T$(f(l$D$Yf(Yf(\$@\Yd$8f(l$0^Xf( ; l$0HD$ ^l$XL$HE1\$ T$(\$@d$8XXf(ED$YYD$YY\XA,$f(H|$XHt$PT$GL$XHD$ E1d$PT$f(t$Yf(f(\K$ YY5 Yf(Y\\f(YXA$f(YUY T \ D$fYY " \f. QHD$ b DYY  11H= HD$  AA$E2E- * t 1 br+ Pf(\$8T$0d$(|$L$qHR! L$|$d$(f(T$0\$8fHn D$T$L$'T$L$=f(\$0T$(d$L$H L$d$T$(f(\$0fHnSf(T$T$ff(f(\$8T$0d$(t$L$H` L$t$d$(f(T$0\$8fHnf(DD$T$8T$DD$f(\$8T$0|$(d$L$H \$8T$0|$(d$L$fHnf(\$8T$0d$(t$L$H L$t$d$(f(T$0\$8fHnf(\$8T$0d$(|$L$QH2 L$|$d$(f(T$0\$8fHnRf(\$8T$0d$(t$L$H L$t$d$(f(T$0\$8fHnf(\$8T$0d$(|$L$H~ L$|$d$(f(T$0\$8fHnf.AWAVSH`D$L$ ff.zu H`f[A^A_@ Ȯ f/pL$fT Y ȭ f/L$<H \$fɻT$fHnfXf(fD(f(t$fX [ L$Xt$ f(f fEfA(fH D*l$8fHnd$0AYDT$(AYf(XѬ d$0l$8f(\ f(DT$(f(fD(f(YDYf(Y\f(YDXfA.8l$fA(fd$ YHO |$(AYAXXDD$X\$XT$fHnfI~fI~,d$|$f(DD$fD(f(Yf(YYYf(|$(\Xf.8\ f(f(AYYf(Y\f(AYXf.f(f(t$@fInXl$8fInXDL$Pd$0t$l$ L$ D$(D$ YD$Xd$0f/D$(l$8DL$Pt$@l$~  D$fWfW`t$l$ f(f(f(YYYYf(\Xf. ff/l$t$f.E„\%]  ' f/~ V fۻ- \$)L$@ 2 f(T$ L$X f(ff(*f(|$@\$fWfW|$f(Yf(Y^f(f(YYY\Xf.Yt$ l$Pl$YXf(T$8Xf(\$0t$ l$L$D$(D$ YD$X\$0f/D$(T$8l$P d$\$|$t$ f(f(YY\f(f(YYXff.E„f/fT|$@fV=x f.YL$ f(t$@D$d$0L$l$(fW|$fWf(t$@l$(d$0|$fWf(\ \X\f(\D$ Lf.VD$L$d$ l$yfWD$@\K l$d$ X\H`f([A^A_fA(f(t$ DL$.t$ DL$f(f( \$T$fA(f(DD$0DL$ t$DD$0|$(DL$ t$f(f(sL$(f(f(t$8DT$0t$8DT$0\$(f(fD(f(L$f(D$l$0d$(Yl$0d$(f(f(#L$\$f(T$%f(f(f(D$L$ f(L$\$f(|$(T$|$(f(f(fDATUHSHH L$L$P$D$X|$XU l$Pf(f(f(Yf(YYYYYf(f(,$\Xd$0f.L$8d$ |$0\$8f(f(YYYf(f(\Xf.T$D$T D$0L$8$$l$ t$t$P$$D$`fl$ f.L$ht$E„t\$Xf.DЄ \ f/ |$PD$ At$X\$H \$ $AAQjL$ fE\$HT$E*Y% L$f(AYfE(EXD\ X\$Yf(YYd$A^A^A^A^^^f(YYYY\Xf. XXl$@d$8f(f(t$0|$(:5" |$(f(\D$ d$8l$@^fTz f/t$0A fut$`3t$hsH []A\f/. F@ f/f(5 -0Z D$D$AUD$(D$@4$Df\$8T$0l$ A*d$XX $f(YYl$ d$fH~fH~f(f(\l$\d$Au |$@t$(XX|$@t$(AHT$HD$A]D$0L$8d$l$ \$PD$\ Y $fYT$XDD$D $f(f(l$d$fA(fA(fA(YYY\fA(YXf. f(f(l$@\$(f(f(f(YYYYf(\Xf.{.\$(T$@f(f(f(f(f(fD$`fuH []A\t$X|$Pf(fW f/f/c5 $$f(5 D$ At$f(t$(5B t$H5| 4$f\$A*YT$HAY נ YϠ f(\T$\$$YYT$YY%|$(X|$(|$ X|$ Aut$X\$P-ˣ f(YYf(|$@Yf(l$HYYYf(\Xf.D$f4$\$f(f(  T$$YYD YYT$YY95   fD( $ \$D$YAYf(5 YYT$YY5O $ fD(: L$P\$D$YAYf(5 YYT$YYt5 $ fD(מ L$X\$D$YAYf(5 YYT$YY5 fD(L$xYf(5$ De D\$p n$ \$EYT$YAYYYf(5{ D- fD( $\$EYT$D$Y u$ YAYYYf(C5[ D fD( $\$EYT$D$Y $ YAYYYf(5{ D J fD(= $\$EYT$D$Y $ YAYYYf(s5#% D $f(͜ DYY l $\$T$YAYYYf( 5=% D | fD(o $\$EYT$D$Y $ YAYYYf(5U% D  fD( $\$EYT$D$Y $ YAYYYf(=5  $fD( D$AYY $ f(YY\$fD(T$DYYfA($D$D$f(D$f(AXAXAXXD$pX$X$X$X$D$\$hD$D$D$AXD$$$AXAXXT$X$XT$PXT$XXT$xX$X$X$AXDXf(YAXXf(Xt$`f(YYY\Xf.GD$0L$8d$<$|$(t$ f(f(d$f(f(YYYY\f(<$Xf.\\\$HT$@$$XXf/|$Xvf/sat$Pf/v.f/t$Xr&5 $$5Ș $$f/|$Xv5A $$L$D$t$0|$(t$0|$(f(f(5\$8T$0$$l$ f(f(t$bl$ t$$$D$L$`f(f($$l$t$"l$t$$$D$0L$8fA(fA(f(l$f($$l$$$L$ D$(d$<$"\$hT$`f(f(\$HT$@f(L$Ptf(f(RAWAVATUHSHHL$XD$`Jl$` |$Xf(f(f(Yf(YYYYYf(f(\Xt$@f.L$8q \$8t$@f(f(YYYf(f(\X|$f.D$Y D$@L$8d$\$Xfd$D$hf.L$pE„tf(l$`f.DЄL f/\$8t$@l$X|$`f(Yf(YYYf(\Xf. X AHD$(^\$^ \$P \$ f(f(DAAQD$(fE\$PT$ E*D$Y5 L$AYfE(EXDXX\ YYYt$f(A^A^A^A^^^f(YYYY\Xf.1 XXd$Ht$@f(f(|$8l$0=! l$0f(\L$(t$@fT d$Hf/|$8A fD$hf;EH[]A\A^A_f.f/0 f/5 f-J AUd$d$d$0d$Ht$@f\$8T$@l$(A*d$ XXL$f(YY,l$(d$ fH~fH~f(f(\l$\d$At t$H|$0XXt$H|$0AHT$HD$A\\$X fl$ d$YYT$`\$hl$pf(f(d$f(f(YYYY\f(Xl$f. f(f(4t$H\$0f(f(f(YYYYf(\Xf. \$0T$Hf(Qf(f(@ff(l$`|$Xf(fW f/f/ =d E1fI~t \ fHD$(A\$ D$ D$0\$Pf\$A*YT$PAY Y f(\T$ \d$YYT$YY|$0X|$0|$(X|$(Au ֐ G \$T$- % m L$H\$YD$Yf(Yf(- YT$YYH-  fD( L$P\$D$YAYf(- YYT$YY-] - fD(H L$x\$D$YAYf(- YYT$YY- J $fD(܏ D$YAYf(- \$YYT$YY-  fD( $\$D$YAYf(- YYT$YY-. & fD(\$$D$Y  AYf(- YYT$YYf(L-Ď  fD(\$$D$Y  AYf(- YYT$YYf(-Z R fD(\$$D$Y AYf(-O YYT$YYf(x-  fD(\$$D$Y 6 AYf(-e YYT$YYf(- ~ fD(\$$D$Y L AYf(-{ YYT$YYf(-  $fD( D$AYY [ f(YY\$f(T$YYf(6D$D$D$f(D$D$XD$ D$D$AXAXAXAXAXX$X$D$D$\$X$%t $DX$f(EXEXDXfXT$HXT$PXT$xX$X$X$X$X$XXXt$`f(f(YXYYYYY\Xf.fA(f(d$|$l$h|$pd$f(fD(f(YYDYYf(X|$D\fD.wD$@L$8t$ DD$d$|$ |$0l$(f(d$DD$f(f(t$ YYYY\X|$f.XAXf(f(f(fInfIn\\ff/|$`vf/sp|$Xf/vf/|$`rG=Ή E1fI~5Y E1fI~f/|$`v= E1fI~' E1fI~r E1fI~L$D$l$8|$0l$8|$0f(f(L$XD$`d$Pd$D$@L$8a\$8f(f(d$f(d$D$L$sL$8D$@f(\$Xf(f(\$pT$hf(f(d$l$d$l$f(D$0L$(t$ DD$d$|$f(D$hf(L$p[d$|$fD(f(ZL$XD$`f(f(l$ DD$d$|$l$ DD$d$|$f(f(f~=X f(fD(f(  fDTfA.vH,ff(fUH*fVf.zuf f/fD(f(f(fDTfA.f.zufΆ f/fD(f(f(fDTfA.f.zuff/afD(f(f(fDTfA.f.zuff/.AVf(SfTHxf/-/ d$0 + f/ fD(d HHn D^fD(Hf(l$(AYfD/H4XH AHAYfUXAYAYXH AYXHAYXH AYXHAYXH AYXHAYXAYXAYXAYXBH* HJHFHf/5 X"H4H HAYX&AYX!H AYX"HAYX!H AYX"HAYX!H AYX"HAYX!AYX"AYX$AYX$B^%< d$D$f(X\j D$f(H5 H=d \$X\T$PL$@l$Hf(fH~f(t$8Y- D$ f(YYD$ t$Y< T$Pf/߃ ~= \$Xl$HL$@^ t$t$8\XD$fI~ct$Xf(H5 H= \\$`l$PL$Hf(T$@t$ MT$@5O D$8Yf(YD$8T$@Y8; \$`YD$f/ ~= t$Xl$PL$HD$8 \XD$D$\H5[ T$hH=΢ t$`l$Xf(\$PL$@荪\$P= D$HYf(YD$H\$PYx: ~=p YD$8T$ht$`l$XD$82 \XD$D$DH,ffUH*fVf.,?H,ffUH*fVf.?JH,ffUH*fVf.JU t$8H5 H= \$Hf(T$@\L$ l$f(t$(El$D$f(l$Y=7 f(~YD$L$ Y*9 l$f(=9 \$HT$@|$^ \X~= D$t$t$8f/5 TH5C f(H= L$H\$@fH~T$8l$ vYD$T$8f/j l$ \$@L$HD$D$X\@ fI~f(H5Ÿ H=; L$P\$Hl$@T$ l$T$ \$Hf/ ^D$L$PX\ D$l$8l$@f(H5E H= T$Pl$H\$@臧l$8\$@T$P^D$X\g D$l$8l$HL$0f(fTf/fHn\D$(f(% \  DL$\$Xd$`DYfD(T$PDYl$HfDTfE/v f/BfIn^D$YD$8d$`~=΀ \$XT$Pl$HD$0t$(\t$ d$H\~ \$8f(Yf(T$YfTf/v f/4D$l$ ^D$uYD$0T$(\T$@\$8\~ ~=- d$Hl$ D$f(f(YfTD$Yf/v f/1D$^D$YD$Hx[A^fD$(\D$ f(\$H\ } %j t$0DD$f(d$PYDYfTfD/DD$(v f/fD$^D$}YD$8DD$(t$0\$H~=< d$PD$fHn\D$ f(\ } f(YfTfD/v f/ld$0fIn^D$\$(YD$\$(~=~ d$0D$D$ \D$@f(\ | f(YfTT$Yf/v f/JD$^D$YD$Hx[A^fD( HG fD(9D^t$f(L$ L$ YYD$0T$(\T$@\$8\{ d$HYd$~=} D$f(f(YfTf/^T$f(L$L$Y<YD$&d$8^D$\$0L$(L$(YYD$d$8~=P} \$0D$L$^D$L$YYD$DL$^D$gL$YYD$8d$P~=| \$Ht$0DD$(D$fDL$0^D$L$0Y0YD$8l$HT$P\$X~=p| d$`D$0f.DAVSHf.$L$T$z7f(y f.z5u3ffH*Y z YXL$XHĸ[A^D$$f.%Cz z9u7ffH*Y z X } Y\L$Hĸ[A^XÐL$f$f.Ef.E„t,$f.-Wy E„thH$XB1 L$ y f/$$f/%x v6Vy f/v(D$-x fTz f/$L$@ffXXf(f(l$ d$l$ d$\\f(f(fһdf/=x |$@f(f(f(f(fW?{ l$ fW 1{ d$<$\$f(d$l$ f(Yf(YYY\f(Xf.(fD(T$@f(f(DX\f(\fD(DXDXXYf(Yf(Y\f(YXf.afA(fA(|$8d$0t$(l$Ql$+w d$0t$(X|$8l$ f(d$\f(\f(l$ d$f(f(\\f(f(\$(\\T$ K\$(T$ D$f(f(,YD$T$ f/D$\$(.Hĸf(f([A^Hg11H=7 蚵Hv ffHn=D @. $YYL$X v XXf(f( . Yf(\$ Yd$(Xu fWx \$ Hu D$f(fHnH- XfHnf(d$(\$ f(YYXl$f(f(u T$@f(f(f(f(d$ l$l$d$ fD(f(fD(f(f(DYf(AYAYYD\XfA. fD(\$@fE(fD(DXD\$f(D\\$fD(DXDXXAYf(f(AYAY\f(AYXf.fA(fA(d$ l$DL$X|$PDT$HDD$8t$0D\$(6DD$8DL$Xt$0|$PD\$(DT$HAXAXf(f(\\fA(fA(l$d$ f(f(\\f(f(\$8\\T$0\$(T$ t$(|$ D$f(f(YD$|$ f/D$t$(f(f(f$L$H|$H|$Ht`f$L$H*Y%s d$yd$fYX.fH* ffD * f/r$L$f(f(\%s DL$$H^ H=E 許Pr f(OL$f(H|$H|$ff/,$i$fWu ff(f(f(qY * \ * f/f(Z L$H$$$)D$pf(= )$$;H|$pfH~fI~$L$,$|$f(f(f(f(YYYY\f(Xf.fInfHn,f(f(f(f(f(f(f(DL$HDD$8l$0d$(t$ |$PDL$HDD$8l$0d$(t$ |$=$f(L$d$ l$d$ l$f(f(f(fA(fA(DL$h|$`DD$Xt$PDl$HDd$8l$0d$(D\$ DT$DL$h|$`DD$Xt$PDl$HDd$8l$0d$(D\$ DT$gfA(f(f(d$0l$(DL$ D$%d$0l$(DL$ |$fD(f(L$$>fSHH'.~f(f(d$(^|$ l$Yf(t$$`f($`fWr t$|$ $`$f(f(f(t$8Y|$0\$$h$hfWq \$d$(f($hXX $f(X$p$p\[$x$x$p\f(\fW:q $$\$$\$$$\$f(D$D$\fW p $A\l$$ D$ l$D\D$($(\$0$ $(\f(AX$8D$8D$0$ A\Xf(AXX$@$@\$H$H$@\f(XXf(f($P$P\$X$X$P\f(d$ ^\$(YL$$f($fW[o VL$|$0D$$f(f(YDD$$$fWo DD$$d$ \$(XX$fA(f(X$$A\$$\$\fWn $$\$$\$$$\f(\$D$D$$$$A\\AX$$l$fWm L$t$8\$$$\$D$$$A\Xf(XX$$\$$$\XX$$\$$f($X^D$@D$@\D$Hd$HD$@\f(X\$P\$P\\$X\$X\T$`T$P\$X\T$hl$h\$`T$P\XXf(XD$pD$p\D$xT$xD$pHĀ[\f.ff.zu ti f.h zu h SHf/w f/h v+1ҾH=.1h H[f/ v%h 1\f(f/ \ah   f(YXYX YX Y\ YX YX Y\ Y\ YX YY\} YXy Y\} ^YXYq @sg fYf. Qf(T$FT$g f(^f/f(\ Tg ^f(Y 6 X XYX YX YX YX YX YX YX YX Y\ Y\ Y\ Y\ Y\ Y\ Y^\fW~i fY  X XYX YX YXx YX YXh YX YXX YX YXH YXt YX8 YXd YXe YXT Y^ f(ֻf(f.ATIH0f.mff(f/s f/r!~h LID$A$H0A\Ð f/N&e T$ YY蓾 e D$t$=d ff( T$ Yf(fD(|$YYYD\YDY\f(A\YfD(f(XY5d YYD\e \f(AYYf(\d$\f(\$Y\$f|$d$f/f(f/]f(]f(fAD$LA$$H0A\fDf(   T$Y^|$ ^L$f(\$Y5 f(t$( f\$T$f.f(u}D$t$(XӼf=c f(f(f/f(\f/f(f(fDHb f( HGLH0A\f(T$(d$[ c D$ȹt$f=b f(d$T$(f(X|$YYXP Yd$YY* ^D$ X 4 YXYXYXf(\Y^\$Y |$\$fATfUSH`f/rf/ra f/s*1ҾH= 1a H`[]A\@f/f(rf(~=c \\fTf/V wf.{f.zu6a @uf(50a f/ f(l$L$L$l$ff(` ~5d Y)t$0X\ f.a fWf(Qf(Y 5d f(X\%B f.%` ^f(D$0fWuQYr L$ Dkd l$\$D^f(DD$\$f(t$0DD$l$X\ L$ f.O` fWf(Qf(Y 5c L$ l$\$^fA(t$蛲\$f(t$0l$L$ X\G f._ fWf(t$ QYw Dvc D^f(AXYX_ Hl$@E1fDf(\\$Hf.f/zf/pf(DL$PfA(fTf/rf(fWd$0f(A^\f/f(fTY% X% fD/fD(D\fA(fTf/f.AEĄfA.D„ f(HL$(l$ DD$t$D$L$(f=*^ D$t$f/DD$l$ ~=` \$@\f(AXY] fD(D\fA(fTf/Jf(ff/f(A]fD(wf(AXYw] f.f(AXYW] f.AEĄufD.D„v% f(^ L$Y\ l$YY%\ d$趯f52] l$d$L$Yf.Qf(L$l$t$kfD\ H\ t$l$DYL$fHnfA.EQD J\ %Z L$ DD$DYt$l$AYfA(fE(AY\% YX% DYAY\YX\ AYXAYXfA(Y蚮f~5^ l$DD$L$ fW)t$0t$Y[ f.Qf/w fA/f(AXY\[ 1ҾH=w1\$褚\$f(f(L$l$d$zL$l$d$f(IL$ l$DD$t$AL$ l$DD$t$=fA(L$l$t$HZ L$l$t$fD(fHn$L$l$t$ȰL$l$t$f(L$ l$DD$\$菰L$ l$DD$\$L$ l$t$\$TL$ l$t$\$Uf(L$l$\$L$l$f\$)fAT*UHSHHPD$0fHt$@H|$0HD$8*XgY HD$HD$@#kf(L$Yf(,$\$d$D$(T$(f(fW'\ "d$H|$$L$\$Y$YT$(XXf(XL$D$0D$0\D$@t$@D$04$*Dd$$L$\ $D$Df(T$f(fT tZ f. TX zuf(fYf/wfDeHP[]A\fXXAfUH@u H?1HĐfHnfHn]ÐfH~f(fHnfH~f(fHnf(Xd$0d$0\d$8d$8\L$@L$0d$8\L$Hd$HL$@l$0\f(XfXXd$Pd$P\d$Xd$Xl$P\f(f)d$`f(X$$$$\d$d$\\$$d$\\$t$\$$$\Xf(XX\$ \$ \\$(\$(\\$ f.f(f)d$pEf.E!f.Eʄtf.DфuIuUHt$pH|$`H$$$?fH~fH~fDuL11f/w"f/wf/wHH@HHfDHHfDATUSHu1H$HD$$L$HĐ[]A\ff(X$$\$$\$$$\$$$$\fXf(XX$$\$$$\f(f)$`f(X$$\$$\$$$\$$$$\Xf(XX$$\$$\$f(f.f)$pEf.E„tf.E„f.̺E„t%HHH$HT$H$pH$`Hf/9S ff(f(rS f/f.-!S zu}f.~5V f(f()4$yf.DЄtH$HD$1HHH$HT$f/R ~5U f()4$f\$0*f(d$(Y$Hf($HfW$Zd$(\$0$HD$f(f(f(Yl$ $P$PfW$ l$ $PXXD$f(X$X$X\$$$X\f(f)<$fDf(t$,$<,$f~5{T D$8f()4$5EQ f(t$@t$Df(f(|f(D$8f(f<}f(\Q $$\$T$@$\$$$\$$$$\Xf(XX$$\$$$\D~5PS H$xH$$p$`$hfW)4$fW |D$L$f(|$)$f(O L$f/ry)P f(2f(t$,$d,$t$ff/ f(D$8f(~=R f()<$=QO |$@fDf(\$ 豮D$(fP\$ L$D$0O X^f({\$ ft$(f(f/vl$0f(X-N \^\ff(Fzf(f(3f xN f/f.=tN d$8f.|$@z#u!~=xQ   )<$~=WQ d$8Y  1P fWN )<$f(^XM f(D$xfTf.v7H,ffUD-M H*f(fAT\fVD$x T$xf(t$Pl$HH- E1d$wfD(<$d$f(f( M f(fAWfAWyf( YYf(f(YL$hf(|$p$f($fAW$Dl$pDt$hL L $fE(EXEYDXfA(AYDXf(AX$ $ \fA($($(D$ D\AYfA(AYxfA(fA(D$0fA(L$(fA(w | L$ D$vd$|$ DT$(l$Hf(f(D\$0t$PfA(fA(At$Pl$HH|$0d$(w|$0d$(\$hT$pD$ D$`f(L$L$Xf(av]UL$0D$(FvDL$DD$ fD(l$Hf(f(fDT%LM t$PfD/%} v$Ad$(|$0DT$XD\$`f(f(fA(t$ fA(l$ wt$ l$f(f(f(f(t$0Yl$(d$ \$$0f($0fW$褝\$d$ $0f(Xf(YXf(YXXf(X$8$8\$@$@$8\f(5vl$(t$0f(f( HI fHngu,l$xD$ f(PT$ D$f(9\$l$(t$0f(^ ~=L HI f()<$=iI fHn|$@)fAWHAVAUATUSH~ff(f/r-*I f/s,H%I f(M HXHĨ[]A\A]A^A_@At@f.zu~HL ofDf.z2u0f(x H@f(g\offf(H$A*d$D$ʅH kH H$gJ f(d$f(=)I fHnfTf.v+H,ffUH*f(fT\f(fVf.fD(8 2 DI f(f(fATf.v,H,fH*f(fT\fA(fUfVf(~=J X)|$ $$\$f($D$\fWf(fAWd$04$nsA,4$H5G d$0D$fHnf.ʼnL$h  HD$EL$hA)EAAI\$h9 \$fҾf.Eքt  Df *YYf/Ao;l$h A@B~ D)ʍJ$$A  $ D$DL$PH$L$HD$Xd$0oDHL~5nI d$0$$)$@)$)t$@$DŽ$HDŽ$`d$0f(t$@$DL$PHD$XE ^$f/H E $fHn f(ff(Չf(DL$PHD$X)t$0$$$$LHH0E f(t$0fI~L$0f(fd$@fHn)$PpHDŽ$$f$*D$p$$$L$f(4$)$`pd$@DL$PDŽ$$`HD$X$hL$0fInd$P$h$`HD$@D $o\$01DfD(ffD(fInf(H$@4pfA(fA(H$$fD$`f(p$$HD$@$d$P$ED $D$$H$ADT5d$0E)E)DADL$l$DA׉T$tA׉$ARAAωT$p$H$H$H$pHT$xf.f.ڸEЄuf.EЄfT$LH*D$lft$X$̀HDŽ$$f$*D$t$D$hT$HD$Pf(L$@f*mHt$xHDŽ$$pf$x*D$p$|$Pf(t$ \$@f(fWfW n$D$@L$Hf(\$@)$`$m$f(f($h $$`f(d$@Tld$@$fD(fD(D$`$f(wmfA(fA(D$`$$$GmHA t$X$$fHn苔$B f ( YL$`)*Yf/vD;$$fHLHDŽ$HDŽ$D)*$fA*X$$@f( $Yf(\$Pd$@$(f($(fWT$ 9 $d$@H$(\$PYY$HXXf(XL$P$0$0\$8$8$04$.D$L$P\ $D$@Df(T$@f(fT uA f. U? z uf(fYf/v XXA$f)D$lAD$$)$@L$tA)ŋ$L$pD$D9$ft$LHA*HDŽ$$HDŽ$$ST$0D|H$H|$x$x$p!+t$LHD$@fD$Xf* $fL$P$HDŽ$$HDŽ$uHLT$0i$$*d$@$f(h$H$@h$D$@f(D$A.T$@D$f(LD$Xf= f(fT5z? HL$Pf(Hb= L$Pf.H$X$fHnFf.ڸEЄ,f.EЄD;$KH$d$0$f(H$$d$,zd$$L$`fH~f( zH$fHn˃$H < f(fHnfWL$ \fHD$$\$o\$fH V< $HD$f/fHn9fHn]f(ff/]f(f@f1D+L$hf.þAAEA)f.~=> ; )|$ f(Kf(ff(H$t$AwH$d$g$$%H_; t$d$fHnH$Xf(XYY\^fp(f(ff(H$t$AwH$d$xf$$$H: t$d$fHnH$Xf(XYY\^\5: ff(fH$Df(t$ d$H$fWf(e$$$H F: H$d$fHnfHn\YD$\H^@fft$ M H$9 YYXf(L$YfWD$ ^ ^f/!NH9 L$fHnH$\f(Xf(fY^ }: HU~< HD$@DH$L$HDL$0L牄$$$$DŽ$HDŽ$)$@)$$$DL$0H 8 HD$@$$fHnf(ff(Df(t$ HD$XAFDL$PfW$f($$d$$H$PH$P$X$HDŽ$HI8 $$L$0fI~ffHnf(Ov$$$f*f(1$fb7 HLH7 f(\fHnfWD$ $$X$$\$$$\$$$$\X\f(X$$\$ $ $\f)$$$H$`H$`$d$@$hHDŽ$n$$$L$f(4$)$`bHD$XDL$PD$$`d$@DŽ$$hE6 f/~59 HD$PDH$L$HDL$@L牄$)$@)$)t$0$$$DŽ$HDŽ$$$f(t$0H 5 DL$@$$HD$PfHn3fHnf(\f( 6H~5 f(t$ L$fWfHnH$Xf(AVATUSHh~*ff(f/rf/f(r=*5 f/s4@1ҾH=1ct 5 Hhf([]A\A^@f/rD~6 f(\\fATf/ wf.Ήrf.wf(,$tff(f(d$*^T$ f(l$蛋,$Ha4 d$T$ D$8fHnYf/ D !4 fD/f(d$ T$,$Ԇ,$H4 T$d$ D$0fHnff(Ǎkf(l$(d$ T$T$fH3 $f(fHnX$H3 f/D$0T$fHnHd3 d$ l$(fLnfD/f(\T$8f(l$ T$$$$$~ 96 T$l$ \$D$fW$<$[$L$f(l$0D$D$d$(,$\$\$\$ 蹋H2 D$$fHn\|$f(3Ht2 fl$0d$(\$ fD(T$fLnf/fA(XAYfA(fD/t$(\fI~w=k |$(fInLd$@d$8l$0D\l$Hf(f.D$Pf/Lf/Bf(f.TNf(f(AXAY\f/r:fD/r3fD(fInDXfATfETfA/s*- f/wDf(f(AXAYAYfD(D\fATYB X\$(fETfA/WfI~f(f(f(ÉLT$ DT$|$$H0 $fl$0|$fLnDT$D~2 fD/T$ L$@\L$8Df/f(A]fD(fW x3 ^f(\f(6f('f(fW63 l$ T$$$耏l$ T$H/ $$D$0fHnfA/qf(~ 2 f(d$(T$ fWl$) $ d$(T$ l$f( $`f(f(fۉl$ d$$)$l$ H?/ \$^f(d$fHn^f/fHnd$0\T$ $衈 $H. f(l$ T$Yf(fHnYX,$- $Xf(^f$$Y ^|$(葇l$ L$D$f(,$Y \$|$(f,$d$0fD(f/H&. f(fLnRf(]\|$8f(1ҾH=1$Im$f($l$ d$PP<$蠈ZYl$ d$$AVff(ATUSHHf.f.f. z-  f/  f/  f/ ޟ f/  f/  f/  f/  f/ | f/ r f/ h f/ ^ f/ T f/ J 1f. > f/ f/" f/ f/, f/ f/ f/iHD HHcH@D ,HC , H ً HcHfD f(HHf([]A\A^f(Af(^ m, HHf([]A\A^fDf(\$fWX. ^p+ [4\$^]+ D$f(>4T$f(* HH[]YA\A^YYYf(1)@f(\$^* L$3-* L$5* Y\X * f(t$l$ |l$f f* f.t$\$f(\YY 2* z f/fW5F- f(L$XT$YY^f(譃T$L$Y^* \F@(* f(HU@ H-? YLchd$YfI~YD$(DfInD$(}L$ YHHXv) |$YT$ YD$L9T$L$ ^XD$D$uYf~8, f(X) YX-) L$fWYl$fW\$ \|$YY( sL$l$f=( Yf/f(^5) Xf(f(\$ |$@Yf(h( Y\f*^f/f(YXrff(5,( Xp( YX-( \$0YL$T$,f(fW-+ ^|$YYl$(t$ sL$T$- t$ Yf.\$0l$^l$(Y% =}' f(fTy) f/\$8T$0L$(t$ l$l0T$0fD!' f(l$t$ f/L$(\$8AY& \A\^X~/f*ЃYf(Y\YX9' YD$d$Hd$f(^L$Y& l$0L$YYf(\$L$\$D$(fD(f(fD(L$ DY\$D^' DD$DL$8@'\$T$(L$ D$Y\$(f(T$|DD$|$f(5% l$0^ & fA(Yf/XDL$8\$(T$@ff(Ã*EYf(\^f/f(YfA(Yf*^Xrff(-% f(D~'( Yf(\$0YfAWL$YT$Y$ ^|$(t$8l$ m~L$- T$^$ Yf(l$^L$t,\$0t$8|$(l$ Hp; fYL$ L$D~e' f(^DHYXf*Y\Yf(YՃ?u# fAWd$Y}d$f(^L$Y9Wf(\$0L$(t$ l$+# YX\l$t$ fL$(\$01hTJ, xA\f( ` V L1ҾH=1L$(l$a"  " f.Df(l f/%J" R" ~5]% ~=E$ D4 f(f(ff(Ӄet^fWfY*fD(YXDXXf(f(^A^YYXf(fTf(fTAYf/v YYYÐAVSH%" ! ~=# D} f(^YY! f(f(XfTf(fTAYf/~5X$ *D 9" fWXfA(^^YYXfD(fDTf(fTAYfA/fWY% Y~ f(^YYXfD(fDTf(fTAYfA/D fWYS! fA(^A^YYXfD(fDTf(fTAYfA/?Dn fW AYfE(D^^EYAYXfD(fDTfD(fDTEYfE/fWYݥ fD(D^^EYAYXfD(fDTfD(fDTEYfE/fWY Y%5 ^YYXfD(fDTf(fTAYfA/Kå fWY% ^A^YYXfD(fDTf(fTAYfA/ fWD [ AY^A^YYXfD(fDTf(fTAYfA/ fWAY^A^YYXfD(fDTf(fTAYfA/wk fWD AY^A^YYXf(fTfTAYf/w% fWAY^^YYXD! f()t$ X\$DYL$,$DT$p,$DT$L$X HT$@fA(\$D Yf(t$ =~ Y fA(fD(D  D ^XL$@f*fD(f(DXAXfA(AYYfA(YYAYfD(XD\AYAYfD(\f(^$HHuf(  T$HYd$XDY^YfW^X^X-T YfWXd$h^fW^YfWXT$x^YfW^X$YfW^X$YfW^X$YfW^X$YfW^X$YfW^XY$XT$PYfWfH~f(\$`^DXT$pYfW^AXYfW^X$YfW^X$YfW^X$YfW^X$YfW^X$YfW^p XA^Y$XfI~ff.wLQ$H|$8Ht$0f(/pfInfHnYD$0YL$8\Y$XD$H[A^l$pl$$f(̕ f/%J R ~=M 5= f(f(f(ӃetQYf*YfD(XDXXf(f(^A^YYXf(^fTf/v YYYf(fSH  D ~5 % fA(^YYm f(f(X^fTf/ =_ Xf(^A^YYXf(^fTf/AYDV Y fA(^YYXf(^fTf/D Ҋ Y fA(^^YYXf(^fTf/PD– Y= fA(^^YYXf(^fTf/ O Y^A^YYXf(^fTf/AYD Y D^EYAYXf(^fTf/Q Y ^A^YYXf(^fTf/w_Z AYD ^A^YYXf(^fTf/w"] AY^A^YYXf(\$XL$l$il$ L$fW 0 YX \$Y. % Y^Xf(^L$ Y^XY^f( XY^X% Y^X% Y^X Y^X Y^X% Y^X% Y^XfYp XfH~ Yf.w2QD$f(ofHn^d$YD$H [Xl$ ll$D$ffH(f/  \$T$H T$fHn[o [ T$f/wf/ v%\ Y= gYD$H(D\Y ggYD$H(@ % fW T$d$]f.D~% f(f(@ fTf.s&f/ f(w ff.zufT fV{ f(SH f/ f/s5# f(f(f(fTf.af.w,ظf(\ЃDf/ vX f(\f(\$'\$f~% Yf.f*Y H [%  f/f(rfD\Yf/sf/% wJf.^Xf/v2f/vf.B YXY^tD%x - f/weD^Xf/Nf/vfDf/    T$f(^Y\ Y\ YX YX YXD$f(lT$f/ D$f(Y ' f(\ Ӄ Nif(f(^t$f(YY YD$TD1ҾH= r 15Q 'H,ffUH*fVDtff.\ YX YX YX YX YX Yf( YX Y\ YX YX Y\ YX Yf(XYX^(ff/ fTD$   \$f(^Y\ Y\ YX YX YXD$f(i\$f/e D$  f(Y\ 4gT$f(^YY YD$L$Y ^f*YD\  f(f^D$ f(\ | f(fT$^zf.fAVfI~AUAATUHSDeH L$fH*D$f(L$Of$fI*\AL$$YL$YD$X$3A$f(YD9sE%  L\D$- ^D$f(fTf.w|H,D9AG9rH f([]A\A]A^AffInL$I*^YD$XD$Y$@$L$YX9wH,f5 fUH*f(fT\fVf(H,D9AG9dH@~  f(D fTf.SHH  f/ f/5 f/ %j ff(f(fD\f(XYf/s5 f/w&?X^f(Xf/f.zu1ҾH=:m 1IL H [f(fW T$f(\$\$~  - D$T$f(f(fTf.Of.z u,ĺf(\ăDf/I vX%M f(X\$\$Yf. z^f(G \\D$f(f/  f(f(\= T$f/l~ |$s^YD$T$f/ \XS f( y Yf( ! ^Y\ YX E| ^XWH,f-' fUH*f(fT\f(fVf.z~fDf/vfW f.\ XYT$\ Y\ Y\ Y\ f(f(\ YY\ L$Y\ Y\ Y\ YfH~f(\L$\ T$f(f(YfHn\ ^X fD\T$ YD$f(f( w Y\^Y\ g YX c Y\ _ YS X S Xf(^XfD5 X f(ff/j%> ff(f(DPH f([[f.f ~= f(f5h f(2f.\f(XYf(fTf.r f.f/rf(Xf.zu5 = D~ (^Xf(fATf.r f.wf/rf(Xf.zuf.7UH0f/% vf(fT$ f/f(Xf/xf/&Hl$,f($$HT$t$$$HD$f(L$\f(Rat$T$fH $$Yf.fHnf/wmf.f~k f(fTf.  D$ f(f(fTfD.\f.z,Ǩt fW% Df.f/wff.~ f(fTf. V h= f(f(fTf.\f.z:,ƨtfW H0f(]~ f(fD(D N fTfD(fD.fA.OID f(fTfD/-f/;f.z f/ tfDf(DP5D~D~ f(fD(D  fTf(fD.v'H,ffUH*DfDTDXfDVfA.y ? fTf/cf(H,ffDUH*DfDTDXfEVfA.f(T$L$$$\L$$$H f(T$fD(f(fD(D D\ " YfHnD\AYfA(Y\f(AYY YY^f(X^f(YA\AYAYAYY % YYXXY^XY,fT%* fWf(sfT5 fWf(ff(fD(fD(fTfD.v2H,ffD(fDUH*DfDTAXfAVfD(fA.oifTfD/UYx cYh H0]f(H,ffUH*f(fT\f(fVH,ffUH*f(fT\f(fVDYYRf.fHXf. f(f(zZuXf/ wf(uUf(fW% f(HX~% fWf(a~% HXfWf(fD5` f/f(f(<$\$T$\$<$fD(fD(f(T$DYf(ff.EYfA(AYYfD(EQfA(\% f(D fD(f/ EYA^AYY5s Y DXfE(D r AYEYAX\-=} DXfA(\~ AY^n Y^օ AYXAX\ T YDYA^\Xr.f( ^\  fT f/=f/= 0  XYf/ Yf/w Yf/f(-v D@ ^Xff(*X^YfD/Xweuf(d$\$T$ |$R|$$f(RT$ H|$LD$f(T$d$\$XXT$f(\$^TYD$iR\$d$f(T$Y\\\X $^\YDf(T$|$$fT$$f(|$f(Yf/9 Yf/vf/EfW $f(^\Bo }X$f(Xf( HX^\^f(fD(EYfD/fD(HD\=vd$ T$(fHnDt$0fA(D<$Y\$LW\$H|$LD$f(\$LT$(D$f(PL$D~% l$\$fAWd$ Y ! Xf/f(\$fAWl$f(|$wPD$$HDt$0\$AYfLnD\5n fD(Hn f(l$DYD|$fA(fLnf(YfD(fD(DYDY5AYDYEYAYY fA(A^fD(DY\fA(A\D DYDX z DYDXfA(YY\ & A\X% AY^^fA(AYY2n AXD lEYAYA^fE(\\ AYfD(f(\%YA\DX%0XEYAYD~%1D^YfAWfD(D\^- AXAXAXfD(DYAXfE(DY1 \-o DYAYXf(XYA\D DYA\Y AX\> YfA(YUXf(X\ i ^ m XY^X@f/ %r f/f/vFf/ r< y \f(T$T$$YT$$Y(f/ $ f/f/C`M$=f(fW%\\$ f(d$<$)MY$d$f(d$\f(l$M\$ 3D$-l$=w\\fD(DYf(Y\f(XYYAXXAXX^L<$Y|$d$\\kL$=f(fW%\f(d$<$:LY$d$f(d$\f(L$LL$4$X 7D$)^XQ@f(\$d$|$(T$KT$H|$L$f(T$ <$d$\$X\$X<$f(^OR\$T$ f(f(f(X5\$^L$t$^XeYWL$X $\$\^f(QT$ f(^D$X"f(L$^YWL$X $\$\\$^f(QH\$f(T$ f(f(fLn^l$D$DX^T$\$A^f(X YX YVd$\$f($$X\^P|$(T$$f(Y $$^f(Y6N$f(4f(l$\$ d$I\$ d$X%D$\f(T$ ^XdIL$Y $l$\\f(L$fE(HD!r H2 D^EYHfA(DXH4fE/H AHEYDXfAUAYEYDXH EYDXHEYDXH EYDXHEYDXH EYDXHEYDXEYDXEYDXEYDXBH HJHFHXH4H HAYXAYXH AYXHAYXH AYXHAYXH AYXHAYXAYXAYXAYXBD^ f/E^Dd$v f/Bf(\\f(X^f(fTf/fD(׸fDWD <` fHH=OAYfH*f(^XfTfD(fDTEYfD/vDo fD(̸H DXq fA/(fD/q 5)q f(YYXXp YYX5q Xp YYYX5p Xp YYX5p Xp YYX5p Xp YYXp Yp X^YXX\Y Y^Xf($HYD$HHf1ҾH=N 1-fHHffA(L$(d$ |$l$@l$|$d$ L$(f(hDfA(L$(d$ l$GL$(l$d$ D$^f(f(DYD$YD$HHfA(L$(d$ l$Dl$DT$CHif~uL$(d$ fD(fHnHP l$Dl$DT$fHn8f.AVf(f(fATUSHhH fW%D$8fHnظf=tJff(*^Yf(Xf(^XfTf(fTY\ f/rf(l$@M?t$8-gYfI~f(fTjf/`ff.|$8-k H-! YfW=<|$0|$l$ f.l$Yl$0fE1*HfHnfHnf(l$fW t$(fDAX%T$AL$f($$BT$$$f(=[ L$X^fTkf/vl$ YT$^T$([ XfT?l$ fT-1Yf/w * fInHl$\\T$ Tff(\ f(fT $f/XD$8Hl$\HfIn\ %f(fTf.f.f(fW zf=qfTfUfVD$8H $uf(fIn\CYD$@ $Hh[]A\A^\f(f(< $fD$Hf.5h H-o YfW L$0L$t$ l$Yl$0fE1*HfHnfHnf(l$fW |$(fDAX%nT$AL$f($$x@T$$$f(5yY L$X^fT+f/vt$ YT$^T$(CY XfTt$ fT5Yf/*ff/w f/v7f(OB\f(fW .>fInHl$\f( g g YYYX g Xg YYX 9Xg YYX\^XfW %HD$ D$HfInHl$\XD$ \--Y f/Rf(\$(f\YH H ^fHnX {Y\^t$(=W f(XYf(Y^X^fT Qf/"X-7^HXX-#YH9u-Y f/Mf(\$(f\YHH ^fHnX Y\^t$(=V f(XYf(Y^X^fT f/X-r^HXX-^YH9uAUATUSHH=$EYL$AAf(8=$H$f(XX5;f(4$YfI~f( $f(fIn\ f/wf/ : 5zY$\ft$ $ ? $Ђ Yf.f/L$ f.L$ ~52)t$pfTf.5 Y~5)4$ft$$AA*DD$fA(YYf(XfA($f(D$&- f.~ AA#Nm fDD$hA*|$`$$\$Hf(d$@X$@$@\$H$H\$Pt$$@$H\$XD$XD$P$@HDŽ$`$`$hf($h\$p$`$h\f(A\$xf(D$xD$pD$`AXAXfD(E\XEX$$\$$$l$(\DXf(AXDT$8$$\$f($$Yd$ L$0$(f($(fW$5DT$8D\T$ l$(L$0YL$d$DY\$H$(\$ fD(f(EXDXf(AX$0$0\$8$8D$0D\f(DT$(YDL$P$f($fW$4\$ l$$d$@YYd$XXf(X$$\$ $ \l$HD$DT$(fE(D\$@E^DT$0fA(fA(Dl$8AY$fA($fW$4Dl$8DL$P$D$ fA(fA(fA(Dl$XAY\$($$fW$3\$(f(<$f(D\$@$XXL$ f(fA(X$$\$$\$\fW$P$PA\$X$X\$`$P$X\$hD$h$`$Pl$HDT$0f(\fWDT$8$p$p\$x$x\$$p$x\fA(A\$D$$$pXf(Xf(A\XX$D$D\D$$$\f(XX$$\$$D$fA(\D\$@A^d$Hf(L$(AY$0fA($0fWQ1L$(DL$P$0D$ f(fA(AY\$0$8$8fW$1\$0$8D\$@XXD$ f(fA(X$@$@\$H$H\$@\$f(<$$d$HA\fWfD(D\fW$$\$$$\$D$$$D$D$E\D\DXf(D$$\$$$\$$$D$\EXXAX$$\$$$D\AXX$ $ \$($($ DT$8Dl$X$L$(A^fA(X$$A\$$$f(\f(X$$\$$\$$$\$D$$$A\Xf(XX$$\$$$\f(X$$\$f($\$$$|$`DD$h\$f(D$D$$XA\$$AX\$f($\$$$\$$$$\f(l$pXf(Xِ X$$\$$$\f(XXf($$\f(fT$$$fT\f(YA_fD(f(f/wf.\$GAfDTD$pd$DYC $f.DXDf/|$f.E„t!f.E„tuf/$Hf([]A\A]ft$$~5H)4$~5,)t$pffDTD$pd$DYr $f.DXDz f/m$\$4$n14$Y$4$R1Y\$4$f.P~5fT)4$~5rfWf()t$pYT$p-*f(f(fTf.v3H,f5'fUH*f(fT\f(fV\f.L$z,~5)4$fWH5HI~5Y)4$~5)t$pUff(H@f/~D$8f/f(f(fTfTf/vfH~f(fHnfH~f(fHn5 f(Yf/v f/mf(5 )$XfD(fDTfD/wf/w f/ Hl$m f(T$\^fTf/H۴=k 1fHD$HfI~HD$PfHn11H= fHĐf([]A\A]A^D|$Xd$`11f(f(f(X^f($|$XH)HD$Hd$`t$hf(-|$8$=ݴHD$Pd$@ffI~l$pfHnDD$pAdE1fA(ff/EAD$AA\-Y\f/'7 "L$Hf(Af(\f(YXf.93ff.zuf(AYXf.hfA(L$@D$8l$(d$ t$|$\$$DD$0hd$ |$fInf(\$$f(t$X^fTf/w+f(DD$0\^fT}f/l$(" f/5;\f(fDtcE~FAfA(L$Pf(@w DAfA(aAD$A}EYA@=! f/vBw $DA~:AYAAXA|Jf(f(\D$HA\^Q@D$Pf(A\\^f.AYA|$X5\t$h|$@|$`|$8f(HfHD$HHD$PfHnt$t$8Xt$@L$LT$xd$ f(L$<$LfH~D$8订fHnLA\D$@fH~茢d$ fHn<$\L$T$x$$d$H|$f/t$0t$t$(?f/L$PC|$(f/PL$Pf(T$f.Hu IE„ff.D„if(L$ \$[\$5D$\f(:|$8T$@\=^f(\RD$\$Y=i YXXD$0f/f/ L$ L$L$\$f(4$f(\D$(^f(\f/r:d$f(\\f(^d$pYYXff/Yt$f/rLf(f(\$$H(t \ӽIf(^d$pYY\f/5Jf(^=s fT4f/Hs IArL$@D$8T$d$HT$f(f/$f(f\$L$P11$$H= |$ t$L$T$$$f/%xT$fL$|$ f/t$|$Xd$`5%\t$h|$@f(f(d$8t$5DD$\f(4$|HݬfHD$H$t$f(HD$PDD$fHnL$Hf($|$t$($$ |$`d$X1t$h|$@f(f(d$84|$t$(f($$Of(\$(T$ L$t$d$,$L\$(,$HJT$ L$t$fLnHԬd$fHn,f.ff.fH(f/w(f/f(wf.z@u>f/zv%f(f1ҾH= 1SH(fDf.{R~%:f(f(fTfTf.vf/@f/nNp f/f/L$f(T$ymfT$L$f.fD(6-.f(=] f(f(t"Xf(^YXf(Yf/rDYD^A\f(f%f/Yf/qf(L$T$諶fT$L$f.fD(-lf(= f(f(fVXf(^YXf(Yf/r/f.)f(Q.F ^f/j1f(H(ٵfT$L$f.~%ȪD$f(fD(fD(-D5fD(D% fD(DXfD(D\fA(AXXDYA^f(cfA(f(^fD/=\f(^fTfA(fE(fD(fE(@ f/DXDXAXfA(AYf(fD(AYEYYDY\E\f.fE(fDTSf/IfD/=hwfA(fE(fD(fE(wDf(EYfA(AYAYfE(fE(EYfD(/f(H(D$Yf(H(&TODqf(L$l$T$"L$l$T$f(f.fH(f/w0f/f(w&f.zHuFf/rw-pH(1ҾH= 1KH(fDf.{J~2%f(f(fTfTf.v,f.wf(t@f.f(f/*! \fT k ^vf/v-Ff/@f/=f/v f/f(L$\$yfHV\$f.L$fHnf(f(De f( t#Xf(^YXf(AYf/rY^ؤf.wdf(QA ^f/f(H(钱Tf(HxfHn\f(#f(L$d$\$L$d$\$f(nAVUSH`f.L$8ff(f/Ff/d$%$$wT$f/1ҾH= 1\$\$$$L$f(\$H-\f(fI~譠\$~%HE,$5Z f(f(fTf(Yf/|$0HFfUt$D$8f(\f(fTf/D$ f(\$ T$\$ T$H|$\YT$(\$f(f(\L$ L$ \$T$(\X# f/f(\$ T$1~%T$\$ fD(ffD.f.z2ff/f/f.f/A5!\D$fD-Z fX\-fD(D^Z fA.6EQL$0<$f/^" HH YHL$8XH4H YHYXHtXYXH YYXHYXH YXHYXH YXHYXH X H4H YYXXH4YYXX H YYXBXH4YX H YXH4YX H YXYX YX YX A^D^e f/DD$v f/f(=E\\ IX X 1^f(fTf/sfD(fD T fDW# HH=t1AYfH*f(^XfTf(fTAYf/vYf(T$(Y e \$ ^XJDD$~%T$(\$ DY D1ҾH=1\$(T$ DD$P\D$5DD$~%3T$ \$(,$Yf(\^A^\f(fTf.w-۞YY,$\^\ЃH`f([]A^@$5K Xf/wf/ў\$HT$@L$(l$ >l$ L$(T$@\$Hf(\fff.B5|$0f(fTf.Zf.!f(T HH1ҾH=!1$&$H`[]f(A^@$fDf(\$HT$@l$(-T$@l$(D$ f(^f(\$Hf(\$(zYD$ DD$\$(T$@~%9DYf(ff.d$f.$$Ϝ!f5`fInfD=p f(D Y5YDXX=N DYDXp YX=< YDYDXZ YX=& DYDXH YX= DYDX6 YX= DYDX, YX= YA^YXXfD5jf\D$؛H`[]f(A^f.fInf(f/ ` \fT^vkf/ve-!f/vWf(f(t$@DD$(T$ \$H\D$\$T$ DD$(~%7t$@f/f/$t$@f(f(DD$(T$ \$v f/0fT$ DD$(f.~%Μ\$t$@D$f(D fA(fA( t)AXfD(D^AYXfD(EYfD/rY^\D$(3fod$f/%U l $H`f([]\A^ff.f(Q7 ^f/^rfD D f($\QfA(\$@T$(l$ t$\$@T$(~%sl$ fD(t$f(T$Ht$@L$(DD$ \$T$Ht$@L$(DD$ f(\$f.AVUSH`f.L$8ffD(f/ef/\$$wT$f/1ҾH=1Dt$Dt$T$4$fA(Dt$H-O\f(fI~xDt$~IHE$$-N f(fA(fTf(Yf/|$0HFfUl$D$8fE(D\fA(fTf/D$f(Dt$ T$T$H|$\Dt$ AYT$(Dt$f(fA(\L$ 诉L$ Dt$T$(\ f/f(Dt$ T$~HT$Dt$ f(ff. f.z4ff/fA/fD.f/?-_=ߖ\|$@=N fA(5fX\fD(D^ N fA.] EQL$0,$f/A^ HHYHL$8XH4H YHYXHtXYXH YYXHYXH YXHYXH YXHYXH X H4H YYXXH4YYXX H YYXBXH4YX H YXH4YX H YXYX YX YX A^D^~Z fA/DL$v f/f(A\\X^f(fTf/fD(f= fDWfDHH=t0AYfH*f(^XfTf(fTYf/vAYf(T$(YY Dt$ ^X d$~[T$(Dt$ YD1ҾH=1Dt$(T$ d$h=\|$-zd$~T$ Dt$(YfA(fW=^$$\^\f(fTf.w YY $\^\׃H`f([]A^@$- Xf/wf/Dt$HT$@L$(d$ d$ L$(T$@Dt$Hf(\{ff.2-jt$0f(fTf.Bf.fInfD fA(HAf1ҾH=1$$H`[]f(A^@`$fDfA(Dt$HT$@d$(T$@d$(Dt$HD$ f(^fA(Dt$(f(%YD$ d$Dt$(T$@~Yf(ff.*- f\|$f5( =P f(Y-YXX5 YYX=( X5 YYYX= X5 YYX= X5 YYX= X5 YYX= X5 Y^YXX-2fInH`[]f(A^f.f(U fD/5 A\fTA^vnfA/vg5f/vY1f(fA(l$@d$(T$ Dt$f(Dt$\|$T$ d$(~l$@fD/U f// f/=Yl$@f(d$(T$ Dt$fD/fA(覜fDt$T$ f.d$(~sl$@'D $fE(ָ=fA(fA(t)EXfD(E^AYXfD(DYfD/rY<$fD(E^A\\|$\$f.$\$f/I = $H`fA([]\A^fD/ f(fA(l$@d$(T$ Dt$荛fDt$T$ f.d$(~Zl$@D $fE(ָ=nfA(fA(f.EXfD(E^AYXfD(DYfD/rfQffA.fA(Q* ^f/Sx@f(fA(l$Hd$@T$(Dt$ 聚fDt$ T$(f.~Td$@D$l$H4$d$ f(D%dfET$(f(fD(A\DXfD(fD(f(DXfA(fD(f(DXfA(Y^YfD/=fA(^\^f(f(fTf(fE(f(fE(f/DXDXDXfA(AYfA(fE(YEYYDYf\E\f.fE(fDTMf/CfD/=ތwf(fE(f(fE(qf(AYfE(EYEYf(f(AYfE(0t$d$ T$(Yf(\|$ddf(fA(l$@d$(T$ Dt$x88fInYtfA(Dt$@T$(d$ DD$eHC Dt$@T$(~fD(fHnHЊd$ DD$fHn@fA(T$Hl$@L$(d$ Dt$T$Hl$@L$(d$ f(Dt$AWfAVE1f(AUATUHSHHHAD$DHDEE1f/vfWCAAD$f/ D$L$ XL$ fDD$L,ff.DEH*D\\-,f/fA(L$@DD$0X\$ t\$ DD$0\DD$ \$(D$f(A\t\$(L$@\\$PL$`D$(%YDD$ f(fA(DD$@YT$ ~-T$ DD$@L$`fD(fW)l$0~-݊ fA(f(T$H\$ AYfTf/\$P|$ f(f(fTf/\$@f(=9 $|$fA()$AXDD$pX\$P$$^D$(XDYf(DYDT$`|$ht$H PXL$f(D$($Yt$@Y$DD$pX|$h$\$PfE(DT$`fD(D|$ f($YfD(Y^EYDYYXf(^f(fDHH= fHfEH*fEHYL*HL*E\XAXA^fD(E\A^fE(DXYE^fE(E^fD(D\EYfD(EYEYAXfDTAXf(fTAYfA/<X^L$f.*$L LAEt AHtUH Ht HHEHt HHHĸ1Ҿ1[H=]A\A]A^A_fA(f(~AYfED XDD$~-fD(L$(f(fE()T$0XDL$ f(f(\5^fD(t$@fDWfE(fD(fD(f(EYDX&HHfE(H=fD(fX%FH*fD(\YXf(f(^fA(fEL*DYD\AYfD(D\ EYDXA\fD(fDWE^^EYfD(EYEXfD(EYEXfDTfE(fDTEYfE/$DD$L$(f( fX^f.QD$\$hf(\$0)l$pfWDT$Pf(Dt$`DD$HL$(bYD$DT$PDD$H%L$(Dt$`AXDYt$@f(l$p\$hf(A^XAXY^E f(fH*AXXY^Xf(A9sAZt$=PD _ YY5YX^YY^ӃfD/vf/ t >Dt$fD-mH DlH D fE(fA(Luzf.f(fA(^f(YDY\fTfD/sqHH=effD(H*D^AXX^fA(XXff.{ff.fA(ff^DYAXf(^EtgT$Ht>Afd$ A*AXkYd$ T$YXEHt#Hĸ[]A\A]A^A_HtU@fD$`fA()$$L$pt$hd$P5kDD$@=քd$PL$ f(f($AY$f(DT$`t$hfT\$@f/L$p^|$ f/`t$\t$(A^YY$f(^1ҾH=B1DD$ T$n DD$ T$@f(T$p)$$$t$hDT$PDD$`d$@d$@f($$T$p^t$h$DT$PDD$`D$@f()l$P\$`d$HDD$@t$(|$L$L$f|$t$(d$Hf(Y DD$@f(l$Pf.\$`NQ^f.~f(fD(T$0D\$ \f(^=DfEf(ЃD*A\fEE*^A^Ae-fAWAYXfD(fDTf(fTAYfD/wYf(f(yFDD$1Ҿ1L$(H=\Dt$PDD$hDT$`L$H\$()l$(f(l$\$(L$HDT$`Dt$PDD$h1ҾH=1)l$P\$`L$Ht$@d$(DD$üDD$d$(t$@L$H\$`f(l$PAfL$A*T$ AXfgfL$f.T$ f.v}1ҾH=1L$ T$'L$ T$1ҾH=1\$@L$0D\$(d$D$ DD$ۻDD$D$ d$D\$(L$0\$@0|[1ҾH=_1T$(DD$d$ \$u\$d$ DD$T$()l$p\$hL$PDT$`Dt$HDD$(,f(l$p\$hL$PDT$`D$Dt$HDD$(D$Hf()l$P\$`d$@DD$(t$|$f(l$P\$`T$Hd$@f(DD$(t$|$Of.Uf(f(SHX~- }5{fTf(f.wZf.кfE„t f/f/wsf.f.f/f(HX[]@H,ffUH*f(zfT\f(fVnf.f/|YD$(YYX)tHX[]1ҾH=1tHX[]1ҾH=1T$ L$|$T$ L$|$'11ҾT$8H=l$0D$ L$|$蛳H|T$8l$0D$ L$|$fLnf(T$(L$ t$Qt$DsD^f(fA(DD$AY\$T$(L$ DD$\$f(T$0DD$ \$t$T$0DD$ \$t$D$(T$(DD$ \$t$T$(DD$ \$t$D$HHfD(f(D sfDWvfD,fA(fA(fA(D~%tDYfE(DYiff(fA(XYAX^YXf.zf/tfD(D^fETfE/w\rH|$8t$T$Yf(\$fft$*D$8\$T$Y,D$8=wf/v7 f/pf(t$T$Hqt$D$<f(T$f~ sfLn+rYAXf(fTf.5 f/nf/-trfHnf(f/fA\f(XYf/s-qf/w&fDAX^f(Xf/f.zf(fWsH|$<T$ d$f(t$\$b\$~ rDqD$(Hpf(t$d$f(fTT$ fLnfD.v,H,ffUH*f(fAT\f(fVf.2,1ҾH=`1T$d$cd$T$f5o\f/d$v \$DD$DL$Y)\$hT$`DL$(~I/DD$ f(\$fTfTT$% % -T$\$f/DD$ DL$(r-H&YfHnY|$0t$8f(f(f(YYYY\f(Xf.zYYf)D$`:D$\Ld$`LH=DL$DD$ODL$DD$tND$`L$hH[]A\ÐfDW'/fA/DD$\Ld$`@~-fA(fA(%,fTf(f.v5I,ffAU-+H*f(AfT\f(fVfD.fD/ ]AYf(fTf.Y FD\A,f(D$`fW.)D$`@D$\Dt$0fWfWfWt$0fWt$0t$8fWt$8D$Ld$pfA(HT$\LfA(DD$tDD$D$\wH54T$`\$pfA(DD$ d$hl$xT$0\$(d$l$DD$ D$fA(ML$T$0\$(YYYL$YD$\\T$`L$hfDH,f%)fUH*f(fT\fVf(:LH=.DD$LDD$fD$\fDD$\Ha44L$0f(DL$ DD$d$~{DL$ DD$d$J(f(f(DL$DD$B{DL$DD$f~%+AVfD(fEAUATUHSHD$ t fD/L$ gfA(^V)fD.QD$D~@*AfE(DL$fDAFfDD$ *DXt$DX'IA,f*fA.zfA/t fE/CfE.f(=)$)$@ fE/ DD$(AfD/L$({ sfA(fATf/ T$(AXf/ J1l$(H$H$DL$Pf/fD\$HDd$@DD$0f.R@G,Չ$AAD)D)*\Y+|D$$DD$0Dd$@D\$pD\$H~)DL$P$Ѓ)ЃzfAWf(fD(AYAXf.#H}=eH$T$(fA(58%8fHnDL$PD\$HDd$@DD$0 7DD$0Dd$@D\$HAD~'DL$Pj D) $$DL$`D$f(f(Dd$PfATfATDD$H\$@T$0@~ %(%D~''T$0f/\$@DD$HDd$PDL$`D$r%H'YfHnY$t$pf(f(YYYY\f(Xf.YYf)$E11ҾDL$PH=d*D\$HDd$@DD$0c$DD$0Dd$@D\$HD~*&DL$Pf.D$(fA(fA(Dd$PDD$HD\$@DL$0?Dd$PD~%$f(DD$H$D\$@fY$DL$0)$A|$(%O$fA(f(f(fATf.v3H,fF#fUH*f(fT\f(fVt$(f. f/ fA(Yf(fATf.F YL$(\,Kf($fW-?&>f.fE.fA(fA(fA(%f#fATf.v5I,ffAUe"H*f(AfT\f(fVfE/~Q%vfA.E„t fDWfWfE/'fE.qkfE. fE/ l$AYD!XD$fAWY!^fA*^Y\$\$DX3f(fATf(_|$fA(fATY|$f/w.fA. !f.rAA'@L$\$fATfATDY DYXAXEHfA([]A\A]A^ÐfD. fD/  fA(AYf(fATf.}XfD.fD/AfA(fA(fATf/vfATkfE/fA(AfWt$(A^f(YX%6 fD. Q= ^f(Y D\$pD$^)\$`D$T$Pd$HDD$@|$0X^f(r DD$@d$H|$0AYT$PD$Xf(D$f(\$`D\$p^fD. QD$0fA()\$pYDd$`D$D$$T$PDD$Hd$@xYD$0$DD$Hd$@D$T$PfA(f(\$pDd$`D$AXD$0"Y^fD. Q$D$(D\$pD$Y)\$`D$|$PT$HDD$@wT$HH58DD$@|$PD$(H vUfHnfHnD-KD\$pf(\$`fA(D$D~D$Df(zAYX9YzXA9YzXA 9YzXA09Yz XA@9Yz XAP9YzXA`9YzXAp9YzX9}qYzX9}^YzX9}KYzX9}8YzX9}%YzX9}YXfDt(Yƒ~Yƒ~Yƒ~ Yƒ uY@tY^Xf(@tfWfATXfD/HAY 9QfA(oDL$P1ҾDŽ$D\$HDd$@DD$0H=!1$[DD$0Dd$@D~D\$HDL$Pf(5ׁ)$$A$f.{LfDfA(fA(DL$@Dd$0D\$(DL$@D~<Dd$0D\$(f(|$fA*XD$Y^AY^YD$=DfA(fW=A|$(*fDŽ$DL$PD\$HDd$@DD$01ҾDl$~Y-rD%f(fATYf/ AYf/tYl$0L$@A/fA*YYl$,@fA(1H$DL$HD\$@)\$0Dd$(Zf$DL$HA*D\$@D~f(\$0Dd$(YYl$D1ҾH=8y1DL$@D\$0Dd$(X-^Dd$(D~ND\$0DL$@H,f-fUH*f(fT\fVf(KA`fA(DL$`D$)\$PDd$Hl$0T$(YY$L$@l$0Dd$Hf(\$PDL$`D~D$YfA*YXYYl$zfL~AfD(HD$(DL$P1ҾDŽ$D\$HDd$@DD$0"D%HHf(|$pfW$fW|$p`1ҾH=#z1D$D\$p)\$`D$L$Pl$HDD$@VD\$pD$D~df(\$`D$L$Pl$HDD$@11ҾDd$pH=y)$D$D$T$`$L$Pl$HDD$@2VHT$`$Dd$pfLnL$PD$AYl$HD$D~DD$@f($f/>ol$1ҾH=]1DL$HD\$@)\$0Dd$(yUl$Y-Dd$(f(\$0D~D\$@DL$H1ҾH=1DL$HD\$@)\$0Dd$(Ul$Y-mEH,f%fUH*f(fT\fVf(DŽ$T$(fA(L$fA(H$LDd$PDD$HD\$@DL$0^DL$0D\$@DD$HDd$P$wH 4$D$(DL$p$D\$`D$DD$Pt$@\$0ZD$HD$(l$HYD$0Yl$@DL$pD\$`DD$PD~ID$\LH=&DL$PD\$HDd$@DD$0V7DL$PD\$HDd$@DD$0$PCH D,E&11DDL$PH=D\$HDd$@DD$0RADD$0Dd$@D~tD\$HDL$PAADL$D\$iDL$D\$D$ AfA(fA(D\$PDd$HDD$@DL$0feD\$PDd$HDD$@DL$0fD(|D$D$)\$pDd$`$T$Pd$HDD$@hf(\$pD$D$Dd$`D$0$T$Pd$HDD$@f()\$pD$D$Dd$`$DD$Pd$HHh=d$H^f(f(|$@YT$0hf(\$pD$D$Dd$`f($DD$P|$@T$0h$D$pD$D\$PDd$HDD$@d$0cD\$PD$D~0Dd$HDD$@d$0zD$D$)\$pDd$`$T$Pd$HDD$@&gf(\$pD$D$Dd$`$$T$Pd$HDD$@f.ATfD(USHĀfD.f(vL$)D$`)D$p_f.fD(PfһfA/UfA/D$fA(DD$DL$nDL$DD$f ڂf/0fA(Xf/ 1H|$HHt$@DL$f/fA(DD$f.fɍ@GA,ЉD$\D)Љ)*\Ydfl$@~%UDD$l$8l$HDL$l$0Ѓ)Ѓ|$fA(fWf(f(YfWf(Y\AXf.fA/H=Ld$`fA(5΀L%fHnDL$DD$DD$DL$)\$hT$`DL$(~)DD$ f(\$fTfTT$g ݀- T$\$f/DD$ DL$(rHYfHnY|$0t$8f(f(YYYYf(\Xf.YYf)D$`u7D$\PwcH 4tLfD$\Ld$`LH=DL$DD$a0D$\DL$DD$taD$`L$hH[]A\@fDWfA/zf.D$\Ld$`kf~fA(fA(%N fTf(f.v5I,ffAU-J H*f(AfT\f(fVfD. fD/ AYf(fTf.Y D\A,f(D$`fWV)D$`@/D$\Dl$0fWfWfWl$0fWl$0l$8fWl$8]fL$fA(fA(DL$DD$DL$DD$D$`f(uL$hfYD$`)D$`D$Ld$pfA(HT$\LfA(DD$JTDD$D$\wH4T$`\$pfA(DD$ l$h|$xT$0\$(l$|$j$$l$|$*D$<l$f|$$$if/_W~Bp)D$@E1ҾH=i1~pl$|$$$)D$@=F$$|$l$~5f(f(fTf(f.v5H,ffUDH*f(fAT\f(fVf.f/ LYf(fTf.Y 6\,ĨTf(D$@fW )D$@|$ DL$@fHTd$$H$f(DT$Pf($fAf(H )$fHn$D$HDŽ$HDŽ$f(,$|$ Dl$HD$@fWL$f(f(l$0fA(fWf(tDD$@\$f(f(fA(fA(YYY\f(YXf.fA(f(Q:f(j~)$OfA(fA(fA(d$hfA(DD$0E1D$|$ D|$xDT$@l$HDl$D4$D4$Dl$l$HfW-JD$PfA(fA(Dt$pf(Dl$H,$^|$ DD$0DT$@L$fH~f(fA(f(AXfA(f(A\L$@fHnfL$@Yd$hDt$pfI~YD$|$ fH~t$DXfH~fI~DD$0Dl$HD $fI~$D$l$Xf(XD$`Dt$pl$h@LfD$xfLnH*fMnIL$p$ffA(I*XXXf(AYAYYYYfA(^^fA(YYY\fA(YXf.\$`T$XfH~fI~f(f(AYAYAYAYfD(\DXfD.D$hfMnfLnfA(XY$XX$f(AYAYYY^^fA(f(fA(YYY\fA(YXf.|$PfH~fA(fI~Yf(AYAY\fA(YXf.XfInAXDL$0Dl$ XfI~l$L|$HXl$,$B $D$@fInBY(Pf/D$@wGI Dl$ DL$0f1ҾH=1,#-l$H,$D$H $fA(fA(f(d$HA\fAfEl$@fW fA()\$0D)T$ H|Off(\$0l$@ $ fD(T$ d$Hf(D$fHnf(H$HC)$HDŽ$HDŽ$D)$$$|$D$f(f(Yf(AYAY\f(YXf.fA(f(5f(f(fA(D$fAEXf($$Yf(\d$PE^D\$HD$$l$0|$ HDŽ$A\$fA(Y7HMfH$$Hf(ƾ $fHnf(nl$0f(4$D\$HD$@d$P|$ L$DYYfWf(A\fWf(f( DD$t$@f(f(f(fA(3kf(fA(fA(DT$`fA(DD$X|$PDL$Hd$0t$ Dd$@l$D$[3Dd$@H9d$0t$ DL$HAXD$l$DX|$PDD$XDT$`FL$XD$PfA(f(D\$HDd$0DL$ d$@Dt$D<$2D\$HDd$0DL$ d$@Dt$D<$D$ fA(fA(fA(2f(D$PfA(fA(f(DL$0Dl$ DD$@,$D2DL$0,$Dl$ DD$@,fA(fA(DD$0l$ DL$@D,$H$Ld$H1DD$0fl$ DL$@D,$f(fLnfMnL$`D$XfA(fA(DL$0Dl$ |$@$$1DL$0|$@fDl$ $$f(fD(fA(fA(|$Hd$0DL$@D,$H$Ll$ *1|$Hfd$0D,$fLnfMnDL$@fA(f(f(DD$pDT$hDL$`Dd$XDl$PD|$H|$0t$@l$D$0|$0H9Dl$Pt$@D$f(Dd$XDXl$D|$HDL$`DXDT$hDD$p4f(fA(fA(t$Hl$0Dt$ D|$@D\$D$$L$H$0t$Hl$0fInDt$ D$$f(fLnD|$@D\$fA(fA(f(DL$Hd$0Dt$ D|$@D\$D$$L$L$}/d$0DL$HfInDt$ D|$@fMnD\$D$$[L$hD$`fA(f(D\$HDd$0t$ l$@Dt$D<$/D\$HDd$0t$ l$@fD(f(Dt$D<$gAWfAVIAUIATUSHf.HT$`HL$hLD$PLL$X$,$~ ULf(fTf/[{]5{N^4$A f/hXH$L$Y,%fT$HL$@Yۃ f(X|$f(\|$fX|$f\|$ @fMl$HA*=f(YfTf(f.vH,ffUH*fVXLHt$8Ld$0AYL$(YY\f(0L$(t$8Y5@M|$f(d$0fW%X\D$@YY^$f(^4$$YYXYXL$|$|$L$XYXD$ |$D$ A9L$@<$^=)f(|$(L$03D$8D$(fWk3fL$0D$@$Yf. Qf(^J^$f.$ QD$0-LHXl$($f(.D$(LH\ġ$$L$Hd$pq.l$HD$`t$ L$Hd$pf(|$@Yf(fW-$YHL$hD$Y|$0\$xD$Yf(\$Yf(l$8YY$\t$l$`Y|$f(Yf(AYAY^(Y$f(fD(L$@Xf(Y\f(f(\AHY^YffLnH\f(fLnXf(AEAffLHl$8A*3JD *It$0DD$(|$ YT$DYDY O,f*XY7D\fA(,T$D$D$|$ DD$(t$0l$8d$\$f( AfW%X\D$@Y$YjId$Y\f(Y^DY\$DYAYEXAXXf(AYXA9T$xH$$f(AYf(YDYYT$p\$DXl$HYDYf(YYf(H$YYDHD$PD^XL$`\YYA\H$^XHD$X8Hĸ[]A\A]A^A_fD%(G x=AYfD(f(Y-f(Y=tWYfEfۉ*D*XA^\Y^YDXfD(fDTfA(fTYfA/vEf(fD(ĸ @=tWYfEfۉ*D*XA^XY^YDXfD(fDTfA(fTYfA/v$YTEEL$ t$d$f(\$'L$ XDAYH5D%EYefD(H=@d$fHnt$\$~fHnD\f@=fEfEDYD*D*EXE^fE(D\fE(EYE^fD(E^DYAXfD(E^fE(AXDYEXfDTfE(fDTDYfE/bHD$`f(L$ t$D d$\$%d$XaCAYEL$ fD(HtH >t$\$fD(~fHnfHnD\UAYD\f(D=YfEfED*D*EXA^fE(DXfE(EYA^fD(E^fD(YE^EXEXfD(EYEXfDTfE(fDTDYfE/d$HD$hYD YfD(f( D=t_YfED*A^fE(EXDXDXEYA^A^YDXfD(fDTfE(fDTDYfE/vHD$PfD(f(D=tiYfEfED*D*EXA^fE(DXD\A^A^YDXfD(fDTfE(fDTDYfE/vD&HD$XL$(t$ DYDA^$d$\$D\f(D\$H#HD$PX@D\$H YHD$XfHnH h<Dt$ d$\$L$(fHn~*D\YHjfLnDX =Yf*^fD(DXXDX^fA(AY^f(A^fD(YDXf*AXD^f(EXAYDXfTfE(fDTDYfD/bH$fD(L$t$DAE^$D\f($DT$!HD$XXr?DT$H YHD$PL$fHnH :t$$~fHnD\lYD\f( =ffE*Y݉D*fD(\DXA^fD(^f*XD^f(A^AXA^YXf(YDXfTfE(fDTDYfD/cH$DYHH tGHHD$hHH H sHH$H LIIHH$HL$0#L$0fL$H#L$HD$0fDf.f(UHH HxUff/Gf.E„u&f.D„uf.z@u>HgfHnH ]@1ҾH=1+ H ]Df(H|$Ht$$"D$$fWL$^Htf(\^HH j~-Z%Y^\f(fTf.v=9fH*ʃY^\f(f(fTf.f(H9|HGfT$H*"T$HfW$f(QY$H ]fDf(f.DfH8f/fL$$j$d$f.zH8,f*f.f~-&5f(f(fTf(f.v3H,f5fUH*f(fT\f(fVf.z'u%1ҾH=v-1 H8f(H|$(Ht$ d$Y|\$d$\$l$(t$ f(f(l$4$^$\$d$Yf(fW@f($^$~-\f(^D$fTf.-s\$ff/w5 Uf/fDf(H8aD1ҾH=Y,1Ef.@,fD(fATUfD(S*HĀfA.zfA/tffA/%fE.f(h/)D$`)D$pffE(лfA/f(fA/D~;fA(fATf/{f(AXf/h;1H|$HHt$@D)\$f/fDL$ DD$D$f.fA(@GA,҉D$\D)Љ)*\Y9l$@|$HD$D~%;DD$DL$ l$0fD(\$|$8Ѓ)Ѓu f(|$0fAWfAWl$8|$0fEWffAYXfA.H8=9Ld$`fA(59LfHnfA(%t:9D)\$DL$ DD$D$}D$DD$DL$ fD(\$h)\$hT$`DL$(DD$f(DT$ fATfDT\$fA($$ 9%\$f/DT$ DD$DL$(riH7YfHnYt$8|$0f(f(f(YYYY\f(Xf.2YYf)D$`u7D$\PwoH B4tXfD$\Ld$`LH=DL$ DD$D$D$\DL$ DD$D$D$`f.zUH[]A\@fDWfA/ojf.D$\Ld$`[fHfA(fA([]A\Yf1ҾH=$1[H[]A\f.D~fA(fA(fATfA(f.v5I,ffAU%H*f(AfT\f(fVfD.=fD/2 bAYf(fATf.Y JD\A,¨f(D$`fWDfA(fA(fDD$ DL$D$aDD$ DL$D$`f(-D$L$hfYD$`)D$`ft[D$\fH,ffDUH*f(fT\fAVf( fDD$\`fDLd$pfA(fA(HT$\LfDD$ DT$D $ D $DT$DD$ D$\wH4l$`t$pfA(DL$0DD$(l$ t$DT$nDT$$fA(ȬDL$0DD$(f($YL$YD$ \@`LH=>DL$ DD$D$vDL$ DD$D$8L$8f(DL$DD$ d$D$dDL$DD$ d$D$fA( fD)\$DL$ DD$D$ fD(\$DL$ DD$D$fD(ATff(USHf/9f.z;u9!f/f.Gf.f(fWf\,*f.EtE~AXąE$$Y@7YX2f/H;=S{~-SH$<$H$f()l$L$8T$ f(l$$$f(fTY$$f/0T$ L$8f(f(fTX+;fTf/%$$1f/Ġf/v f(ĀT$),$f(fTY%Gwf/%Ňf/+YT$f(,$D$|=%f(XcXf(f(YfTf.\$8f f/2Df/ODf(f(fA/ \f(XYfA/sDfD/w$ @X^f(XfD/ f.zu1ҾH=y1)l$@|$ T$4$r4$ T$|$ f(l$@\ufT1f/5])l$ |$$1H= $|$ff(l$ f.zf/qf. t$8f.5%Ef(f(fTf.v+H,ffUH*f(fT\f(fV\f.ztt,tQ3,f*f.zFuDܼfW f($l$YH[]A\H[]A\@Xf.[f/Rwf.v~ff(fTf. μw-$f(f(fTf.v3H,f-!fUH*f(fT\f(fV\f.z G,< %@Yf/s"f/qs#D,Et f/?H@=Xv~-XH$HI<$H$f(d%@'kfDWfTfVBYfH$f(f(l$$$f(fTY4$f/$T$ L$8@H[]A\ ?A'DH=15mL$Pd$@$ $=H$f(5f(|$8\XT$Yf(4$l$ l$ \f(V4$fd$@T$|$8Yf.L$Pf/yf.Y~-kf(fTf.ӹwif(fD(fD(DfTfD.v2H,ffDUH*fD(DfDTA\fAVfD(A\f.82Y%EifD(fD(э4DYDXDU2D%,CL$fD(̺f(fD.rf9t]ff**A\YA^Yf(DXfTf(_f(fA(fTfD(EYfD/wf.zu)l$`f(DD$P|$@DL$8t$ L$$p$DL$8L$t$ AX|$@DD$Pf(l$`fTf($AYfTX=rY<$$f/3ff/| 8Wf()l$Pf(\%-f/)|$@t$d$ $ d$ $f(f/$6t$Y|$@f(l$P\X nf(f(Y^tnY\:YX'^XfW H|$|)l$P|$@f(t$ T$ $荨 $f(l$PD 1D$`T$f(t$ |$@f(fTfD.v+H,fH*f(fT\f(fUfVf.z,ĺf(\ăDf/D$|v Xf(X)l$P|$@L$ T$4$L$ f4$T$|$@Yf(l$Pf.z')l$@|$ T$4$4$ yT$|$ \f(l$@\L$`(Yf(WfT5fWf(~-9f(l$`$DL$8DD$P|$@t$ AXL$f/vD$|fW%fA.A\x)l$P|$@t$ XT$Y $\xY\xY\xY\xYfH~f(\xY\xY\xY\xY\xYfI~f( $T$f(fHn\\xt$ |$@f(l$PYfIn\Ax^XK$|$@d$ f(l$Pf(fD(t$YYD^ w\XkAY\ wAYX wAY\ wAYX w^Xaf()l$@|$ T$4$4$T$|$ f(l$@f(A,fW%Df(fD/7Y~-{f(fD(f(D+fT,,f(fH5-0fW=8f/f(f(fTf.v5H,fDH*f(fAT\f(fUfVf.z:f/u4uRf/~ƴv@f(fWf/wf(H鲤1ҾH=I1uHf/vf/sf/7f(ǿHh1ҾH= 1+HfDAWIAVAUATIUHSHH8Ll$(Lt$,D$(LLD$L$t$,AAOiD$(D$L1L$D$,L$,EM@D$(0LLD$L$tT$,KD$(D$L$LD$,,D$,A$AL$cD$(vH8[]A\A]A^A_Ht11H=f(A$H8[]A\A]A^A_H,D11H=4Of(sHaDf.D„u,ff.zbu`fHu'H0f([DfH0f([f1ҾH= 1KH0[f(fHfH*f/f(H|$(Ht$ L$ L$D$(^f(\\$ ^f(HPHq~-a%ѩY^\f(fTf.vD f.fH*ƒY^\f(f(fTf.f(H9|f(L$!L$f(^fDf^f.w*QD$Xf(T$YQL$T$L$T$D$f.f.f(f(~H8HxMff.w f.%vaf.zuf(f(H8@ЧH8f(1ҾH=1#˧fH8ff.E„t%f.E„tHuf(xff(f(t$(H*XId$ l$Жl$d$ D$f(f(L$f/|$DD$f(f(l$t$(AYf(YAY\f(YXf.zf.z u f(f(f(f(fA(t$t$l$f(f.f.f(f(FH(Hx]fɺf.E„tf.BDЄu$f.w f.%vXf.z:u8f(H(1ҾH=1CfH(fH(f(ff(f(d$H*X\$讜d$\$D$f( $fml$4$f(f(Yf(YY\f(YXf.z f(f(f(f(f(f.f(H(HxQff.zuݤHu`H(f(fȚf.<vzf. "{HH(1ҾH=M1H(fDf(H(ufRH*xY(k^f.w/QD$fH*X(YD$H(H|$L$GL$H|$D$@f.SHH HD$ $Ef$d$f.z uHH f([~x f(fTf.wfTf.f.z^u\f.%f(!1ҾH=ը1kfH [fH f(f([fH f([fDff(f(d$H*X\$[d$\$D$f( $fu4$l$f(Yf(f(YY\f(YXf.z=f($fH*4fYf(f(f(f(nf(f.ATSHH8H $D$Cf $d$f.zuf(H8[A\~xf(fTf.w fTf.vxf.zuf.% zNuLf(f(f.1ҾH=1kH8f[A\XH8f([A\@fH*XD$ f.D$(1f.'f/vfWLd$ f(HL$Ld$ $  $d$fۅT$Bw;H l4u$f.˺E„tf/l$(t$ Df(f(fl$4$4$l$f(f(Yf(YY\f(YXf.f(f(f(f(@-pf(kLH=L$$$T$L$f$$5f(#f.DAUATUSH%KD$H==5՞XXL$(XXT$0f(Yt$xXYf(f(YXYt$PYXu\$Xf(f(YXKYYXKd$`YX9f(cYf/|$hf( f(^5YYYL$f(Y=f(t$fD(DYDl$ $D$0[DT$(=\ff(Dd$HL$fA(t$DGfD NfYf(\&fd$`^%pYd$h^%.\f(YAYXf(f(AYYf(fA(AY\%eXT$X^TYfA(AYXf(AYXAYAYXÜAYXf(YXAYY|$XYT$PXXYD$0YXAYXAYX$Hĸ[]A\A]YfDhXf(fT 6f/t$(f.5f.f.5n5t$ 5̛t$pfDL$(*腙f(x\$ t$HD$pf(YYYD$xYt$0\Y\YX nD$(X`S $\D$pHT$(\T$p\f(YXD$0t$( $f(f(fTf/-<HHF^l$(f(YH5XH4H f/HYXYXH YXHYXH YXHYXH YXH$BYXYXYXH HJHFYHH4H XfUYf(XHYXYXH YXHYXH YXHYXH YXHYXYXYXYXBHĸ[]A\A]^^Yf(@5pfWpL%t$ 56D$8t$5t$p@t$Yt$8E1HfHnt$f*f(fW t$@ $H $f(fHnX%T$L$f($$T$$$f(=L$X^fT|f/AA~5P f/sf(\$@f\<YH51HR^fHnXL$pY\^t$@==f(XYf(Y^X^fT ݙf/w'X-Ǘ^HXX-YL9ufYT$t$ XfTt$ fT5Yf/dCfDHLf(kHAL$($AfHnDNהt$ ,$%$IcH5A\$f(f(Yf(fWHĀYAD$YHYD$0YĀf(AD$\YD$PHYD$pĀf(HcXY\YD$X^ĀH L$(d$8l$fHnT$\$<$5p<$AD$l$\$ HYd$8T$=YY\YYXY\$X\YD$`^Ā$t$HYX$YX$YX$YX$YX$t$(t$ 5t$p9t$(f.5D$(5ҔD$ t$pHҕL$(t$d$fHnl$$kl$$=d$fD( t$YYXYf(\$ Y\ MYYYf(f(\5YXf(YX\AY\YL$h^ Rp1ҾH=12~L$(5fWfTfV t$pL$ f.AUf(ATUSHxfW-L$ Ld$lf(T$D$%X\$YD$Xf(^f(_D,D$D)øHfLA*f(D$0AfA*YT$l$L$T$LYT$XT$ \f(L$фL$\fD$(9 fH}HD$*fHnl$0f(5ӒD$lYf*f(fT;f(f. f(\5l$Hf(L$@\$8t$ T$\$8HL$@Yl$HfHn\XhI>f(fHnY^=IY\YXe^XDYL$=ґ\D$lXL$ f(fT<f.5ZUf/=f/D f(ffA/ f\f(XYfA/sD0fD/w$@X^f(XfD/ff.zu1ҾH=1\$8l$ Hl$\$8\\$f(\D$(XD$9H4\$fHnD$D$(YD$Hx[]A\A]ff/ Tf(\$Hf(\5ďf/ |l$@L$8t$wYD$L$8f/ l$@H\$H\XDGf(fHnY^GY\YX=^f(X@OD.f(ffD\f(XYfA/sDXfD/w0@X^f(H5fLnXfD/qff.zu1ҾH=1\$@l$8L$^HwL$l$8\$@fHnf(LfWa\$Hl$@f(L$8T$PT$="DD$PHf(L$8l$@f(fT\$HfHnfD.v+H,ffUH*f(fT\f(fVf.z ,ƺf(\ƃDf/qD$l\$@T$8l$wT$8f\$@Yf.l$zf\$8l$ _Ql$\$8\\L$P@fWLl$HL$@f(\$8T$~T$=ΎDD$PHf(\$8L$@f(fTl$HfHnfD.v+H,ffUH*f(fT\f(fVf.z ,ƺf(\ƃDf/D$lo\$HT$@l$8L$JvT$@fL$l$8\$HYf.z )fD\$@l$8L$L$YL$f(OXL$ l$8% \\D$PH|\$@\f(fTnf.fHnD$l fff/vD$lfW5FfA.A\^Ol$XL$P\$HXYT$8\>OY\:OY\6OY\2Of(f(\*OYY\"O|$@Y\OY\OY\OYD$f(5|$@\=NT$8DD$D\NHBY\$HL$Pl$XfHnA^Xff/vD$lfW=fA.A\\$Pl$HXNYL$8\NY\NY\ NY\Nf(f(\NYY\Mt$@Y\MY\MY\Mf(f(YT$t$@\5ML$8T$\Ml$HY\$P^X ЈL$8Hֈf(l$@\$HYT$f(fHnY\Xo@^KMY\GMYXCMY\?MYX;M^f(Xf\$8HFYD$l$Hf(fHnL$@fHnY\X?^LY\LYXLY\LYXL^XmDXf(X@Xf(Xof(\$@l$8L$?f(fDof(\$8l$l$\$8f(\\$f(\D$(XD$H\$fHnD$@DWf(fD/Cf(f(fD+f(Sfd$f(f(f(AVYf(fD(SfD(fD(f(fD(HhDYL$YYYDYEYEYAYD$xYD$`YD$ Y$Y$Y$f(YDYD$0f(AYD|$@fD(DYD$Hf(AYD|$PfD(DYD$Xf(AYD|$hfD(DYD$pf(D$AYfD($DYf(D$AYfD($DYf(D$AYfD($DYf(AXD$D$AYfH~f(YfD(DYD$(f(D$AYfD($DYf(D$AYfD($DYf(D$AYY kfI~f(ff.+QD$XfE( D=8$0D^%Zf(XXY$@Y|$@$85>D$PYt$AXDYD$HY=L$ $$(Y%LfA($^L$D$Y$D$f($DT$8qDL$\$l$H/f(fA(fE(DT$8DD$@\fHnD5KD$^f(fE(|$HY$fLn$0EY\ԃDYE^fE(AYfE(EXEYDt$0YDYY$^D\SYAYA\D%DYEXD\% D$(EYD5DYDXf(XE\D\5qAYD5JD\Y\XFT$(t$(YYAXfE(D^T$XAYDYt$PAYfE(E\EYD%`YDY^A\AXD-pJfE(D%DYE\D\5$ $8D=DDYEYAXfE(D%wDYE\D%DYE\D%IDX5 DY$DYA\fE(D%IDYE\D%IDYE\D%IDYEXDd$0DX5IEYDY|$EYD%IEYDYAXD5DYE\D%yIDYfE(D%vIEXD5`IDYEXD\-]D5\EYfD(EYDX$A\D--IDYE\D-HDYEXD$EYEXfE(DYl$DYt$hE^A\AYDd$pDY%HY^L$(\lYfD(A\AYD\T$XYHDmDl$PDY-HD5HDYDYYfA(\9D`HDYYWHYAXD\YDXCDXYEYA\D HDYA\DHDYfE(DHDXGYDXGD\%Y$@DYDYfE(DGDYDXE\DGDYEXD-GDYEXD-GEYD$HE\D\GEYE\DGEYfA(DGDYA\DGDYfA(DwGXDYAXDhGDYA\D]GDYA\XSGDBD$0AYDY\$Y4GEYAYAXD%$GDYfD(DXGYD\ GYAXD%GDYAXD%FDYA\\FD%FDYFEXfE(EYfE(fD(fA(fD(DYYA\DFEYDYA\D FDYfE(D DXDYE\fE(D\EXDYl$E\fA(D$DYXFfA(fE(D^AYY^L$(fD(EXfD($Y "FfL~DDYfD(L$pY FfE(D$D\%t|DYEfA(AYD$D\EYA\X D EDYYE\D EAXDYEXDX%DT$hDYEED EDl$PD(FYDYDY-EEYEYfE(D fEA\DYD%CEDYE\D%XEDYAXDt$XDY56EAX\!ED 0EDYAYE\D EXDEDYYEXD EDYE\D DDYE\D DDX%DEYEYfE(D$PD\DA\D%DYDYDXDYE\D%DEYD\DYE\DDDYDXT$HDX5DYDEXDDDYAYE\DDXDYE\fE(D%{D DDrDD$0D$XDYD5DDYAYAYDYt$EXDl$@DY-9DDYt$EXD\%DD+DEYEYfE(DDA\D%CEYEYEXD%CDYE\DCDYEXfD(EXDCDYE\DCDYE\DCDYEXDCDX%CEYDYfA(D\ CA\D%CAYDYD\ CYDX CYE\fE(D\ CYDX }CYDXD\sCEYD5mCfA(fE(X_CEYYYAXDLCEYDYA\D%D5>AYEYD%>\fA(A\fE(EYDYA\D->AYDYX>DYYAXD=>DYA\XAXD$DY->A\D$fA(Dl$8A\D .D^$DYAXYD$D$YH>XAYAYD^d$(D$DXfL~D5DYE\DXD$D$DY%=D$D\-oDY =DY5=YfA(D-=AYD%=DYDYfA(\f( =A\YD%=DXDYAX\D$DY%r=AYD$DY%=D\f( Y=fA(Y\ L=YX =AYA\XY^=AXD(=DYfE(D=DYE\D=DYEXD=DYE\D<DYfE(fE(D$EXD-<DYAXD<EYAY\f( <A\D-<YDYfD( <DXYE\f( <AXDY\$hDd$pYDY%<X <\~<AYAYDd$XDY%<fD( o<XAYD\ a<YfD( X<EXYD\ J<YfD( A<EXYDX 3<YD\ J<D\-!<YEYD<EYA\D-T<fA(D;EYA\D;EYDXD\ ;Yf(L$xAXD;DYDYAXD;DYA\D;DYA\X;D;EYDYE\D;DXEYfE(D;EXEYE\D;DYfE(D;EXDYfE(Dw;EXDYE\Dg;D|$`;DYAYfE(DH;EXDt$PDY5C;DYEXDX-(;D?;EYEYD-;EYE\D5;DYEXDt$HDY5G;E\D:EYEXD:EYE\D:DYEXD:DYEXD:DYE\D:DYE\D:DYEXfE(DX-:D%:EYEYDt$ E\fA(D:EYE\D%:DYE\AXD:EYA\Dt:EYDXj:YDXa:YD\X:YD\fA(DI:DYDX?:YfD(EXD\%0:DY$D-:$Y:D-:EYEYDXfA(D=:Y^:EYAXD9EYA\D-9DYA\AXA\D=9EYfD(E\D=9DYfA(D=9AXD9DYDYAXD9DYA\D=9EYA\D9DYAXXz9DDY\$0AYD$DXV9AYfD(E\fE(D-Q9D\DYEXD=A9EYfE(D=69EXEYE\D=&9EYfE(D=9EXDYEXD= 9DYE\D=9DYfA(fE(D\$fE(D=8DYfE(D=8EXDYEXfE(D\-8YD$D%8fD(8EYD-8AYD8E\Dt$ f(D$`EYAYDYDYAXD5u8\f(fA(AYAYDY\U8XfA(YYX @8AY\fA(YXXfA(D=DYA\D$DY-38A\fA(\iD=8DXDYDX7$DY\$Y7A\D\$8YfD($Y 7D^fHnEYD7DY$DYA\$fHnY ]7\a7YA\X`7AYD-j7DYX$E\D-R7DYfE(EXD\%B7YB7D$DY-_7fD(*7EYYA\f(7Y\7YX7Y\X7H7YAYD-6DYX$Y 7fE(D-6DYE\D-6DYEXD-6DYE\D-6DYEXfD(6DX-6AYEYD-6DY\6A\YX6Y\6YX$Y6A\\n6D-u6EYYfE(D-f6XEYE\D-W6DYEXD-L6DYE\D-A6DYEXD-66DYE\D-+6DYE\D- 606D$Dt$xDY=6EXAYfE(D=5EYDl$pEYDY-$6A\D6fA(D=5\5EYDYAYX5Y\5YX5YA\D|$`\5YXX 5AYD-5EYXE\D-5EYEXD-}5EYE\D-r5DYEXD-g5DYE\D-\5DYfA(A\D-L5DYfE(D-A5DXL5DYAYfE(Dl$hDY-%5EXD\%5fE(D-!5EYEYA\D5EYA\AXD-4EYA\D-4Dd$XDY%5D%5EYEYAXD-4DYA\D-4DYA\D-4DYf(4YX4AYAXD-4DYA\\4Dl$ AYD%4EYX k4AYXr4AYA\D4X c4AYA\D%`4DYXG4YX G4YA\D%E4DYX,4YX$DYA\Dd$PDY%4\ 4AYD%4EYXfA(D-4E\EYD%3EYE\D%3EYEXE\D-3EYEXD-3EYE\D-3Dd$HDY%DYE\D-3DYEXD-3DYEXD-3DYE\D-3DYE\D\3D-3DYEYD$DY%c3A\fE(D%X3DYEXD%]3EYE\D-B3EYE\D-?3EYEXD43EYE\D-13DYEXD%3EYEXE\D-3DYE\D-3DYfE(D2DYEXD%2DYEXE\Dl$ D\2fE(D\$@DY2EYD$DY%2A\D$DY2fA(A\fD(Y2fD(f( 2A\AYX2D2AYEYX t2AYA\Xf2AYX]2AY\T2YfD(f( G2A\D$DYW2YX'2YX2Y\2Y\G$YT$0X 2Y$Y1XfA(D1X1EYfE(AY\f( 1A\AYD=1EYX1AYXA\D=1EYfA(D=1XEYAXD=1DYA\D=1DYfE(fD(E\fA(D=u1DYfA(D=j1X.#YT$DYAXD=M1DYA\\ C1YT$D=<1DY$D91DY X1AYYf($X 1YYD\fA(D%0AYAYD\D$ \$ AYD$DX0DYYEXD-0EYAYE\D50EYEYE\EXE\D\fInY=0DXt$(D^f(AX\d$8\X-#0Yl$ X\L$\^YAYX$d$үDL$\$ D$D$(D^AY*YD$YD$Hh[A^$($ D$D$D$$$l$8d$pHX$($ l$8D$d$fLnD$D$$$iAWAVAUATUSHD$xYWL$ T$0$D$@l$xY-.D$f(t$xY5.D$f(6WX\$x%(Wf(D$L$Y .^XWYX.\ .^X臰T$ Y.Y$t$xf/5WXrl$f/-rl$ f/-Vf(fWY$ +.f( rWeL$xfW gY$X.L$(_t$YD$xt$%L$YfL$(D$$\$ $T$Yf(X\$Ӯl$xfL$(fH~HVf(fTfUfVfHnD$Hrf.rU5tUf/k\U%RYd$Y蓧f(YL$fHn1\ $L=gL5iL-HfL$H$f-T5TD$0D$xHD$@HD$8fTfUfV$fWW$>=Tf/\TYD$˦YD$\D$0$D$`D$X耫|$`HTYD$HfHn|$X=Tf/wf/{T]\uTYD$JY$YD$L$ YL$X&SHLAXTYT$YSYD$XYD$PXD$8T$XD$8f(L$($H c$$\$pHd$`\$PxT$XHLt$xl$T$hYYf(l$胨d$`Y$$$D$Y$\$XX\D$0苬\$p4$%RL$XD$`Y\d$ T$hYL$$Yf(\X8YD$`YD$PXD$@D$@H4$AX4A,L$(f(l$Pt$XgYD$HRfHnD$D$Hf.Rf`f|\Q5Ut$Y(f(fW TXQf.\QYD$Y$\xQYD$ţfWT$,$fW-jTL$ f(T$@YL$ D$$T$A$D$0豪l$8Yl$T$Y$f(^L$Hĸ[]A\A]f(A^A_XYH=Tf|$fPf($\^f(賧L$ $Y RXf(sf(f.AUATUSH5SQ%D$H-%PXXL$(XXT$0f(Yl$pXOYf(f(YXYl$PYXOt$Xf(f(YXYYXd$`YXOf(=Yf/\$hD-POf(^-dPf(-DYYfA(YYt$f(f(f(Y|$ $Tt$(D\$hf(^ f(f(Dd$Hf(D AY|$DAYAY\ yf(\]d$`^%OAYYXf(t$f(AYf(T$X^AYXf(AYY /XY$X *NXAYf(AYAYAYXf(AYXAYXMYT$PXXYD$0YXAYXAYX聠XD$0H[]A\A]D0NXf(fT Of/ l$(f.-M f.f.-M'!5BM-"Mt$ l$xfDL$(zMJf(Ѓl$ t$HD$xf(YYYD$pYt$0\Y\YX LD$(H$L$>L$$f(Yt$0\4$Hf([]A\A]f(X@-pfWpOL%ԁ5fDHaKL$($AfHnDNGd$ $-DJIcH JA\$fD(f( KYf(fWMHĐDYAD$YHYD$0YĐfA(AD$\YD$PHYD$xĐf(HcXY\YD$X^ۺĐH*JL$(l$8T$fHn\$t$D$FT$%D$=uAD$Yt$ l$8HYI\$YYD\DYAXYt$X\YD$`^IĐ$t$HYX$YX$YX$YX$YX$t$(-"Ht$ l$xt$(f.5GD$(ʀ-GD$ l$xHHL$(|$l$fHnT$4$ET$4$l$ f(|$YYY=HY%XXYf(t$ Y\VYYY\XYX\YL$h^ 1ҾH=>L1`~JL$(-FfWfTfV *l$xL$ fAUf(ATUSHxfW-IL$ Ld$lf(T$D$踝%F\$YD$Xf(^f(菝D,D$D)øH fLA*f(D$0AfA*YT$l$/8L$T$LYT$XT$ \f(L$8L$\fΞD$(9 fHEHD$*fHnl$0f(5FD$lYf*f(fTkGf(f. f(\5'El$Hf(L$@\$8t$ җT$\$8HDL$@Yl$HfHn\X>f(fHnY^mY\YX^XDYL$=E\D$lXL$ f(fTlFf.5f/=8f/D=Ef(ffA/ f\f(XYfA/sD`DfD/w$@X^f(XfD/ff.zu1ҾH=1\$8l$ xCl$\$8\\$f(\D$(XD$9HdC\$fHnD$XD$(Hx[]A\A]f/ f(\$Hf(\5Bf/ l$@L$8t$试YD$L$8f/ l$@HB\$H\X|f(fHnY^MY\YXu^f(X@WDfCf(ffD\f(XYfA/sDBfD/w0@X^f(HmBfLnXfD/yff.zu1ҾH=1\$@l$8L$AHAL$l$8\$@fHnf(LfWD\$Hl$@f(L$8T$3T$=ZCD)BD$PH\$@\f(fT@f.fHnD$l fff/vD$lfW5vAfA.A\l$XL$P\$HXYT$8\nY\jY\fY\bf(f(\ZYY\R|$@Y\HY\DY\@YD$f(e|$@\='T$8DD$D\Hr=Y\$HL$Pl$XfHnA^Xff/vD$lfW=F@fA.A\\$Pl$HXNYL$8\DY\@Y\<Y\8f(f(\0YY\(t$@Y\Y\Y\f(f(YT$7t$@\5L$8T$\l$HY\$P^X <ێL$8H<f(l$@\$HYT$f(fHnY\X^{Y\wYXsY\oYXk^f(XfK\$8Hv;YD$l$Hf(fHnL$@fHnY\X^Y\YXY\YX^XmDXf(X8Xf(Xof(\$@l$8L$of(fDof(\$8l$El$\$8f(\\$f(\D$(XD$HB:\$fHnD$@D:f(fD/Cf(f(fD[:f(Sfd$f(@f(f(f(AVYf(fD(SfD(fD(f(fD(fD(fEDYHhDz9L$YEYDl$(YD|$@YDYEYEYAY$YD$`YD$hYD$0Y$Y$f(AYfD(fD(DYL$Hf(AYDl$PfD(DYL$Xf(AYDl$pfD(DYL$xf(D$AYfD($DYf(D$AYfD($DYf(D$AY$DYf(AXL$D$AYfH~f(YfD(fD(DYL$ f(D$AYfD($DYf(D$AY$DYf(D$AYY8fI~fD.f( -QD$XfE(D%7D=b8D^f($@=XDXf($8Yt$@$0%gDYD$PAXYd$D$H$ YY5$$(AY=D$$Y$L$fA(^L$$DT$8虍DL$\$l$DT$8f(fA(fE(HB6DD$@\fD(fE(D$fHnfLn|$H$0Y$^D\7DYE^D5EYf(^EYfE(DYYE\fE(EXEYDt$(DYY$A\D%ڰDYAYEXD\%*6D$(EYDXYfD(f(E\XD\55AYD5D\Y\Xd5T$ t$ Y 6YAXfE(D^T$XAYDYt$PDYDY^fA(AXfE(E\EYA\D5fDYE\D=D\54DYEYAXD5$ D-Dd$($8DYD=DYEYDY|$E\D-DYEYE\D-DX5*4DY$DYA\fE(D-DYE\D-DYE\D-DYEXDX5D-DYEYD%DYAXD5DYE\D%EXD5DYEXD\-D$EYfD(EYA\D$EXD-NDYE\D-DYEXDl$xDY-)EXDY|$fE(A\D= 4EYDY|$pE^AYD%3DYY^L$ E\EY\$D\$XD5DY2E\DYD%D|$PYDYDY=DYf(\GE\D5 DYAYEXDX%AXEYA\D%DYfE(D%>DYE\D%3DYfE(D%(EXD"DYDY$@EXD\-D%DYEYDXYfD(YD\YEXD5EYD$HDXYD\D\%AYEYE\D%DYA\D%DYfE(D%DXDYYDXE\D%xDYE\DXmD%4T$(^D5eAYAYDYDYd$AYfD(5YEYD$AXfD( EXYE\D5DYfD(EXD- YDXE\fD(D\EYDAXfE(EYf(fA(fD(EYDYA\D%EYDYA\D5DYDXE\fD(E\EXDYt$D-DYE\E\fA(D$DY%]fE(fE(DE^DYfE(D$D\=/DY/fE(EYfE(AYY^L$ f($Y X$fH~fD( E\YfD( #YD\L$xY DXD-D DT$pD%!DYDYAYEYDYEXDX=ֱD-AXDYfE(D uDYEYDT$PDYE\D UA\D|$XDY=XDYfE(D 5EXfE(D%zDYDYEXD "D\ E\D%SDYDYEYfE(D EXE\D%+D-DYAXD\$HDYDYDYE\D%EXD-DYEYE\D DYE\D%DYE\DX=|D$PEXEYD%DX5EYEYA\fE(E\AXD-D%D$XD5DDYDYEYEXE\D%XDYfE(E\D%HDYfE(D%UEXD-/EYDYEXD%?EXDl$@DY-D\=EYEYE\D%DYA\fE(D%EXD5DYDYEXD%DYE\D5E\D%DYfE(fE(D|$(EXfD(EYDYt$EXDYt$D%EYEYD=A\fE(D%EYE\D%EYE\D%uDYEXD%jDYE\D%_DYE\D%TDYEXD%IDYEXfD(D\9EYfE(EXD1EYDYfA(fE(EYfA(D%AXfE(EYDYA\D5EYDYA\D-DYAXA\D$DY5A\fLnDXEXD|$8DY\$E^D56DYAXDYYDY^D$ $$YvE\D$D$DY%DfA(fE(D$D\%DY5&fE(D$EYD%DY50DYA\DDYA\XÚYX YD\ YDX D\%YEYfD( A\D%YDYD\ YDXE\D\D$xD%YD-D5DYDYDYf(AYDE\DYD-jDYXAYEXE\A\D5LDkDYDYE\Dt$pDY54DX%#AXDEDYEYA\D%%DYA\Dd$XA\DDYAXX D EYDY\$PAYX AYfD( AYD\ YDX YD\ YD\ YDX YD\ D\-AYEYDEYA\D\ AYAXDDYA\D$D-D5DYDYDX ZYDX QYD\ HYD\L$HY ADX0AYD:EYX!YAXDEYA\DEYAXD DYA\DDYfE(fD(E\fD(YAXDDYAXDDYA\D\$@DY\AYDEYXT$`DYE\E\DEYEXDEYE\DDYE\DDYEXD}DYEXDrDYfE(fE(D-bE\DYE\DXRD-QD=`Dt$(EYEYDYl$DYl$EYD#DYA\D5DY{EXD5EYE\D=EYE\D=DYEXE\D=DYE\fE(fE(DDYEXD5DYEXDDYE\D\5DEYEYD5DYA\fD(EYfA(fE(A\D%EYDYA\D-qEYDYAXfE(DYYAXD=VDYA\D=DYXfA(D$XA\Dd$8A\D$DY AXYT$E^DʱDYXE\DX=AYAYD^l$ X$D$D$D$DY-DY59D$fH~D\a"D%YEYD$EYDY-WE\EXD=TDYfE(D=IDYE\D=>DYEXD$DY=)D\ EYD=DYE\fE(D= DYE\D=DYEXD=DYE\D$DY=DX6EYfE(fD(EXfA(D=DYfE(D=DYE\D=DYEXD=DYE\D=DYfE(D5DYEXD$DXhEYEYA\D`EYE\D5emD|$xDYd$p$DYEXYD7DY=FDYE\EXDX2D\AYEYfD(AXDDAYEYD\YfD(EXYD\YfD(EXD57YDYDXYD\D\=AYEYD\A\AYfD(EXDYDYD\YEXDl$XDY-DXoYD\fYD\uDXTAYEYD\]DXAYfD(NEXAYD\?YfD(6T$`DEXYEYfD(EXYD\YfD(EXD|$PDY=YDXDX5AYEYD=DYE\D5DYEXD|$HDY=D\AYDXAYD\YDXYDXYD\YD\yYDXD$hDX5iEYD=kDYE\D5`DYE\D5UDYE\D5REYEXE\D5BEYfE(EXD2DYEXD'DYE\DDYfE(fE(E\D5DYfE(EXDDd$0D5DYDYEXD\=DY$DEYEXD=DYYEXD=DYE\D5EYE\D=(DY|$(EXD5EYE\D5EYE\D5uDYEXD5jDYEXD5_DYE\D5TDYE\D5IDYEXD5FDX5EYEYD\6EXfE(Y0AYD\&AYfE(D5DYEXfD( YEXD5EYD\YEXDXYD\YD\fE(D5DYEXDXD\5$D$ YT$Dd$h$$$D$(D$$DYfA(Dl$`$A\fD(fA(fD(,AYD&EYDYAXD%EYDYfHnA\D-EYDYfA(A\D5AYXfA(fE(YDY Y|$8XA\XfA(YXD$ A\A\DXDXjDY\$A\fD($Y-^DYDY$A\$rjfHn$D $Y:$$DY$Y5:$D$DYvfE(D$D\NDY fA(D AYDY\fA(D DYA\X D DYY$Y5fE(D XDYE\D DYfE(D EXfD($D\-jDYEYfE(D jA\DYE\D ZDYEXD ODYE\D TDX;DYEYfE(D ;AXDYE\D +DYEXD D$DY%D$DYDYME\D fA(D$DYDYjfE(D EXfE(D$DX5EYEYD5<fE(D A\DYE\D DYEXD DYE\D DYEXD uDYE\D\jD$ EYAYXZAYfD(PAYD\FYDX=YD\4YDX+YD\"YD\AXfE(D$(DYAYA\A\D5EYAXD5DYA\D5DYAXD5gD$D%DYEYAYA\D5DYA\D5DYAXDt$xDY5XAYX AYD\ AYDX }AYD\ sYDX jYD\ aYfD(fA(A\Dt$`fD( BYfD( 9EXYfD(L$pY -EXD\-fD( EYDl$XAYA\D%EYA\D%EYXAYA\D%DYXYA\D%DYA\D%DYfD( YAXXA\\ DY-DD$0D%EYEYAYDl$hXAYAXA\D%EYfE(D%DXgDYAYD\XAYAXfE(D%`DYDX>YD\5YAXfE(DY-NAXD% DYA\Dd$PDY%\AYD%DYXfA(E\D-EYD5EYE\D-EYEXDl$HDY-E\D5EYEXD5EYE\D5DYE\D5DYEXD5DYEXD5DYE\D5DYE\D\%~D$DY5sEYD-mDYf(A\fE(D5YEYEXD-VEYE\D5;DY>AYE\EXD\*AYfD( EXAYDXYD\YfD(fA(A\fD(fD(YfD(EXDl$hYDXYD\fA(Dd$@\DY%DY$YA\D$DY%A\Dd$0DY%A\D%EYfD(tAYAXDiDYDXgAYE\AXDWEYAXDLEYA\DADYA\fD(2YAXD(pYD$(Dd$0DYDY%5AXDDYA\DDYA\XD$DYYYD$X$YAXA\D%EYA\D%DYfD(AYAXDEYDXAYD\AYAXDvEYAXA\D%nDYA\D%sDYfD(QYAXDGDYAXD\$DYAY$A\\#AYD$X DYYA\D Dd$0\$(DY EYAYA\D%EYAYAXD-EYAYAXD5EYAYA\D=EYEYA\DXE\D\|$8AXXf(\\XBYD$\f(fInYg^f(Y$^L$ YX$]\$( f(D$\L$Y$^YD$ Hh[A^XX$($ D$D$D$$$l$8d${`H $($ l$8f(D$d$fLnD$D$$$EAWAVAUATUSHD$xY L$ T$0c$D$@\l$xY-D$f(ct$xY5D$f(b6 X\$x%( f(D$L$Y ^X YX\ ^XbT$ YY$t$xf/5 Xrl$f/-rl$ f/-f(fW% $ +f(] r eaL$xfW g $XL$(__YD$fl$xL$(HD$f(fTfUfVfHnD$Haf.f/\' \$YYf(YL$f1L=aL5L-L$H$~`L$(D$$^T$ $\$Yf(XT$0@`D$D$xT$0\$f(Yf(f(\ $ `f-D$0D$xHD$@HD$8fTfUfV$fW $D=f/\YD$XYD$\D$0 `$D$`D$Xp]|$`HYD$HfHn|$X `= f/wf/k]\eYD$:XY$YD$L$ YL$XXHLAXTYT$YYD$XYD$PXD$8T$XD$8f(ZL$($H$$\$pHd$`\$Ph\T$XHLt$xl$T$hYYf(l$sZd$`Y$$$D$Y$\$XX\D$0{^\$p4$%L$XD$`Y\d$ T$hYL$$Yf(\X(cYD$`YD$PXD$@D$@H4$AX4A,L$(f(l$Pt$XW[YD$HfHnD$D$H]f.f`f|\%d$YVf(fW Xf.\YD$UY$\hYD$UfW}$,$fW-ZL$ f(\T$@Y}tL$ D$$T$1Zl$8Yl$f(YL$f(X^D$UXD$0Hĸ[]A\A]A^A_=f|$f($\^f(YL$ $Y Xf(q[f(AVff(AUIATIUHSHH`f.z2u0HHHHH`[]A\A]A^~%f(fTf/E1fHT$A*fHnXT$HH H5YH=fHn~fHnfHnfHnfD(fD()tff*Yf(\AYfD(DXA^Y^\Y^YDXfD(fA(fTfA(fTYf/vD DYDYfE( )tff*Yf(\AYfD(DXA^Y^XY^YDXfD(fA(fTfA(fTYf/vDYQADYLfA(EXA\DY<EDEAt7fW7EfW&AfWA$AEf.f(6QY^Yf.*Q=~5DDf(f(^^vf(fW\$HfD(f(YDYYDYf(DXYfWYD$8XEXDXf((DYfWYYYEXl$DDYfWDXYYYEXD DYfWAXDYDYYEXD DYfWAXDYDYYEXDDYfWDXuYYYEXDcDYfWDXMYYYEXD ;DYfWAXD$YDYYEXD DYfWAXDYDYYEXDDYfWDXYYYEXDDYfWDXYYYEXD DYfWAXYEXD DYfWYEXDlDYfWL$@EXDT$D8d$ DYT$(YAXDDYDXf(Yf(fWY\$0AXD$f( Vd$ L$@5fD(D$YT$(T$YL$AYXY wn\f(A $U\$0d$ H|$XXYD$T$Ht$PYH~5Y%KXd$fHn l$HDL$8Yf(YAefHn^YY\f(YYfWYXYfWYf( X=YfWYXpYfWYXhYfWYX `YXf(fWYY TXYfWYL$DXf(YfWYDXYfWYAXYfWYX=YfWYf(XYXf(f(fWYYX\$xOL$\$d$PD$Xf(\T$Xf(f(YYYYY\-kXYY\mH`[]A\A]A^T$OT$fT$OT$f.fUff(HSHHf.z#u!HHH[]fptf(Yf/5fD(f(~=ճfD=t_Yfɉ*XfD(XD\AY^f*^YDXfD(fDTfA(fTYfA/vf(DEY?T$d$,$KT$XhfEYE,$H d$fD(~fHnH fD(fHnf(f=YfEۉD*fA(AXfD(\DXYf*A^^f(A^YDXf(A^AXYDXfTfE(fDTDYfD/mAYfA(\X^#H[]D~5 =  ^HuH$Yf(fW^XYfW^X YfW^X ٱYfW^X=ѱYfW^X=YfW^X YfW5XXf(f(E`^f(ffY^Y-Y XXfXf(`fYXfXf( `fYXfXf(`f$fYXfX^ff.f(Qf(H|$(Ht$ T$\$L$$$JD$ $$t$(L$\$f(T$Yf(YYYX\YY\UH[]T$t$\$ $.KT$t$\$ $f(8f.@AWff(AVAUATUHSHHf.z+u)HzsHHHĈ[]A\A]A^A_fDof/>~%>-)f(f(etVY f*\Yf*^Yf(YXf(fTf(fTYf/vZfl$8T$ Y)d$\$0YYD$`u5lYf(fI~-FD$fInF5=Yt$f(cXY \fInL$hE=wcT$ \$0l$8f(d$XfD(\=F \$@l$H)d$Pefۉd$@|$8*Y 6T$f(\$0\Yf*^f(^YYL$ DXfInDD$E\$0T$fD(DD$DX bXf(L$ |$8f(l$Pt$H^AXA\YXfTfTYf/Y|$`X|$hY=d;NfDDYD^fA.EQDT$HL$PfI~t~%t-dE15!Lt$xD[ Ll$pfEf(fD(ںE*fE(DYEYYffE(*fD(DYfE(D\E\EYEYE\fD(XDYAY\YA^fE(E\AY^DXfD(fDTfA(fTYfA/w ef(fD(YffE(*fD(DYfE(DXD\EYEYE\fD(XDYAYXYA^fE(E\AY^DXfD(fDTfA(fTYfA/w efA(f(LL\l$8AY=HbD\$@DY )d$ DX *aT$DY k\$^A\DYDd$0DD$pA|$xD\$@Dd$0fD(fD(Ht$HEY\$T$EYfHnH f(d$ AYl$8DYfLnHE\AXDYYfHn4At%DL$@~-D=|$8D5_^\$0D-_D%DV`D^f(fWYf(fWXXXYYXfWAYAYYYXfWYYYYXfWAYAYYYXfWAYAYYYXfWAYAYYYXfWAYAYYYXfWAYAYYYXfWAYAYYYX {YD$YXf(f(fWXAYYYXfWDYf(YDYT$YDYDYAXfDWAYAYYYXfWDYEYDYDYAXfDWEYEYDYDYAXfDWEYEYDYDYAXfDWEYEYDYDYAXfDWEYEYDYDYfAWAXDYDYNjDYAYXf(Xd$ >d$ fInt$|$8DL$@f(Y\$0DYYd$PYf(T$D^^^A\X\XE^\#@|$PfM~:fA(\$A\$fD$Hf.Uff(HSHH(f.Bff/  fD(D^fE(D^DYDXfA(^DYEXfE(f(^Y5ҥDXfA(f(^Y-`Xf(f(^Y%PXfD(D^YBXNf(AYfE(D^X'AYfE(D^XAYD^XDY AXE Yf.0QD$f(L$\$CL$\$ff(f(f(^D$YYEE[f/]D~%^fD(YrfEWD^fD(CDXfE(DY `fEWD^EXfE(fA(DYFfAW^EXfE(f(Y5fAW^DXfA(f(Y-fAW^Xf(f(Y%fAW^Xf(fD(YfEWD^Xf(XAYfE(fEWD^XgAYfE(fEWfA(^XY KXG^ f.QD$fAWL$f(AL$YL$Y_Y\H([] f(5YY~-D%ʢfD(f(3tTYf*҉fD(XD\AY^f*^YDXf(A^fTfD/vDYYf/DEf(L$Yd$\$9L$XvWfd$fD(5XfD(fD(Ǹ~-D\fD(f(D%ġ\$@3Yf҉*fD(XD\AYfE^f*эJD*^f(A^fED*YA\YDXf(A^fD(fA(DXf(AYDXAXf(A\^fTfD/DYH([]DHHH([]L$\$<L$\$D$\$; \$D~%D$I@AWff(AVUHSHHXf.vaFf/fD(GD^fA(^DYDXfA(f(^Y5Xf(f(^Y-XfD(D^Y%Xf(fAYfA(^XfD(D^Yf(X%Yf.AYXfA(^YX]Qf(T$d$\$ $= $\$d$T$YhVYf/^]D~ ^f(YмfAW^fD(DXfA(f(Y5fAW^Xf(f(Y-fAW^Xf(Y%fAW^Xf(ffD(YlfEWD^X6YAYfE(fEWD^XBAYfE(fEWfA(^XY&XR^f.GQ$fDWT$fA(L$\<T$L$Y $Y^HX[]A^A_@%(T~f(5gf(f3tJYf*\Yf*^Yf(YXf(^fTf/vTYYYE=Tf/T$L$Yf(fI~x4$fIni4%Y$$f(QXYXXfI~fIn)4XQT$D%RL$fD(f(~3D\5@d$H3Yf)\$0*t$@DD$(L$ T$f(|$\d$HYf*^f(^YYl$DXfInD $M3|$T$fD(D $l$Xf(DD$(f(\$0t$@L$ ^=PAXAX\YDXA^fTf/RYYfInDYA\HX[]A^A_HcYHHHX[]A^A_f(T$ $6]T$ $f(>L$5L$D~ $AWff(f(AVIIAUATUSHHf.H|$PHt$XWQsDbD 5PDQD$ffA. EQD\$=; f(H$(H$@fE(DfEHD*fA(D\\YAYAYfD(f(AY\XH9uf(fD(~VD%]JAYٸH$ YDYf(EXfE(@HetmAYfED*YfE(EXE\YEYD\A^DYEXfDTfE(fDTEYfE/@ƃH@tfD(D$(D~-D^H$ EYfA(DX@HdtrAYYYfD(f*f(XAXYfA(^YDXfATfE(fETDY5 IfD/AHAtDYfD(H$fE(@fH*f(\\YYAYfE(fD(EYD\DvuAY~5HH$AXHPtbEYf*DYf(XAXDYYD^AYXfTf(fTYf/@ǃH@tY~5GH$HPt`AYf*Yf(XA\YY^YDXfTfA(fTYf/@ƃH@tt$l$fA( HD$PYYAYAYf(\XfD(DXYYDYf(HD$X\AYEHH[]A\A]A^A_f(H'D l$@d$ AH@H$AYfHnDL$L$f(t$(9D$0D$(^,1D$8D$0-L$(YYL$8\\XSD$D$0,d$(l$@f(DYDL$l$`YD$8DD$@DL$hX\d$ d$HD$fDfD$0ڍT*0B LHD$ fA*L$IX\D$@YD$8.T$ L$f(YfW ^Y$YXD$Y$XL$D$L$I V|$(d$HfE1l$`DD$@T$f(DL$hd$`Yl$pDL$@D$t$H5VJt$8fT$0A*XL$8Af(L$ YXD$H>+YD$@L$ XD$D$D$(^/T$0XAuD$LHDL$@d$`t$8AD$\D$d$hDD$@t$xR-D$\D$$$t$T$ c1T$ f(f(YYL$66HL$(D$`fHn6D$0D$(^Ͱ0.D$8D$0*L$(YYL$8\\XPD$D$0)t$(f(dYYD$8X\D$@DfD$0ڍT*-B LHD$ fA*L$IX\D$@YD$8,T$ L$f(YfW Y$YXD$Y$XL$D$L$I Vd$hl$pf1t$xDD$@T$D$d$@l$ht$pDL$8DD$xfT$0*X Yf(L$ YXD$H(YD$8L$ XD$D$D$(^f,T$0XЃuD$l$hLHt$pDL$8\DD$xd$@l$@t$0DL$(DD$ d$H*D$\D$$H$d$.f(fHnYYL$3|$`fDD$ fD(DL$(l$@f(d$HA^f.t$0wEXD^DD$8DL$0t$(l$ d$D\$*D\$DD$8DL$0t$(D$EXl$ d$D^\$`MfA(DD$8DL$0t$(l$ d$q*DD$8DL$0t$(l$ D$d$fDAWf(AVAUATUSH$4|$fDŽ$fE)D~%5*ǍG$A*L$$AAAYAXY,f(YN F $Hcщ$HHtH$H$AVHcH$MTƒ$$HLT$ H$׉$AIH$ $H$H$|$D?DH2f(YXAYAY^XYAYAY^XYAYAY^XYY>AY^XYYI?Y?^XYY?Y+^XYY@Y2^XYY 4AY^XYY@Yt@^XYY AY@^XYYAY^XYDYDY>D^fA(AXYY8?Y2^XYY?YT?^XYY@Y?^XYY5Y@^f(f(XL$9d$D$f(DD$|$(L$f(D 5YfA(\$ DY(d$AYYT$8XfA(\fA(A^A^^^\AXD\fA*L%9DY\YT$0DT$f.LLf(t$k t$Ll$@D$8d$HL$\d$fIn YD$8L$\CfIn\EEfIn fWYD$\EEHP[]A\A]A^ffA.wiEQY0)Hf=܍A*L%8f(|$8A^DYAYA\\YYD$fE(fA(T$(d$ \$DD$DT$2 T$(d$ \$DD$fD(DT$HAWAVAUATUSHHL$D$t$f(f(fT%uY%'E$fۃA f(Af(C$ffP*AD$A*^f.QAD$YYYf(YXXD9uf(A9ufHR|$\$*YYHYY \$YYfD(HHfA([]A\A]A^A_ÐY%fۃAff(Af(Dff؍J*D*^f.5QAD$YYYf(YXXD9uf(AAD9fHC|$\$ *t$d$YYHYY CD-f\$ *d$t$YYf.fD(QDs\$ l$d$E9f(fl$L=*D$(d$t$YAYf(|$AYOYYYl$00 d$AEf(f(YfD(DYD9l$0f(E)EeYYfD(A9\$ Gt$D~Pt$(|$ ff(Af(El$AVfDAfE)*D)A*^f.QBf(fAfAW*^f.QAOAD$AYYXYXAD9QYt$T$YYYT$YYfD(fD(f(;f-.%ΈE1fD(f(\$0t$(L$ T$d$:L$ D9T$d$\$0AD$Yt$(YYf(YXXb\$8AT$0|$(l$ t$d$t$D9d$T$0l$ AD$Y\$8AOY|$(D~=YXXA\$8L$0|$(l$ t$d$8\$8D~L$0|$(l$ t$d$\$0t$(L$ T$d$L$ D9T$d$\$0AD$Yt$(YYf(YXXD$f(\$0t$(L$ d$o\$0t$(L$ DD$f(d$fEfA(sAVf(Hf(AU1ATAUHzSHHH)H0~ {dHHǂfTHf/E#Wf(fWIA0A AL$fԬH*H5HHtY^AfA*Y^Tvff/f.f(DQDYYX1f(A\Y5bf(YXfA*Y5=XD,AMcJLHD+M > f/#Eff.f(DQDYYXpf(A\Y5f(YX4=f(fW EHr^ GdKHH0[]A\A]A^f.V=tH0[]A\A]A^A%HfD(fD(E5afD(*f(@fE(HYDXAfD(fEA*AX\f(Yf(\xAY^A\fD(fDTfD(fDTfE/sfC3*d$(l$ T$DD$|$GT$Hl$ 3YfHnd$(|$f(DD$\fD(fD(\^YK'f(YDXHf(A9f(f*X\YfD(f(A\Y^\A9ufD(f(HHHH9uH=HH0[]A\A]A^f(QHHHH9uHHAHfD(fD(D5_=fD(.fD(ȃ@HDYfE(EXfD(f*fD(DYDYf(A\DfDTAY^A\fD(fDTfE/vfD(f(3fD(D^\DDYf(AYD[^\ K fD(HDYEX9|OfD(f(f*\fD(DYDYf(A\Y^A\9uHf(9}kSYf(XYYXXfA(^AXYYDXA^f.f(0 QɃ!AY^DL9HY9}D1=fD(f(Kf(X\YY^^\^YKYf(XYXDXA^f.f(aQE%ADf(HfHHfHfYHH9uDAtHHDYf/#EAOAKf( HHHfHfW@H9uȃ{HHfWЧ`AAAL$fRH*H5}HHtY^ yf/#Df( ѧHHHfHfWBH9uDAPY HHKYHHCfD(fd$ *l$T$DD$T$Hl$DD$YfHnd$ \\^YSYDXA^f.f(QEADf(HfHHfHfYHH9uDA@HHDYf/#ADf( KHHHfHfWBH9uDA>KYYXf(A^AXYYDXA^f.f(QYAL$HڸD9AOA^ Y D9|Y H9|HcA9|A9LYLHA9}f/#EAOAY5XfD(fD(=hfD(,fD(DHfE(DYEXfD(fHJ*fD(DYDYf(A\D fDTAY^A\fD(fDTfE/yfD(LfD(3D\߸fD(D^DYD[(f(YDXHfA(95fD(f*fD(DYDYf(A\AY^\9ufD(Hv^CH=!fD(\^YSYAX^f.QEADf(HfHHfHfYBH9uDA`HHDYf/#qADf( 3HHHfHfWBH9uSYYXf(A^AXYYAX^f.f(Q҃dEAOԉf(HcH|f1HffYHH9uу9 HHDYAL$9NэzNHfo-fDoաfDoܡYHHf(f(A^ffvf>foH fAfAfYfYv~H9uЉfpf~DF9tOA^IcHDYF9}/HcHDYF9}HHDYFA9)A9ĉʹLD1f/#XYBH^ KHC*f/# od$d$ fef(d$d$f(d$md$f(d$t$DL$Fd$t$f(DL$fDYʾf( A^Y f(d$L$DL$d$L$DL$f( d$DL$|$|$DL$d$f(d$ l$T$lT$5uYuYX*bf(f(\|$3Hԛd$ l$|$f(~ T$fHnf(d$ l$T$T$5muY]uYX!f(f(\|$HKd$ l$|$f(~ 5T$fHnDAWf(IAVAUAATIUfH~SH81D1DD9Ãf(DT$T$f(f/ff.f(kt-ktQYYX f(\YOtf(YXfA*Y*XD,A~H55T$L$HHHxHHHHǀH1H)HHt$(DT$L$f(DfHnIY%sAAAED$d$EHT$(AIi@D9l$,AfT-Y-JfT f/HD9uqfHT$ *YD$L$wHT$ L$YAXA{1@fHT$ *YD$L$4ffHT$ *L$YD$ft-fHT$ *ƉL$I$AuAL-f*YD$f(f*XAYEYAX$A$@9l$.A$fTԙYAMfT f/5IAD9!WAOf*D$L$YL$AYMYA$\A$ifA*DfD$A*YL$L$AYMYAX $A $f.f(p-pQYYX\f(\Ypf(YX[AA$H8[]A\A]A^A_I$H|$(H81[]A\A]A^A_É9Evf(L$T$T$oYoYXD\f(f(\d$ML$d$T$f(f(L$T$T$oYoYXf(f(\d$L$d$T$f(qAA$f.fAUfATUHSHHf/H$HD$f( f(f(=ݕfTf.f.f/,f/`fWHt$HEf(KAA\EAf('fA*Y$EfA*YD$-1ҾH=10ErH[]A\A]H,f=fUH*f(fT\f(fVHEHH[]A\A]fDHHf(ʿf(xn1H=[@11E JAE\AAf(7fA*Y$EfA*YD$f.fAUfATUHSHHf/H$HD$%=yf(f(f(fTf.f.f/f/,fWkHf(OI\ڃEAf(EAAHt$fA*Y$EfA*YD$H[]A\A]fD1ҾH=1EH[]A\A]H,f=fUH*f(fT\f(fV{GfDHHf(ʿf(t,1H= @11E WPfAWIAVLcAUDMATIULSHHH1HD$.GT$f/ExiHCH9A~Af( j1fDHLHH9uDAtH= HHH|H%HCH[]A\A]A^A_f.AD$~5!AfWAHSH@L)H@f(Lfo-fofHLfoH fH fpf`f^f^fYf`f\fHfYfHbf\JH9uȃp9t}fHc*AL^AY\ ӍP9|QfHc*AL^AY\ 9|%fHc*AL^AY\ AEHHUL)fWEHV@Mf(Lfo-fofHLfDfxfoH ffpf`H fYfxfYf^f^f\fHbf\JH9uȃp9Hcf*AYDAL^\LP9Hcf*AYDAL^\L9uHcf*AYDAL^\LH[]A\A]A^A_AEfWu#@QfAL*AYD^\LHH9ufDJ1fDHDHH9u@QfAL*^AY\ HH9uAWAVAUATUSH$$HL$XL$L$DŽ$D$HL$u л)D$H4$J|$HD$f/ f$f.f(eeQYYX5f(\Y eD$HYXf* $Y X,$=z L=L@IHt.HxHHHǀH1H)HLHHt.HxHHHǀH1H)HLIHt.HxHHHǀH1H)HLwHD$@Ht.HxHHǀHH)H1HL2HD$xHt.HxHHǀHH)H1HLH$Ht.HxHHǀHH)H1HLH$Ht.HxHHǀHH)H1HL]IHD HxH1HHLHǀHH)HHD$8H HxH1HǀHH)HHЁHHM M H|$@ H|$x H$ H$ D<$L$LD$HDDd$1fW%Df(ЉD$ D$(D$|$H$D$0f. QT$(Yf(L$0LHꋄ$L$L$YDxf(DL$Llj$ $ $LMD$LL$8HL$xHT$@f(D$yHt$X$H hDLt$`A$Ll$hIHD$ Ll$@d$$SCYDC\f*D$BDY$\$PBYDCYDXD$PYD$AXAIv0f(fTƈf(Y\L$fT f/A.Il$L9|$ D$f$B 8*Ƀ)|BLBTCYLCYTCYD\YAXAJ$d$d$H$$H2$=ЅLt$`IAHT$ <$CYDC|f*D$PBDY$|$XBYDCYDXD$XYD$PAXAIv0f(fTNf(YJ\L$fT 4f/A&Id$L9|$ D$f$B 8*ɃtN-BLBTCYLCYTCYD\YAXANfDCYDBYDCYDAXACYDBYDCYDAXAwA^$ALd$H$MLt$`H$HI&+HD$f*BYDHD$8B4L$hD$PBDY$t$XHD$8BYDT$0CdBYDL$hXD$XYCDY$T$`d$XCYT$`CYDL$PXD$XYD$(\YAXAIv0f(fT+f(Y'\D$fTf/A/Il$L9d$ D$f$B *ɃHD$8BTf(BDC\BYTBYDCY\\CTYD$0CYT\YT$(HD$\BYLYAXA f[HD$8T$(CYTf(D$0BYDBYDCYTLd$$\$Hf.Qf(H$YE1A^$H|$8MtLH$HtHH$HtHHD$xHtHHD$@HtHMtLHtHMtLHD[]A\A]A^A_f$f.f(ZZQYYXGf(\Y ZD$HYXHD$XLl$hA^$A$Lt$`Ld$PMH$L|$xL$HI|$-@HD$PC4f*BYDL$pD$XBDY$t$`BHD$@BYDCYDT$0XD$`B$L$pYCDY$T$hd$`C HD$@T$hYD$XBYLXL$`YL$(\YAXEAEIv0f(fT~f(Yz\L$fT df/A]I\$L;d$ D$f$B *Ƀ3BLBTCYLHD$@CYTC\BY\\CTYL$0BYT\YT$(HD$P\BYDYAXEAE DHD$@L$0T$(BYLCYTCYLBYTLd$PL$$|$Hf.Qf(A^ $YH$E1$A~HD$XAH$H$H$Ӄ$f(A^$H$H$H$f(|$A^$|$f(HD$H $ $[LHD$8HttHD$8HxHHǀHH)HLH|HD$XAH$H$H$|HD$XAH$H$H$D$H\$H )VYVYXuBf(f(\T$~T$f(>D$HdH$f(D$HDt$H UYUYX:f(f(\T$ T$f(D$HT$(YD$H$$Vf.Uf(SHXY{|$L$YfEDL$|$f(fE.zuHXf([]fA.zIuG5zff(A\Yz,fD/*f.fA(fA(|$0D~}l$(HfAWDL$;DL$5zzD$zfA(DL$ Yzt$f(T$\gT$l$(Yf(^l$l$HR;t$D5yfE~ ||$0f(D-#zDL$ f(D~|fEfD*fA(A\AY,*f.93fA/v7\,ԃf(ָf*Y9ufAWAYYA^YXfTf(fTY>f/wAYl$HHX[]f(f. fA/sv4\,҃f(޸@f*Y9u xy\$AY\$-RHXf([]Y^f(fD(fDTfD/[A,`VfD(ffA(*Ѓ\DY9uffA(*\H=HfHnYHHX@H9uYfD/f(^oAYfD/_{t$@DL$8Y|$0l$(\$ T$DD$d$T$d$fEHIwDD$YF{D~UzfLnHiw~ 1y\$ l$(|$0t$@fLnDL$8Y^f(fD(f(fT-xf/,ͅQf(@ff(*ȃ\Y9uff(*\HNH@YHHX@H9uYf/f(^YfD/f(DL$Yz\$T$Z\$T$DL$YyY^9fD(f(~f(f(9f( f(f.fATfD(USHpY+vDT$ $AY%DT$fEf(fE.z^u\ $Y GuX OufD/s$<$fA.@:HpfA([]A\,f*f.ztfD $Y KuDT$TuT$L$T$Y^uD$htX$fWwYxL$fEDT$fD(f,*f.fA/-[t\,уf(ոf*Y9uD~*vfA(f(D5CtX f(HAYffEfD*fA(\$Ys,*f.nhfA/3v4\,҃f(ݸ@f*Y9uAYfW=xvfA(YAYXA^f(YYX^fATf/vfA.AEĄu#D$hHp[]YA\f(L$Yv)L$D$f(4 $Y sD$sDL$DYD^L$HpfA([]A\D~t-zrf(fATf/,̅Qf(ݸff(*Ѓ\Y9uff(*\HH@fDYHHX@H9uYf/f(^YfD/uD)\$0l$(YDT$ Dl$T$L$T$L$fEDl$DT$ Ylul$(fD(\$0Y^0f.fD(fETfD/kA,lVfD(ffA(*؃\DY9uffA(*\H=HfHnYHHX@H9uYfD/f(^7AYfD/'tD)\$Pl$`YDT$Ht$@|$0d$(Dl$ \$DD$T$\$T$fEHdpDD$YtDl$ fLnHd$(|$0t$@DT$Hl$`fHnfD(\$PY^afDf(fD(fD(f(:f(f(v"-oD~qZf(?f(?fHHf(L$Yd$Yl$D~ Hr5(od$$fD(~=ql$ fEWd$fE(DD$D\f(fTf(fA(Dt$HnDDnl$ DY )D~ qfHnDY$DD$fHnfHnd$~=zpDt$fDAYf*fD(DXYDXYfE(D\AYAY^Xf(^fTf/wuAYff/wf(HHfDfAWf(\$f(DD$l$Dt$ tDD$l$$f\$~=oA,*HmfHnfD.ff/Dt$ A,փfHnȃf.f*Y9uqYH|$8Ht$0\$L$T$f(\D$8L$T$\$YY\$0Yf(^Y$HHf(\f(fTf/0,υ2Qf(ָf.ff(*ȃ\Y9uff(*\HH@YHHX@H9uYf/f(^Yff/ofA(l$(\$ YL$DD$T$L$DD$T$\$ DYl$(DYof(A^b goMfA(f(f(fHn$H8f(YkL$d$Yd$~-mL$$f(d$fTL$f(=MkD$L$5jDYf(Dkd$\~-lD %f(\\AYYf(Y^f(f(X^fTfD/K$kAYfD(D\fE(D\D\AYfD(DXDYAYA^XfD(D^fDTfE/DYAYfE(D\fE(D\D\AYD%jDYAYDYA^XfD(D^fDTfE/D5iAYYfE(D\YfE(D\D\AYAY^Xf(^fTfD/*AYfD(D\fE(D\D\AYAYD%jDYDYA^XfD(D^fDTfE/D-,AYDYfE(D\DYfE(D\D\AYAYA^XfD(D^fDTfE/fDNAYfE(D\fE(D\D\AYAYD%DYDYA^XfD(D^fDTfE/D%AYDYD\fE(D\DYAYfE(D\AYA^XfD(D^fDTfE/D5AYD\fE(D\D\AYAYD5}DYDYA^XfD(D^fDTfE/?D5AYYD\fE(D\D\YAYAY^Xf(^fTfD/AY\fD(\D\AYYYY^Xf(^fTfD/gAYDY\fD(\D\DYAYYA^Xf(^fTfD/CTAY\fD(\D\AYY$YY^Xf(^fTfD/AYDY\fD(\D\DYAYYA^Xf(^fTfD/AY\fD(\D\AYYYY^Xf(^fTfD/wGDYD%\DYf(\DYDYf(\AYA^XDYff/wfA(H8~hDT$L$fWf(n~gL$$fDT$~-ffW,f(*HdfHnf.ff/\,ԃfHnЃf*Y9u5hYDT$T$\$f(\$Y$T$DT$H8DY^DXfA(DfTf/,,ͅ-Qf(f.ff(*Ѓ\Y9uff(*\HNH@YHHX@H9uYf/f(^Yff/#gf(L$(DT$ YT$d$\$Gd$T$\$DT$ YL$(f(fY^Kfqf(f(f(fHnIfDAWf(f(fAVAUIATIUHSHHHfT=bdYbT$|$ f(fT=RefV=eXYD,f(|$A*DAE1\t$(A)d$蚻|$fT$d$f/f.0*f(f(Yf(fEA-aAVf*X\Yf(f(Y\AMLHH9uHULH)HAYaEAO1f(HffLftfYf\A HH9uމȃtYT\TAMcIBD5AECD4HH[]A\A]A^A_@:Xf/D$ f(d$T$f(sX#ET$d$f(j-J`D$f(Xf(T$d$\$f(bET$d$f(-_D$f(Xf(sT$d$\$f( f/`f/9f/D$ f(|$d$f(T$T$d$f|$fD( 8->_AVdf(DE fDf(f*ƒ\XYf(YXf(A9|Hcƒu f(f*\XYf(YXf(\HyfA(AN^Ef(HfHHfDfHfYHH9uȃtHHDYEf/fT%E`HELH)HA EfD(LYQ^AOfo5afEfDo aHf(Lffof@H H fpfhfAXfAXfAfYfYf@fYf\fXfYjf\ZH9uf*LYXYD\A ԍPA9cfHcʃ*LYXYD\A D9.fHc*YTXYd\AfDL$(XE-\d$8|$0\l$(T$f(fW_L$,f(‰D$ l$(L$T$D$Xl$f(HcT$ f\$f(T$l$Hf|$0d$8D9H f(f*\XYf(YXf(DHykD5f/D$ f(|$(d$f(T$d$-w[T$D$ f(d$\f(l$T$fl$d$DD$ f(|$(fA(fEAfD(AVfDW ^f(AYf(f*AXfD(\\^\Hf(H9ulEYZ1f.LY\LA HA9'd$-aZT$D$ f(d$\f(l$|$(fDD$ d$l$f(T$YTZ1f.f\*YXYL\AHA9w|$d$fT$fD(Qf(fW\d$0|$(,f(L$T$D$ -bYL$T$D$Xl$f(HcT$ f\$f(T$l$Hf|$(d$0Df(=1f()AWf(f(f(AVfIAUATIUHSHHHfT5[fV5\fT=ZT$X|$ D,f(t$A*DAE1\A)Yd$Yt$fT$f/d$fPf/f/DWDf(fD/v AX,f(‰D$4d$(t$ DD$8L$T$L$DD$8T$D$A\f(HcT$4|$f(T$t$ Hfd$(DxO WA9nHff(ff(*YXXYf(\,HyEfHSLH)f/HAEfD(HYVAOLfo-YfDo Yf(5fEHf(Hfffof@H H fpfDPfAXfAXfAfDYfXfXfYf@fYfD\fXfYDRf\ZH9ufU* YXXYD\A ׍PA9~\fHcʃ* YXXYD\A D9}(fHc*YXXYd\AMcIBD+ECD/A$HH[]A\A]A^A_f/f/D$ f(f(t$ d$T$hd$DTT$D$fA(Xf(vt$ l$d$T$f(f AAUf(fY*X\f(f(^HH9ujfff.f(f/D$ l$ .f(f(t$d$T$l$ t$d$T$Y-f(Yk[f/D$ f(t$d$f(T$JET$d$t$f(DuSf(D$f(t$ A\T$d$f(l$t$ f(ŸfD9 Sff*\\Yf(YXHA9}Dff(*YXXYf(\f(A9|]d$DRT$D$fA(Xf(T$d$l$t$ ET$d$t$f(D+Rf(D$f(t$ A\f(f(ST$d$t$l$ fDHAY REAO1f(HffDf ftfYfXA HH9u߉ȃYXTAf(f(t$d$T$t$AUd=?+d$T$fD(C iQff(ff(*YǃXXYf(\A9|Hcƒu &f(ff(*YXXYf(\,HyfA(AM^Ef(HfHHfHfYHH9uȃ&HHY fYP1DPDf*YXAXYL\AHA9RYP1fDYXDAHA9f( 1Xf(A@AWf(AVAUATUSHH$)$f*ƉT$Y.Ot$|$X,f/ÉD$xHDh|$0HMcL$ I9L=^N$LL謫L$ DL$0HHMVLT$ M1LHDL$@L$0_LLdL$0DL$@HLT$ IIL1DL$PJL$@LT$0LD$ LLLD$ LT$0HL$@DL$PHJ1DL$@LD$0L$ ʢL$ LD$0DL$@HHM $fD$|*D$YɉЃ)Yȉ$$EG ft$xC A*Vf(Xf(Y$D$|Qf(fAnDfoPfpffD()\$ fopPHfDo5sfD( z)$fn1)\$0f(fp)$$)$f(m)l$Pf(-f)\$f(_D)D$`fEo)l$@fAofD(l$`fo$frfFfo$fot$0fDD$ ffDfEXfDX<$DffpfpfrDfEYfD(|$fD(fEXfpfpfDXfD(fEXfEYfE^fD(fDXfEYfDYDlfD(l$`fDXfX $fAYfD(l$fDXfEYfA^fD(fDXfEYfYLfA(fAXfEYfAYf\L$PfXfA^fYfAXA f(fXfYfYf(t$@f\L$PfXfXfXfAYfDYfA^fYfXALf(fpfXfYf(fXfYf^fA^fY,fYTH H9&DBD9\DTffJCfEf5J*r%KD$D$D*ƍ4D*ҍP*HcH4f(XXfD(f(DXY(KXAY^f(\\DYYAYDf(XAYAYA\\A^AYXfA*Af(\Y^AY׍PA9EDTffCfEfD*DZA*DD*A*f(XXfD(DXYf(XAY^f(\\DYYAYD5fA(AXYAYA\\A^AYXfA*AD0f(\Y^AYD7A9aDffAffE*DRA*DDA*D*fD(XfA(DXAXXAYY^f(\\DYYAYD5f(XYYA\\A^AYXf*AD0f(\Y^AYD7 fAnDfD(6$fpf(%`fDo5)$fnfHfpD)D$`1fEofD( ձ)$$)d$@f)\$Pfo~J)\$ foJ)\$0f()$f()\$f(fAofD(,$fűfo$fot$0frfDD$ fo$fDfEXffpfDX|$`DffpfrDfD(fpfpfEYfD(|$fEXfD(fDXfEXfEYfE^fD(fDXfEYfDYDlfD(,$fDXfXL$`fAYfD(l$fDXfEYfA^fD(fDXfEYfYLfA(fAXfEYfAYf\L$PfXfA^fYfAXA f(fXfYfYf(t$@f\L$PfXfXfXfAYfDYfA^fYfXALf(fpfXfYf(fXfYf^fA^fY,fYTH H9&DBA9PffEDfEfHcC4  ]E-E*D^D$D$E*D6D*A*f(XXfD(f(DXY%EXAY^f(\\DYYAYDf(XAYAYA\\A^AYXfA*Af(\Y^AY׍PA9DffEC4ff*D^E*D6D*HcA*f(XXfD(DXYf(XAY^f(\\DYYAYDf(XAYAYA\\A^AYXfA*Af(\Y^AYA9ffHcA4ff*DVA*D6DA**fD(XDXXXAYYf(XYY^f*A\\AYLf(\\DYYA^AYXAf(\Y^AYfDPBJD#It$jNT#~-;E~%#DAD 4ffD(f(D$$f(f(AIH{A0YL5ArA\fD(fDTYXfW^7f(fTfA/fA/Av9|`T$x)ƒaELAIMf HfAYJL9uEAAE9tHcHT Y Yf(f(Y!f~1HH觕|$|E1H=@HHDEffA*fW*\\YLH^YDX9}9~%?-HcfD=D~ @DH9|df(уt/EffEA*fAWD*A\D\YA^LYXfD(\fDTDYfTfD/vD$D$EAEAAff(A*Y%<f*҃XYD9~T$|+$AAAA~+%K=fDf*҃YYD9~fA(^YX^^Åt\A^Yt=Af(HAfIIf HfYJL9u@D9tHHDY009|fD$xDH)A)tDDHcf(HTf1HfDf fY HH9uDȃA9tHcHDYL$E1єL$LŔHH贔A@\$YGYXfW^}D9fD(A9}f(fD(Gf(>LLDL$0L$ 袗L$ DL$0HIMVM6LLDL$@L$ HD$0gL$ LD$0HDL$@HAHM$DEASG4D9Kff(1f(f(ffOf(fD(ff(1f(LLDL$@HD$0L$ 藖HHt`ML$ LD$0DL$@MyLLDL$@L$ HD$0WL$ LD$0MHDL$@HCAAH詒AL$A菒L$MXYAWf()AAVAUIATD$UASHA)H(CD%85t$fTfUfVf*AYX,Ѝj/P58t$ffA(ĉT$A*L$舏f(fW=l;GT$G4?G'DH&8CL&D-&8DZfEf(E1~%:5fLnff(D$DfW=:D)Ef(9}f*ЃY9uA<9~Df*ЃAXY9uB˃JY9T$fEfEE*MQfD(E*LDXfA(@H9 f(fEfE(E<D*fEE*fE(EXE\EXEXAYD\AYfE(EXAYAYfE(D\EYfED*EYEYA^fD(YXfA(fD(\fDTDYfTfD/3~PD$f*؃Y9~Y׃^CTM9t+M0fD(ƒD$Y^|$A|H([]A\A]A^A_Ã~f(MQvf.fAWAVA@AUAATUSHH-EHL$PHLD$@D$8L$T$gIHHxH1HHHHǀ8HH)@H@L$HH HxHHHǀ8HHDH)@HHDD$qAŃD$LHD|$8-4f(Y\l$E^fۺH54f.\$XHt$HE„;D)fA$*XD$,(D$0D$lD$D$0AAYD$~6DhI)\$ X\@fC4D$T$A*t$YD$T$XA ~^-fTD$ f/w IM9ufd$8fTd$ *T$`f(d$f(\$荊YD$HT$`d$f.%K3HD$P\$YzcuaE)AY$AD$HD$@X\d$Xf/d$8HE1XLPHĈD[]A\A]A^A_ 2f(T$x\$`Xd$L$Ή\$`d$f(fL$A*^D$Y\f(\$`蒉L$H|$lY 2A\$T$xYL$pAD$D$0AXYD$DhIXyffC$D$\$0A*T$Y\ 1d$YD$A \$0T$X~^-fTD$ f/w IM9uD$HYD$`Y\$pd$Xf/d$8HD$@YXcu{HD$@fWa4Ef|$XfD$A*Y 1BD$HHoAt7AtEHD$@HHD$PfW3HD$@H5 H00AY$HD$@~%2)d$ H@AHIH|IxLLAHIIǀ8H)@HL菉:A'IHtLlL$@AWAVAUMATAUHSHL=?T$@LL$D$L$ 舌IHHxHE1LHHHǀH)LH=AHI HPHHHǀHLHH)HD)ىAA9D$GD$ ,D$EDBPM.f(T$YT$ D D$f/f(H$DL$HH$DD$0\$Pt$8T$(HT$XT$(D$$DD$0$DL$Hf(t$8\$P^fW-L1^X^A.Af(\^AfY  /HT$XIN=rY^\~-/f(ANfTf/rL^fH*X\Y^\f(f(AfTf/ f(ȉƃ9}l$D$Of(Lfo%f(-ffDoS0HL@fofD`H H fpfDHfXfXfAfAYf^fD\fHfYfHDJf^f\JH9uB9fHcЋt$*I !IXY^\A ׍P9|[fHcʃ*A XY^\A$9|-fHc*XAY^\A f.D$ X~ Df*Y9u|$ fDE*D$@DYf(Yf(^f*Y +\|$8AJfD$ ~--f(|$(f(D +=oP f* \Yf*A\Yf*\^f*A\^DYDXA9}#fE(fA(fDT\DYfTfD/wHfA(A9lD$8DL$hDD$X)$\$x|$pDD$0t$`T$Pd$H袁d$HDD$XIEDD$0T$Pt$`DL$hA^|$p\$xf($D$0D$Gt$ HcˉD)fED*D g*HNI<ƸfAfA*D \YfA*A\Yf*\^f*A\^DA4YfA(YYDXfA(EE\fTE9}fA(fTfD(DYfD/HHA9fA(AÉfE(ufD(AHf(`LȅIHt7HxHHHǀHLH)HLAHĸD[]A\A]A^A_5(fATfA(f(^DL$xDD$ht$P$t$pT$`d$X|$HX|t$P;t$$D$0AYE|$Hd$XT$`DD$ht$pDL$x$AE  (D$ DD$P|$hDL$`\$pt$XT$Hd$~T$@fEDD$P|$hED*D^D^T$8EYUD$Gt$ HcˉD)DL$`~-[)fHD 9'D'I d$T$Ht$X\$pf*Ǎ<3\Yf*A\YfA*\^f*A\^DYDYAYXf(\fTE9}f(fTfD(DYfD/wFHHA9|+f(AfE(ufD(AH>f(fTf(^T$H$YT$0YAXXRzH$,$,9LE1LKLC+H$A ՅHf( }f(1HDA AHH9uȃgH5hHI4H5I4Jt$5pHt$8f/H|$xHt$p$d$wy $D$x\$p^f(\A^E~DA7f(t$P\^D$@AGAX^L$P\KHĈ[]A\A]A^A_fHcL,J)H9s J*H9oL1LxL1H xH>#IE~HHC덐d$fL$=0YD,EuAA*Dt$0Yt$Hf(|$Xwd$Y%$f(^t$Hf(d$ t$`vf$=A*YD$HDl$4Yd"YL$(\\f(\$v$D$ ^D$(v$D\$Y"L$YD$(\f(\-WDDE^ffD)!A*f*L$l$\^\D,A*Y<$uD$D$ ^$uT$Y$E9YW!l$L$f(\f(\-AE9`HD$8DD0EiHU%%"ffHnIcƐf(f*XXY^\f(AHyt$PT$@fT"f(fT%"f/d^f(օrf(LfHLDfHfY@H9utHIYHHKL)Hҿf(LOfo%effo=9#f(-qHLDfoH fH fpfXfXfXfYfXf^f\fPfYfPYf^f\QH9up9Hcf*XgAYAT^\ˍH9Hcf*X,AYAT^\9nHcf*XAY^AL\ kML$HIjML\$\MM|$HfDT$`fH$*L$hAf(*AYHH$0HYD$p$fX$*AG$E f(fnۉ1fpfD(f)$fE$fDo-wf( w)$HfD(%wffEo)$f(f(=~wf)$fo:)|$0)\$ f(hwfD(fAofo3f($frf(d$0fD\$ ffD(fpfDXf$fXfpf(fD(f(fAXfAXfYfXfYfXfD(fXfD(fXfDXfDXfA(fAX)d$fA(fAX)$$fA(fXfAYfD(|$fEYfDYfYT$fAYfA^fD($dfA(fXfDYf($$fAYfDYfY$fEYfD^DtfD(fE\fA(fAXfD(fE\fXfAYfA^fD($fA\fA\fXf(fAXfAXA$fA(fYfAXfXfAYfAYf^f(fAXfAXfYfAYfA^A|f^fXAdA\H H9DH9GC f fD$+ )D\$pAID$*fE(5 D$*AAHH4DXf(XfA(\YXAYfD(XD\AYfA(XfD(EYDYYA^Lf(A\A\X\AYA^XA f(XXYAY^AL9ffɉ)fE(**AADXf(XfA(\YXAYfD(XD\AYfA(XfD(EYDYYA^D5f(A\A\X\AYA^XAD4f(XXYAY^AD59ff)**DXf(XfA(\YXAYf(X\AYf(XfD(DYYYA^D5f(A\A\X\AY^XAD4f(XXYAY^AD5IcLcAwA,JH$HD$XIDH$x J SDT$0C4HL$CLT$H~% LD$ ID|$XAǐ)ȅ< DLf()H)HLf.ADYD^A H\H9uDfW^ADHL9uLD$ DT$01D|$XHL$Pf(fAYA Y HH9uH$(9 9 HcA DAYDA^\ALH9|ԅ A;$fEHL\$XE*LL$0fHnLD$ DT$$fA(D$$]D$LL$0$LD$ fA(HD$PD f(˃|$xHT$PXAY$DT$Y$L\$X$YD$pf(X\\$YCY ^BȍCH~AYDDHA9}ꋄ$DЉ ff(*Y pf*XY9~EHpYYEYHhXLE1$LA$L$H}.H}$ LAl$M Ɛfmf*YA*XEY ,f(YXHP@!P8HuxfL(PIXH`L0}fE]H`A*BtIuX\ =!YE]=If(Xf(\^fTf/v A  f(ED9wH`xf(L0L(HEf+XE*U` UDY8؃Pf(Yf*YE^@Y0(HXxf%H`HHuPHHHXHff(fHXE`*UlXY\ mYEU`PXf(\^fTbf/v HH;HmHXxHE|MLELMLEDY8X(U蛬E]U\&9Hpf(Y^@YYEX0HhXYXE7Hh#f(fHXU*`Xf(\A\ YDEELYEU`PXf(\^fTf/v HH;HaH`L0L(xHEf+XE*fDY8f(Yf*YE^@Y0(fHEfH}u'AM'LAsAMILOLGH}>L#fDAWMAVAAUAATA@USLH8H5HL$$L$T$\"H;L$HDD$HuAus\$f/D$, LL$p$IHT$L$DDE1AHYH8D[]A\A]A^A_LD$$MHL$DDZtAXE1fDAHHIHD$4DDPL$L$ D$\ZYtD$,xADIHLJ"f.USHcHH=i!H,H[]fSHcH=@!H[DAW AVIAUIATIUSHcH HCH= H,t`MHLDMtA}u\H-LL$LHڝL1X!AHtfDH []A\A]A^A_@ILLLL$!MLHHOLL1뉐H=ftIHt)t7HBHx HIt<SfHH5!HBHIxHIuLH=xBHttL}LfDHH5H"BHff.fHHL$8LD$@LL$Ht7)D$P)L$`)T$p)$)$)$)$)$H$HL$D$HD$HD$ D$ 0HD$HfDUHSHèuu2uHu^H[]fD1HH*t1HӛHt1HћHtHHHɛ1[]HHL$8LD$@LL$Ht7)D$P)L$`)T$p)$)$)$)$)$H$HL$D$HD$HD$ D$ 0HD$^HfDfff.ff.@GVf(Xd$d$\d$d$\\$\$d$\\$f(DD$|$Xd$A\\$\$X\\$\$\T$T$\$\T$t$l$T$\Xf(XXT$T$\T$\$T$\Xf(XD$D$\D$T$D$\ff.HHgnf(L$Y\$$$l$D$(T$(f(fW~\$L$Y\$T$(Y $XXf(Xf(D$0D$0\D$8T$8D$0HH\fH'._~f(f(d$(^\$H|$0l$Yf(t$ $pf($pfW|$0t$ D$pD$f(f(f(t$@Y|$8DD$$x$xfWYTDD$d$(f($xf(XXL$fA(X$$A\$$\$\fW$$\$$\$ $$\$(D$(D$ \$Hl$$A\f(\fW O$0D$0D\D$8$8\$@$0$8\f(AX$HD$HD$@$0A\Xf(AXX$P$P\$X$X$P\f(XXf(f($`$`\$h$h$`\f(d$(^\$0YL$$f($fWl$ |$8L$D$D$f(f(YDD$$$fW DD$$d$(\$0XXD$fA(f(X$$A\$$\$\fW4$$\$$\$$$\f(\$D$D$$$$A\\AX$$l$ fW{t$@L$\$$$\$D$$$A\Xf(XX$$\$$$\XX$$\$$f($X^D$PD$P\D$Xd$XD$P\f(X\$`\$`\\$h\$h\T$pT$`\$h\T$xl$x\$pT$`\XXf(X$$\$$$HĘ\ff.HfH)$Hofۺ'f.E„tf.%`DЄJHf/l$r ?Hf(f(d$ HBD~!H$D$(fAWH$$d$D~f(L$f(f(t$ Y$f($fAW d$ft$ l$f(D$$|$(YYXXf(X$$\f($$\$XT$hT$h\T$pT$p\L$xL$hT$p\$f(D$t$xXd$hA\$$$$\$$$\f(X$$$$\Xf(XX$$\$$$\Xf(X$$\$$$f(\ \L$8L$8\L$@ T$@\L$HL$8T$@\L$Pt$Pf(l$HT$8\f(XXXD$XD$X\D$`D$`\D$XHff(f(f.USH( nH$HD$f/s'f/mHHH$HT$r$L$H([]fgf.z!uf.zIuGH?1H$HT$=@f.|$Xz*u(f.z"u fo=z3)<$@=|$X-J3f( γ^XҲf(D$PfTf.v3H,ft$XfUH*f(fT\fVD$PL$P521d$0\$(H2f(t$ Y$hf($hfWd_L$Pt$ $h$f(f(Yl$$p$pfWl$$p\$(XX$f(f(X$x$x\$$\$x\fW $$\$$\$$$\$ D$ $$d$0A\f(\fWX$($(\$0$0\$8$($0\$@$@$8$(\Xf(XX$H$H\$P$P$H\f(XX$X$X\$`$`$X\AjYYf(f(<$Y\$@$f($fWܲ<$l$@$f(XYXf(YXf(X$$\ Y$$D$\1AYt$ Yf(f(X$$\$$\$$$\$f(D$D$$X$$\$$\$$$\f(A\$f(D$$$AXXf(A\XX$$\$$$\f(XX$$\$$$\l$0f(D$8f(AYD$xT$xfA(fW|$D$u|$D$f(t$ D$@T$x|$(YAYXXf(X$$\$$$\ G-t$f(L$ Y$f(l$`T$`fWƯt$ -L$ Y $fD(Y\$`|$(l$0d$8f(f(XAXXL$hL$h\L$pL$p\L$hf(уHX$$\$$\$$$\$f(D$D$$XA\$$AX\$$\$$$\$D$$$A\Xf(XX$$\$$$\f(XX$$\f($$\f(Yl$8$|$ l$0$f($fWt$xt$Yt$@|$ f([$\$(|$Hf(4$YXXf(X$$\$$$\ t$f(L$ Y$f($$fW\$(t$L$ Y $fD(Yl$0D$d$8f(fA(XAXX$$A\$$\$f(fTf/Pcv|$Hf(ѻ X$$\$ $ \$($$ \$0f(D$0$($XA\$8$8X\$@$@\$H$8$@\$P$P$H$8\Xf(XX$X$X\$`$`$X\f(XX$h$h\$p$p$h\f(@f(\$Y $$f($fWOJ $\$$f(Xf(YXf(YXXf(X$$\f($$\$X$x$x\$$\$$x$\$f($$$xX\$$X\$$\$$$\$$$$\Xf(XX$$\$$$\f(XXf($$\$$$\؃|$X,l$Pf(X$$\$$\$$$\$$$$\Xf(XX$$\$$$\ $f( $fH~f(fHnf(f)<$%f(ff(f(\f/vf(\f.Lf/f(Y56f/\YX5&YXYX5YXYX5Y\YX5vY\YX^\\^YY5Hf/X~YX58YX~YX5Y\~YX~YX~Y\~Y\~Y\~^vY^Ðf(DXXYYff.D5 f(-âfD(D%f(fDW `YX%D-/gDDYDDOYAYDYA\D\fA(YfA(\U(YX5fYA^\-0>Y\5-YX-fAYDYY\-f^-\%~'DXYDYD\fA(\%^fDXYf(X%a+A\DYA^YXvAXYXf(^5-AXAYY^XYX_\AYDXXDYAYEXAYX^X^X^XXSHH  G0fWXf/v f/f/@ S(S8Kfo k8f(S~(Kf(fTfTf/f(f(f(fTCT$Yd$l$d$T$ ~Xl$YYS`\f(ShfTf/ǃCfC8f/r f/K0f/ǃǃ&f/ǃ1f/ǃfDPtK=GXG0YG8f/r7GG(G8ǃǃPC0PfDf.Ghzf/Ghtƃf#f.zf/tc c(c@f(fc(f(fC8cf(HzHH [GXHozG0HH [=ELJ멋3DC(ffTf/vfWf(܋\Y[p;ǃfA(\f/{xv#fD(fW9fDf(=fAW{pu X[pf.z f/Kxf(Yf/f(Yf/v@^f(6fDLJ1f/LJXfDC@Hx#HSfs Nf(C0f/ǃǃDK@DS fA(fE(E\\D\D\A^E^{PAYAYDKHDY[pA\|ff.fUSHH bHf҃ZG f(f.ǃd1ҋf/…u uSf/vMKǃCpXCPCHǃC`H[]fK@ǃ\CPfǃCpd3fDx====AK@Cp1[ f/f/f/ȉǃSPYSX\SPǃCpCpCHǃC`@K1C f/1f/6f/ىǃ(CPYCX[pCPXǃx=?=t]=4=SC EXǃ=]1#ǃKCpMK8EǃfDf/fDǃǃǃff/ǃǃǃH C@CHǃC`O@G`f/Wf/LJLJ GHO`H[]G GHLJG(GG`H[]G O(1fGHf/Gw?f/f/s;HPsH@ǃCHH[]f/r`f/rmCHK`fT lYK0bǃZCPeGHLJIHrH6HLJ&HrH1CCHǃC`Ht%CHC`CHCHǃC`dff.H(L$D$T$L$D$f( DD$5 fD(-qfA(f(fD(^E^fD(DXA^EYA^f(fD(YDXfD(f(fD(f(pqDXEYAYDXDXA^AYXXDYY (qDXDXAYfA(X%qYXA^YAYXAYXpDYAYYAXAYYX pXAYY\%pYXYXY\pH(YXA^XfDf(f/:SH f/- kl$^pL$YY\pYXpY\pYXp^D$f(L$f(f(\5f(YXD$\XD$H [\,؅1f(ff*XY9uf(\$L$T L$\$\f*T$XD%`f/%f/<,f(\ oYf(\f(L$Y$fWY}L$$Yff/z\f(ff(tW WY-yY\\WYX xWYXLWYX hWYXKY\:KAYYX1KYX-KY\)KYX%KX!KY\KAYYXKY\KYX KY\KY\KXAYDJDYDXJDYD\JDYDXJDYDXJDYD\JDYDXDDYD\8AXY fA/^f(\ $f(Y\X=g%g\f.zf(QGJgf/s?f/ YKf(w1f(1 $l$(\$l$(\$ $f(f(l$(T$ $ $1H5fY @%"gl$(T$fHn^f(t$@^D)D$0l$(\$$f(Y;Y\YXoJYf(Y /\^A\\$f$Yl$(fD(D$0t$@Yf.zr Gf(t$@D)D$0l$(\$$l$($He\$f/fD(D$0t$@fHnf/fLnf(fLnDID\fHnfHnDXAYfD(DYAYDXAXfD(EYfD(AXfE(D\D^AYEYXDXfD(E^fE(E\fE(EYfETfE/sAYf(\fH~XfH~ YqHdfD\$XDL$(\$0L$@T$HfHnfD(T$Pt$`%GY kG\ kGY\%oGYX SFYX%7FY\ CFXYAY\ 6FX 2GY\ .GAYYX %GY\ !GY\ GYX EY\ EX GY\ FAYYX FY\ FY\ FYX EY\ EYX EYX EX FY\ FAYYX FYX FY\ FYX gEY\ cEYX _EYX [EY\ WEYX SEX WFY\ SFAYYX JFYX FFY\ BFYX >FY\ :FY\ DYX DY\ DYX DY\ DY\ DXEYXEAYYXEY\EYXEY\EY\EYXDY\DYXDYXDY\DYXi>Y\X\%0'1f(^L$pLHHC\Hcf(^Yf(fATf/rD/EfD/s,f(\f(^Yf(XfATfD/rf(HHT$hXHH9u^Xf(Y f(f(%q&1X^D$pDHHXfD(HcD^AYf/rDnDf(XfD(D^AYfA/XwHHT$hX HH9u^Xf(Y\fH~XfH~>t$`D)T$PL$HDD$@l$0\$(D\$H_t$`fD(T$PL$HDD$@l$0fHn\$(D\$f(4$ѵHr_4$ff(fHnt$HDD$@l$0\$(D\$莵H/_t$HDD$@l$0\$(D\$fHnf(4$O4$f(\$,$1\$,$ff(bfA(t$`D)T$PT$HL$@\$0DL$(D\$t$`fD(T$PT$HL$@\$0DL$(D\$f(t$`D)D$Pl$HL$@Dd$0DL$(D\$$vH^$ft$`l$Hf(fD(D$PL$@fHnDd$0DL$(D\$ fA(t$PT$H\$@DL$0D\$(Dd$H]ft$PT$H\$@f(DL$0D\$(fHnDd$fAW1f(AVAUATUfH~SH8f/H\$pL$ L$HH\D$@HLHH$H|$HH$H^f(f(D\fA(^f(l$(AX^d$XYfL$f.QfA(d$8^DT$ fHnfW|_^D$@|$0[YD$@fHn^|$HD$f(;L$HYXL$f(fW/_L$贵d$8L$DT$ D$hf.zVuTf(H8[]A\A]A^A_d$@f(D[^^f(t$(fA(AX^t$Xf.f(QX|$Y=fD(D^-?d$`DY-F[DT$PL$8 [Y|$|$pDl$ $fW 1^$fH~ =f/d$`DT$PDl$ t$(DL$0fLnL$AfE(fE(H?EYf(D|$8YY>DY>|$P|$XfD(XDX|$X|$X|$`fHnH$0HD$ DYd$PfICL$(A*ZHD$MAYXEXAXYL$X^[XBLL$`AY^B fD$EEA*AkLL$ YHAXYY$ Lʸf(fAfH*A)A*Y\YDHYBXH9ufDHpI*Y^XAAH9uCTHD$A^BTAfAMDffY$f(fXXifAMffY$XfX@fAMffY$XfXfAMffY$XfXfAMffY$XfXfAMffY$ XfXfAMffY$0XfXtwfAxffY$@XfXtOfAhffY$PXfX t'fAXffY$`XfX@DAt&A)AHMcBĀYXXfW*ZIIAUL;\$%f(AY=L;A\AYDY5;AYXt$8DYDYt$0DXAGDYAYDYAYAYf(fTXYXfT vXX ZDXAYf/sIIL$HD$@D\$fWɔYIB\$X&XD$(T$\\H0[f苔Y BT$Xe&XD$(\$H0[\\f|$f(\,Ѕ1f(@\f(Xf(^Y9ud$ L$T$XD$T$D$f(OL$D$f(:|$d$ \%VAH@XfHnf/fH~"f/f( \X\D$f(YYd$XfHn\XD$H0[f.D$f(T$ 苾L$D$f(L$pT$ L$D$Xf(Q\$\D$H0[Xf(\$L$諒L$\$f(fDXf(sf(+f.[f(f(fTAf/A?$X^#f(YXYYX#X#YY\#\#YYXX^YX1f(f\Ӄf(f(^X^Y9uf(T$L$舑L$D$f(L$ m\$T$f(f*T$Y\f(\$証T$L$ D$f(XD$XD$mXL$f(L$f(f(DD$f(T$;L$D$f(&L$T$|$H=XXmfHnf(\%>fH~f/sbf/f(sl\XBYD$f(?d$XfHn\f(f(XXf(f(f(6޹f(f(fT?f/^w}l=!X^d!f(YXYYXP!X`!YY\@!\P!YYXX^YX"XL$f(DL$f(USHHT$ L$\$D$f/{<d$L$T$ -kf(f/f/-;f(f(Xf/fH~f(l$ \$L$d$ǔf/;d$L$\$l$  f/7D$f(8T$f(f(\,х~n1f(\f(Xf(^Y9ul$ \$t$T$T$l$ t$\$\Xf(f(fLnXD\f/f(\$\L$l$蕖l$L$\$X^D$fA(l$ \$L$觽L$\$f(Yf(:l$ XY^D$HH[]|$f/@f/l$f(fT <f/n:f(fW=5j-9\^jf(YXYYX5>XNYY\5.\>YYXX^YD$l$0L$(d$ t$\$%t$d$ L$(\$Yl$0Y?f.f/f(59XYf(^f(X^^D$f(f(\t$f(fW;~5:^f(fTf/ ^T$f(L$8d$0\$(l$ M\$(l$ d$0L$8\~5i:^fTf/5qsD$L$8^D$d$0l$(\$ l$(\$ d$0L$8\f(Y܉d$YL$XfW:L$fd$f(D$Yf.QY_YD$f(LfW:/YD$HH[]fYl$f(^\f(X^^t$D$kDf(l$\$L$l$\$L$XD$g@f(HHf(fHn[]\Df(L$ d$\$ŶL$ d$\$fDf(L$0d$(l$ 荶~58L$0d$(l$ f(f.D$fHnl$(L$ d$\$VfT$\$f.d$L$ l$(frf(L$ d$\$T$藈T$H\$d$f(f(fHnL$ fT=7f/-5f(fW8=Y\^-Y5fD(DYXAYAYXX=AYAY\\=AYAYXX^YY@D$f(L$(d$ 蝇D$D$茇t$d$ L$(-4Y\$YD$f(9T$\$D$f(f(*L$XfHn\p\$Yf(fHnl$0X\$(T$ d$L$t$認t$l$0L$d$fD(f/T$ \$(7f(L$0\d$(\$ T$t$l$vl$t$T$\$ Xd$(L$0fD(D^f(l$ \$T$L$#L$f(f(l$ \$T$XXf(YA^Y^AYf(X^r-2D$L$(f(d$ \l$苅t$d$ L$(l$Y\$Yf(l$(L$ d$\$T$Il$(L$ d$\$XT$fD(D-82L$(d$ f(\D$\$l$لl$\$d$ L$(f(jL$d$T$1L$d$T$f.SfD(H@D 1f(f(XfD/AXwJYf/1fA(fA(d$8t$0l$(\$ T$L$DD$DD$H"1f(fL$T$A^\$ l$(fLnt$0d$8f.fD/ɍ{f/A\Y^A\fD/If*f/,f(9t~~|ff(D*XX^YYXf(AYf/r9>@ff(*XX^YYXf(AYf/s9uYH@[f(1D$sDD$f(A^H@f([ff(܅~f(1ff(*ʃXX^YYX9%0fD~vDkf(XX^YYXf(AYf/sB17@ff(*XX^YYXf(AYf/s9uYH@[f(Å~Df(XX^YYXf(AYf/s1;@ff(*XX^YYXf(AYf/{9uomfAVfSHhf.L$\$(E„lf.D„ZT$0f(fH~^D$ T$茂f/.Dt$ T$0$ f/|$(f/ f(fT/f/ -f(fW%0 Dg-\^f(YYYX XYY\ \YYAXAX^f(f(XYD$(DD$@T$8Dt$0L$ DD$@T$8Dt$0L$ AY<$YD$fA/XfI~NL$fA(DD$8T$0Dt$ zf/,Dt$ T$0DD$8fA/E4$D$ T$0f(L$ T$0f(f(A\,Ӆ~|1fA(A\f(Xf(^Y9ul$HL$@Dt$8T$0DD$ ~L$@DD$ l$HDt$8A\T$0Xf(<$fMnT$8D\\$0XfA/f(A\.\$0T$8AX^D$ fA(T$HDD$8Dt$@\$0迄\$0<$Yf(׆DD$8Dt$@T$HAXY^D$ D$8f(%DD*|$fD/f(AXEYfA(^D$f(AXfA(^^D$ f(fA(\|$0f(fW s-~=[,A^)<$fTf/=^f(DD$X^D$ Dt$PL$H\$@T$8|L$HT$8\$@Dt$P\DD$Xf(<$^\$fTf/=D$(DD$P^D$0T$HDt$@\$8 $`|\$8 $Dt$@T$H\DD$Pf(AYDD$8YD$T$0D4$XfW_,fD4$DD$8f(D$ YD$f.T$0KQYDD$@T$0Dt$ YL$$fA(萓fW+s<$Dt$ T$0DD$@Y|$8ff.fE(L$(fHn~-*E^AXfE(AX),$f-(EXfE(fE(|$ fE(L$(f(l$0EXA^fE(D^f(#f^fA(fD(fD(^fD(fA(fA(AXd$t$AXf(\AYYA^YA^YYf(YYfA(A^DXT$0XfD(EXXfA(^l$(YXl$ XYXfA(YY f(AYYXXf(^Yf(A\fT$$f/YD$8Hh[A^DD$ fInDD$@T$8Dt$0脀fL$ Dt$0f.DD$@T$8 Hhf[A^f.f(Dt$0T$ JyT$ Ds&Dt$0f(jL$fA(Y\$(f(AX^\^l$ L$0f(Dt$0T$ xT$ HUf(Dt$0f(fT'fHnf/=?&f(fW%(; D%f(\^6 f(YXYYX X YY\ \ YYAXAX^YL$fA(DD$0T$ D4$Mf(fIn\~D4$T$ DD$0D$8f(Iff(DD$@T$8Dt$0 $ΤT$8 $DD$@Dt$07f(DD$PT$HDt$@\$8荤DD$PT$HDt$@\$8f(}f.<$D$0DD$Pf(Dt$@T$HL$0D$ f(L$ fInX\f(}$Dt$@DD$PYT$8T$H|$8)fT$8\$0AXD$ ld$fInDD$HT$@AXL$8Dt$0d$ }d$ DD$HL$8Dt$0f(fA/T$@Bf(T$8A\L$0d$ L$0AXT$8fD(D^fA(T$0L$ ~fD(D$~fA($L$ AXAXYA^Y^Yf(T$0AX^|$8D"T$8Dt$0fA(\D$(DD$ 0uDD$ Dt$0T$8f(RDB"Dt$@L$8fA(DD$0\tT$ DD$0L$8Dt$@Gf(T$0L$ }T$0L$ AXfD(1DD$8T$0Dt$  $xT$0 $DD$8Dt$ }fH8$L$D$v5f!\$|$D$f/*f(f(EzH6!\$|$DL$f(fHnf/8H!f/fA(L$覝L$D$f(\,Ѕ~m1f(@\fA(Xf(^Y9u|$(\$ L$DL$RsXD$|$(\$ L$DL$D$$|$(\$ L$DL$ sH; L$DL$\$ fHn|$(\Y\$fD(EXfD(D\D$L$fD/fA(\{fHn\$XA^D$(fA(|$ \$DL$Ky\$fEDL$f(fA(\$^YfD(D$B{Hc\$|$ fHnXDYD^L$(fE.fA(H8$|$\$q\$|$f(Yf(f(T$ T$\f(xx\$|$fEH^fHnfD(fE.h_f/fA(fA(f(D ^D~m D^XfD(f(D^A\fD(DXXY$Yf(A^XfATfA/wYXDYfA(H8ff/fEfE(H8fA(f$f(tfEH\$fA.|$fD(fHnufD(\$DXfD/fA(e\LyHm\$fHnXfD(E^f(\$yfD(f(yfHn\$f(fA(XXYf(A^A^YDYQxfHn\$XD$(fA(|$(\$L$tL$DL$ D$fA(gD$$Wo\$L$XL$Y\v\$fEDL$ f(HS|$(fA(^fHnYfD(f9DwH \$fHnXfD(ff.ATf(f(ISXH~D A\A\fTf/%xfEf(fD(fA.f(z1u/fA.z`u^fGLHĘ[A\f.fA.zyuwfE.2,AD$fA$ fu`fDf(ЃAD$A$HĘL[A\@fGLHĘ[A\@fA.fE.{fA(f(t$l$DD$<$s=pDD$l$t$f/<$fA(f(t$l$DD$<$nl$fE==H&DD$f/t$<$~ fLnUfA/f(AXaYA\1fD/v&fH~f(fTfHnfH~fA(fLnifA/.fA/ifA/sAYf/f(f(fA(f(HPf(fHnfLn\DXȅufH~fA(fLnAD$fDE $fDE~rLAD$A$HĘ[A\fDf(fA(AD$AX^^fA $1fD/s"fH~f(fHnfH~fA(fLnDf(t$ l$AYfA(DD$|$D$lDD$H4D$|$fA/l$t$ fLn~"fA(fA(t$ AYl$|$DD$D$L$(l|$D$DD$l$f/t$ v!fA(L$(Yf/* fA(f(D\$ t$l$DD$<$ppl$fE=UH>DD$f/t$<$D\$ fLndfA/lf/-f/-V fD/Eff(f(f(fA(VH f(fH~fHnfLn\DXȅm^fDf(f(Y\fA(Yf/A,f*D\fE.zuHCfLnf(f(f(l$fA(t$|$D$Ul$fE="D$Hf(f/t$|$fLnrvfA.f(fA(f($$(H$$fD(fLnAXfA(\DXȅufH~fA(fLnAD$fDE $RTf/zf(fA(f(f(H5f(fH~fHnfLn\DXȅf/}bYf/gf(fA(f(zffA.f(fA(f((HfD(fHnfLnA\DXȅtfL~fE(fLnAD$fEE$[55HVf/fHn^fA(f(f(%2^XD^Y^DYX% f(^XfTfA/wDYDXDYfA(A\DXȅJ6f(f(,$DD$|$j,$fE yHz|$f/DD$fLnDfA(l$D$g|$fEH.D$l$f/t$fLnf/-fA.b f(f(fA(jHfD(fLnfA(A\DXȅtfL~fE(fLnAD$fEE $fA.f(fA(f(HsfD(fLnfA.uf(f(fA(H@fD(fLnfA(A\DXȅfA. f(fA(f(HfD(fLnfA(A\DXȅ&@DfD(D-EXf/DXnAYfA/D%EfA(f(f(Dd$@f(Dl$0Dt$(d$ t$l$DD$<$<$fEDD$f(l$t$^d$ Dt$(Dl$0Dd$@fA.fA/Bf/5fA(\Y^\f/ Hf/, fA(1ffA(*҃XAX^YYDX9|҃ffA(DA|*XAX^YYDXfA(AYf/r:@ffA(*XAX^YYDXfA(AYf/suAYXX=YfD(fD(EXEXfA/DAYfA/D%f(f(f(D\$@fA(Dd$0Dl$(Dt$ l$t$|$D$D$fE|$t$l$A^Dt$ Dl$(Dd$0D\$@fA.f(f/of/-}f(\Y^A\f/  f/,fA(̅x~ Bft8ffA(*XAX^YDYAXf(AYfA/rY\f(f(f(AXnH fLnfA(\DXɅufL~fD(fHnAD$fAA$fA(f(t$Y|$DD$,$d,$ fEHN DD$f/|$t$fLnfD/3ff(f(f(fA((KH fLnlH 1fLnif(<$D\$l$_<$fE H YfLnf/EfH D\$~DD$l$<$fLn$f/ f(\f(T$$$ _T$X|fEH ~57$$|$fD(l$fLn~DXfE(H fDTDY%EfHnX fD(f(D^A\Yf(^DXfTfD/rEXfWf(AYH 1fLn!f(f(f(ϿfA(l$t$|$D$D$l$t$|$f(f(f(f(AX7&c/fA(1ffA(*҃XAX^YDYAX9уIf(DD$(|$ T$d$l$5]l$fEHC$f(DD$(HD$hH+ D$Xf(d$fLnT$|$ fE/)D$pf(~ )$ fA(fTf/fE.D ~5 E^ A\fD( fA/v ~AYAXXdAYAYX bXbAYAYX XXXAYAYX NXNAYAYX DXDAYAYX :X:^fA(\ 1YDXDX$DX)yDX+DtfA(1ffA(*XAX^YDYAXf(AYfA/suYfA(1ffA(*XAX^YDYAXf(AYfA/suY~5 fE(;fA/vsfA(1HL$pD%AYHT$XD^AYfA(X XHAYAYHuX ^fA(A^\DXfA()t$0l$(|$ D\$T$d$Yd$fED\$HT$DX|$ l$(f(t$0~fLn~5 fE(fA(~DrfA(1ffA(*XAX^YDYAXf(AYfA/suYfA(1ffA(*XAX^YDYAXf(AYfA/ufE/V ~5 fA(f/Q,fE۾D*A\DDYA,fEۉD*DYSwA\YcuD=D\fA(Y+ȾufW΍AfA.)t$@l$0DD$(|$ L$T$d$YL$fEDH~D^f(t$@l$0DD$(|$ fLnT$d$DY~5fA( SfWfE(fE(=)t$@l$0DD$(|$ L$T$d$9YL$fEDH&d$DYT$|$ DD$(l$0fLnf(t$@~DYBff.ffH8f/Yf(-f(X^f/wl=f(\f(Yf/w.Yf/w$f.E„tQf.E„tCf(f(f)<$$L$H8^=<f(\f.f/wf/wf/wf/wf(H|$f(f(D$\$@H?1H$$HT$L$H8ff.f(f(f(Yff(X^f/^f/hYf/f/ Xf/f/f/H8HH|$d$fHn2d$fYD$L$f/XvfH~f(fHnH8 f(f/vfH~f(fHnf(f(fD f(f.f(fH8f/H?1f/H$HT$f/f(wyf/f(wof.кE„tf.E„uNf/wHf/w:f/w4f/w.f(f(f(H|$f(L$D$ fDf(f(f)<$$L$H8H?1H$$HT$L$H8ff.f(ff/f/5Tf(Xf/\f/wxf.E„tf.E„uWf/wQf/wKf/wEf/w?H(f(HT$ $H(f(f( f(f(f(f(f(f(ATffD(IUSH5yD-`DYA,fA(*\fTYf/kfA(T$8L$0Dd$(l$Dl$Ql$fEDl$f(D*Yl$ Dl$fA(Dt$A\\$"k\$\f(_XDd$(L$0T$8fD(HDYDt$Dl$f(l$ fA(X^f/5Vt$fHnfLnD\d$Y 1fED #DYfXf/w8fA/w1f.E„fD.E„oHfA(AYf/$fA(Dt$hXD\$`DT$Xd$PDl$@Dd$HDL$ l$il$H{D$fHnf(l$8XiL$DL$ \fA(DL$(L$0iDd$HD$fA(Dd$ OD$D$Ol$8T$DL$(L$0f(Y\L$l$AYDL$f(XXdVHDL$l$d$Pf(Dd$ Dl$@fHnDT$XD\$`Dt$hf/4Yf/~{fE(f(fA(fDDYfA/rT~Pf\fE(*DXA^EYYf(XA^Yf(DXAYXf/sf(fA(f\Xf.x Dt$`D\$Xf/fA(f(l$PDT$Hd$@Dl$8DL$0Dd$\$|\$fH~f(\$(NDd$D$fA(Dd$ MD$D$M\$(fHnDL$0fW f(Y\$DL$AYf(\D$Xf(XhTH1Dt$`l$Pd$@f(fHnHD\$XDT$HDl$8Dd$ DL$fHn>@f(Yf/r_fED*fA(XA^f(\DYfA(X\AY^YfA(D\AYXf/sA$$LAD$\XAD$HĐ[]A\fD^fHnA\\$UfDf(IDffEfA/fD/y\$f/if/_fA(fA(f(Dt$8H|$pDT$0Dl$(Dd$ DL$l$D\$pDt$8DT$0Dl$(Dd$ DL$l$ffGLHĐ[]A\fA(f(Dt$`D\$XDT$Pd$HDl$@DL$8Dd$l$茳l$D$0f(l$(KDd$D$fA(Dd$ JD$D$Jl$(T$L$0fW f(YDL$8l$f(\D$AYDL$XXpQHDt$`D\$XDT$Pf(d$HDl$@fHnDd$ l$DL$DDT$P\$Hd$@Dl$8Dd$DL$l$ cl$ fH~f(l$0cfHnDL$\fA(DL$(fH~]cDd$D$fA(Dd$ ID$D$IfHn\T$f(f(DL$(\$HY\$AYDL$Xf(X;PHDL$l$0d$@f(fHnHDd$ Dl$8DT$PD\$XDt$`fHn@f(Dt$`D\$XDT$P\$Hd$@Dl$8l$0Dd$DL$EbDL$fH~fA(DL$((bDd$D$fA(Dd$ zHD$D$iHfHnfWf(f(\D$fSH-ثD$f(fT^ $f/o|$ff(fWIfD(f(fT=(-f/fTfUfV|$f(,$T$@Y\$8Yf(Yf(D$f(X-f(^\f(|$(L$ [G$D$ GG%gY$$D$xf(d$0rt$ W%'H@$f(|$(f(\$8fTDL$@fHnf.f(DL$h\$X|$`LD$(D$FHd$(f(YfHnf(Xf(t$PL$8qL$8\\L$f(4Md$(=nD$pD$Xd$8|$(%FL$(d$8YfD(d$@DXfA(DT$8L$HZqL$H\\L$f(L\$XfHDT$8t$PfD(f/|$`fHnd$@DL$hdL$0ff/mf.L$(Ef.E„fEf(fE(f.E„tpff/bf/Xf(L$ f/Df/:D$0f(f(f(H$DL$hDD$`d$XD|$PDt$HDT$@t$8Dt$H$$DL$hfA(DD$`d$XXD|$PDT$@t$8DH,ffUH*fV\DL$0ffDW=ef/H?1ff/d$H$HT$wH?1H$HT$$L$H[ÐfA(fWH[&cfDD$H[ Dff/f/P\$ f/@f/6L$(D$0f(H$DL$`d$Xt$PD|$HDT$@|$8bHCfD$D$|$8DT$@D|$HfHnt$Pd$XDL$`ffEfE(fDffAXf(?f/AXt$@DT$8f/L$pfA(T$0D$YDt$hAYXd$X$T$PXIXL$`mDT$8D$HfA(kmDL$HDD$0DY$\$(D\Y\$xD\$fA(AXDD$8XHHT$PD$(fHnf(Xf(ld$X5D$0Xd$Pf(l\$0t$@T$xDD$8\t$8Yf(\$AXXGt$8$Dt$hl$pfD(D$0f(fD(D$HXfE(Dt$8Dd$(|$@L$`|$f(Dt$ fE(fHnD|$HfDf(EXEX^D$fD(XDXDXXXYf(^fA(YDYfA(AYXfA(\XfTTAYA^DYfA(AY^f(XDYYf/Dd$P$Dl$ Dt$8f(|$@D|$HXD\$pDd$XfD(X'DXY\$0DYL$(f(\AYAY^D^lf(D$fT~XDXf(XXfE(EYD\EYA^A^YYf/DYs^f(E\\5A^fA(DYX\A^f/AYDYf(AYXX>Yf(Y@fDHff/|$f(fHn$fHn\w6!@fxD$f(f)<$MffEfE(?fBD$f(f(f(ff.@ff/f(f(f(D~X\ )\f(fATf/f.f.AVUSHPf.%f/f/%D kfA/DL$ f(t$d$|$=DL$ fD~Bt$d$f(|$DYf.Q fA/DDYX XDYDX2YX FDYDX YX 4DYDX.YX D^A\fD(v fDW%f.fD(EQfE(fE(Z eEYf/%}DLAYEYfA(\DXAY^fD(fA(\ A^AXDZEYDXmAXfE(EYDXYEYD\5dD^ݭYDYA\f(fA(AY\AYA^X_!f(fA(fD(^\ ;AXfATf/ fA/DYfD/x  f(øf/f(1A\A\fI~|$(1t$|$ f/%Xv/f(ʡ^\XfATf/s{f(f(\$d$^nf\$f.f(E„uAf.d$D„u-=bf/WfD(D^fD.HPf(ø[]A^f.f(fDf(fD>f/=¡fDTfD/ ~f(\fW^ f(YXYYXX YY\\ YYXDX <^YfW1HP[]A^DV1f(P1f(8fWDf(|$d$t$8t$fd$|$DL$ f(D~rfDD7i\$@L$8D^T$0d$EYAY\PAYXCDYf(Y_D\YvD^fA(DT$fd$fDT$T$0L$8Yf.\$@D\fD(EQfA(d$@\$8L$0T$DL$R>DL$fd$@DY HW\$8D~L$0T$DYfD.L Mf(\D$A^=f(fATf/fMnD\DYfE(DYfE(fETfA/DX%5DYA\Yf/fETfD/rDY5+AYf/fA(fATf/r9\T$fATf(YD$(f/]f/Swf(øf=0\Yf/rf(ø@D$ \A^@\L$ fATkD$f(d$8L$0\$5d$85\$T$Yf/L$0d$\wk\$@L$8T$0$<d$D$f(ZDL$fd$T$0L$8D^\$@D~>f\$8;d$YfD(f(=d$fXT$L$0D~\$8DY^fD1f/5fI~@Ņt$(fX|$t$d$f(T$ Z|$fd$D~bt$f(Yf.JZfD(D^Yf/Bf/%g fA/TDX`Qt$|$ d$fA(fW|:D$q:\$Yb:\$t$ Yf/f(ad$|$ fD~uf(\\fI~fD(fD 8XWD%XYf/YfD/f(øf(ĽA\A\fI~?@DYfD/ f/Yd$|$t$g2d$^89d$t$fD~|$f.: Of(^\$ f(\f(X^f/f(f(Ľ\\fI~ff(ÉDj\1~ff(1fD/fD.ztfA(|$8t$0DT$(d$:1d$D Sf(fWofA(d$ \DL$T$AXD$f(0D\$T$f(DT$(DL$fA(f(d$ t$0Y|$8\fA/K fA/C fA(f(9;|f(DL$8t$(|$0\$@T$d$[d$T$Hf(\=_Xd$fHnf(T$fWVY|$T$ 16YT$ d$t$(|$0DL$8f/ \$@d$ f(\$/|$\$Xd$ YfW=D~t$(DL$8fD(f(|$0D^f(\T$fA(fATf/fA(AXD^fD(DYXAYEYXDXAYEY\D\AYEYXDXA^Y\DL$@|$8t$0f(d$(L$ T$r.T$XL$ \$D~d$(^t$0|$8YDL$@\\$f(fATf/ɿX^fD(DYXAYAYXXAYAY\w\AYAYXX^Y\f(DL$@|$8t$0d$(\$ DT$T$L$Dd$HXT$L$\$ DT$X-d$(t$0|$8YDL$@T$f/Df(^ Xf(YfA/Xwf(t$0|$(DL$ \$d$,L$\$d$\XL$^f(D3D$Y,d$\$L$t$0Y|$(D%޾D~eDL$ \\f(\^ :\Yf(ŸfDf(fATf/GyQf(fW M\^Uf(YXYYX)X9YY\\)YYXyXq^Yf(|$t$ Ud$X^f(t$^|$d$XHfW/1t$|$fD~d$}f(DL$(|$ t$d$T$*d$ T$f(\f(d$#5DL$(D~|$ t$f(d$LDXL$(d$fA(^0d$L$(f(f(f(X5d$ ^T$t$^XYX)T$XT$d$ \^f(0L$(f(^D$Xf(T$^YXl)T$XT$d$ \d$^f(#0Hd$f(L$(fLnf(^\$d$ DXL$T$A^X1Yf(^XYX(T$XT$d$ \d$^f(/L$d$f(t$0|$8DL$@D~Yf/yY TDd$Hf/fD/hTpt$d$\|$(|$d$t$f(2DL$(|$ Xt$d$\$'\$d$t$|$ D~DL$(DL$@|$8AXt$0d$(L$ T$n'T$L$ d$(t$0|$8DL$@f(DL$Ht$8\T$0|$@d$(\$ L$'\$ DL$d$(D$f(fE(XD\d$AYf(XYX\XYAX^&L$YL$T$0d$t$8|$@D~DL$H\f(\cf(DL$@t$0d$(T$ |$8L$!&L$X K|$D$7^X%|$Y|$T$ DL$@D~t$0d$(\|$8f(\f(\$@L$8T$0DT$d$)\$@L$8T$0d$fD(DT$f(DL$0|$(t$ Dd$T$d$(DL$0fD~Y|$(t$ fD(Dd$T$d$DL$(|$ t$d$T$\(DL$(fD~|$ t$d$T$ff.f(fHf/%f/r}f/f/f/f/Ddf(Xf(fT5hA\A\f/5޶vlfGfU @fTf@f@fT@H(f(H|$FHD$$L$f(<$@H@8H(f.fGHGffGHGfAW1fAVIf(AUATUSHf/H$L$HHHH$XHH$HhH$H5f/f/f(f/f/6f/D~Xf(fAT\~\vf/f/l$@H\$T$.$tf$h8\T$\$L$$$D$$a$xfD~f(\l$$$f/$P$p$|$p$|$D$t$`A$D$|$x$H$$D$`|$P$$@$D$|$X$($ $$D$D$+ E1E1E11E1f/D$oD$nD$m t_BPq=fD(DYfD/fA(f(E1APfD(AA u@t D$|$mt$|Et$$EtD$p|$ot\$p$\$x$|$nt D$Et$@$ $($XH$f(H$t$f)$`[\Rf.=;AFfAfTAfHĘL[]A\A]A^A_@d$5fAFAfTAff(fA(fATfATf/vVf.zf/tD$oDT$x\$pD$nfA(fE(fD(fD(fD(f(AfA(AfA(D$Xt$HfATT$@YL$P\$8DT$0Dd$(DL$ l$Dl$'$T$@fDL$ YDd$(f(DT$0D~AXY=\$8t$Hf(A\fD(fETfD/ODl$l$A _P=fD(DYfD/fA(f(E1APfD(AA uH\$ T$l)$tf$h \uxl$T$\$ l$\$T$7\D$H$)$tf$h T$\$\tfAFIFA0fD$mf(f(E1fD(ոPAA{f(fA(fATfATf/vVf.zf/tD$oDT$x\$pD$nfA(fE(fD(fD(fD(f(AfA(AfA(D$Xt$8fATT$0YL$P\$(DT$ Dd$DL$l$HDl$@Z!T$0fDL$Y)Dd$f(DT$ D~&AXY=\$(t$8f(A\fD(fETfD/Dl$@l$HA2fDt$`fD.zfD/t A[fE1Q$hHH$t fAFIFABEEL$Et D$Et $=$h\fAFIFA%fAFAfUANfD/fD/L$$$h\$fAFAAfDEtD$D$@o|$ms$||$nmEt$$EtD$pD$|$otT$p$T$x$f$$@)$ f/fATvfW$fA($@\Y$0-DŽ$|fA(\$8f/v(f(fWXffW5fW-D)$0$u X$0f.z f/Lf(Yf/:f(Yf/^$Pf(AXHLf$D$D$H$tf()$$f)$`D|$`fD.z fD/A$f/rf/$f/$}$f/eD$mf(f(E1fD(ոPAA9H5fHnC$P$Pf(E1Hf/D$oE1E1E1D$n1E1D$m 3tbP=fD(DYfD/fA(f(E1APfD(AA ufA/D$mf(f(E1fD(ոPAAPfA(f(fATfATf/vVf.zf/tD$oDT$x\$pD$nfA(fE(fD(fD(fD(f(AfA(AfA(D$Xt$HfATT$@YL$P\$8DT$0Dd$(DL$ l$Dl$ T$@fDL$ YDd$(f(DT$0D~AXY=\$8t$Hf(A\fD(fETfD/2Dl$l$A D|$`fD.zfD/tA5fA/L$E1$fD($fD(f(\A\E\A\A^^$AY$YAY$0\yD$$$D$oE1E1E1D$n1E1$D$m$$D$D$ $tOP=fD(DYfD/rufA(f(E1AfD(PAAfD/:fA/D$mf(f(E1fD(ոPAAXD|$`fD.z fD/OA{f(fA(fATfATf/vVf.zf/tD$oDT$x\$pD$nfA(fE(fD(fD(fD(f(AfA(AfA(D$Xt$HfATT$@YL$P\$8DT$0Dd$(DL$ l$Dl$T$@fDL$ YDl$f(l$D~AXY=Dd$(DT$0\$8t$Hf(A\fD(fETfD/AE1-ATf(1IUSHf(H$Hl$0H)$HHf(H-u)$0f(}(H$@H$Xff/H$f( f/f/f/f/f((f/f/fD(?f/5f/RfD(~ND -DĢDXfA(fTA\A\fA//f(AXfTA\A\fA/5I$AD$fUA\$-@ I$AD$fTAL$HL[]A\I$LAD$fTAD$H[]A\I$LAD$fTAD$H[]A\AI$AD$fTAD$bI$AD$ID$CDI$AD$fDUET$H$Hd$(HDD$ |$t$l$$Hl$t$|$DD$ f/d$(fA(f(f($`d$ DD$|$t$茹t$HH\$ N$Ht$|$DD$d$ t$`AD$ID$A $f.f(f($`fA(d$ DD$|$l$ܸl$HH\$ $Hl$|$DD$d$ tK$t(HBqfHnAD$A $AD$JH fHnff.ATf(1IUSHf(H$Hl$0H)$HHf(tHp)$0f(#H$@H~$Xff/H$f( ,f/f/f/f/f((f/f/fD(?f/5f/RfD(~κD DDDXfA(fTA\A\fA//f(AXfTA\A\fA/5I$AD$fUA\$-@ ;I$AD$fTAL$HL[]A\I$LAD$fTAD$H[]A\I$LAD$fTAD$H[]A\AI$AD$fTAD$bI$AD$ID$CDI$AD$fDUET$H$Hd$(HDD$ |$t$l$`$Hl$t$|$DD$ f/d$(fA(f(f($`d$ DD$|$t$ t$HH\$ $Ht$|$DD$d$ t$`AD$ID$A $f.f(f($`fA(d$ DD$|$l$\l$HH\$ $Hl$|$DD$d$ tK$t(HlfHnAD$A $AD$JHfHnff.fHf/f/f/f/-f/f/f/Dڴf(Xf(fT5޶A\A\f/5THf/f@H@(HDf@H@Ðf/vf@`fD%PfDfGHGff@fU`fGfUH|$fHD$f(f(@ATf(1IUff(SHf(f/H$Hl$0$H)$HHf(_Hh)$0@H$XY$`D ,fD/f/fD( fD/f/f/f(fD/f/2fD/'f(~˴DJXf(fT\ \ fA/:f(XfT\o\gfA/:I$AD$fAUAL$);I$AD$fTAD$HL[]A\AI$LAD$fATAl$H[]A\fDI$AD$fAUAl$@I$AD$fAUAl$bfI$AD$ID$:I$AD$fAUA\$H$H|$Hd$(T$ DD$t$X$H|$ft$DD$HҰT$ fD/d$(fLn)fD$`f/f(HHd$ A\T$|$DD$$ $HfDD$|$T$d$ t$`AD$ID$A$f(f(d$ T$|$t$kt$HH\$ $HfHt$|$T$d$ fLnO$`f/rfA(HHd$ \T$|$t$$ $HfH3t$|$T$d$ fLnt@f(f(d$ T$|$DD$jDD$HHA\$ $HfDD$|$T$d$ R$t f(AD$A$A|$AAT1f(IUfSHf(f/H$Hl$0HH)$Hf(H5e)$0f(H$@H$XH$D fD/f/f(fD/f/fD(f/f(fD/f/1fD/&fD(~Y9DВDXfA(fT\\fA/6f(XfT\\fA/?I$AD$fAUAL$-@ˬI$AD$fTAD$HL[]A\I$LAD$fATAl$H[]A\I$AD$fAUAl$@I$AD$fAUAl$bfI$AD$ID$:DI$AD$fEUET$H$Hd$(HT$ DD$|$t$$Ht$|$fHhDD$f/T$ d$(fLn(fD$`fA/f(HHd$ \T$DD$|$$ O$Hf|$DD$T$d$ t$`AD$ID$A $fA(f(d$ T$DD$t$t$HH\$ $HHEt$DD$T$d$ fLnP$`fA/rfA(HHd$ \T$DD$t$$ ,$HHƩt$DD$T$d$ fLntfDf(fA(d$ T$DD$|$|$HH\$  $Hf|$DD$T$d$ S$t(HG`fHnAD$A $AD$?HfHnAW1fAVIf(AUATUSHf/=H$T$H\$HH $xH$H^H$hf/f/f(f/f/f/f/D~!f(Xf(fAT\\f/f/t$H*H˧f$fHnfHn$\ƒFt$L$fD(D~$t$f/t$f(*\$$$8$f/$p$$hD$x$ $$l$hA$D$L$XD$$$$$D$$@$D$D$`D$H$`$$D$D$ f/1 T$pE1E1E1D$w11E1D$vD t_P=fD(DYfD/YfA(f(E1APfD(AA ut D$@t D$p$Et$$EtD$|$wt!t$x$$$ |$vt D$Et$`$@D$H$HD$xH$fA(D$f)$f(A\UDAFfAfTAfHĸL[]A\A]A^A_@fAFAfTAffAFIFAfAFAfUANDf(f(fD(E1PD$pAAf(fA(fATfATf/vYf.zf/tD$wD$t$xD$vfA(fE(fD(fD(fD(f(AfA(AfA(D$`t$@fATDD$8YL$XD\$0l$(T$ DL$\$PDl$H/T$ fDL$YHf(l$(D~AXY עD\$0fHnDD$8t$@fD(E\fE(fETfD/Dl$H\$PAzf.D|$hfE.zfE/t AfE1H~D$H$gf.fA/f/f(t$f(Xf/L$\f/f.E„tf.E„lfA/f(]fD/Rf/Hf/>f(fA(f(H$螅Hf$D~qfHnEL$EGEt $==$\f(fAFIFATHl$GHf$fHnfHn$\Ѓugt$f/t$l$f(\fH~@HH$8Hf$fHnfHn$\Ѓtƒ7$f(AFfAfAyfAFIFA\ElD$t D$@D$p$|$vu $Et$$EtD$D$|$wt!l$x$$$ fÃ$$`)$@fA/fATvfWLfA(ɋT$p$`\AY$PY$DŽ$A\$Xf/v(f(fW ffWPfWء)$P$u X$Pf.z f/f(Yf/fA(Yf/^$pfD(D$EXfA$Hz)$$ fA(H$D$f)$"D$$f/r fA/f/$$f(\^f(dD$p8f(l$f/f(f/f(s{t$f(f(Xf/wcL$\f/wSf.ĺE„tf.E„u2f/f(w(f/w"f/wf/wH$$\l$H$86Hלf$fHnfHn$\Ӄ$f(I$pfD(6D$f/[T$pE1E1E1D$w11E1D$v tcP=fD(DYfD/fA(f(E1APfD(AA u<fA/f(f(fD(E1PD$pAALf(fA(fATfATf/vYf.zf/tD$wD$t$xD$vfA(fE(fD(fD(fD(f(AfA(AfA(D$`t$PfATDD$HYL$XD\$@l$8T$0DL$(\$ Dl$T$0fDL$(YHĚf(l$8D~AXY D\$@fHnDD$Ht$PfD(E\fE(fETfD/gDl$\$ ADt$hfE.zfE/t(A!fA/L$$ME1T$pE1E1E1D$w11E1D$v /t^Ptv=vfD(DYfD/fA(f(E1APfD(AA ufD/fD/L$?f(fA(fATfATf/vYf.zf/tD$wD$t$xD$vfA(fE(fD(fD(fD(f(AfA(AfA(D$`t$PfATDD$HYL$XD\$@l$8T$0DL$(\$ Dl$T$0fDL$(YyHf(l$8D~wAXY RD\$@fHnDD$Ht$PfD(E\fE(fETfD/%Dl$\$ A!Dt$hfE.zfE/tAAHf(f(fD(E1PD$pAAE1$ $D$f(fD(\A\E\A\A^^$0AY$(YAY$P\MfD/g$D$pL$D$w11D$vE1E1E1$t$pE1$D$D$ tOP=WfD(DYfD/rxfA(f(E1AfD(۸PAAfD/fA/-f(f(fD(E1PD$pAAUDt$hfE.z fE/_Axf(fA(fATfATf/vYf.zf/tD$wD$t$xD$vfA(fE(fD(fD(fD(f(AfA(AfA(D$`t$PfATDD$HYL$XD\$@l$8T$0DL$(\$ Dl$KT$0fDL$(YH#f(Dl$D~AXY \$ fHnl$8D\$@DD$Ht$PfD(E\fE(fETfD/AE1ff.f(fHf/r_f/r9HeYf/wc cf@H@HfGHGffGHGfYH|$f(f(HD$AVf(f(AUATIUSHf/<D,1Hl$ ff(yH$f/HHH)$f(uyHm)$ f(H$$H5Hf/rzf/f/f/f(Xf(fT\\f/xI$AD$fUAL$0I$AD$fTAD$HL[]A\A]A^@D,fDf(I$AD$Ad$fH$HT$Hl$\$$8f\$T$fYl$A*f/t$fI~=?fI~YHёfHn\fInl$$XD$f/HH$8l$f gY$Pf/vfInl$0l$f(@5fI~,HH\$$8\$f f(Y$Pf/vfIn\$\$\fIn$XD$f/r$PAD$ ID$A$I$AD$ID$$Pt"AD$ID$A$D$tAD$A$Ad$HBjfHnfDAVf(f(AUATIUSHf/lD,f(u1H$HHl$ )$f(uHHHF)$ f(&H$0Hi$Hff/H$ Yf/r{f/f/f/uf(Xf(fT-)\- \-f/-tI$AD$fUAt$1 ˎI$AD$fTAD$HL[]A\A]A^@f(I$AD$AL$fD,fDH$HT$Hd$\$$8T$f\$Y d$f/fI~f/Hf5IA*fHnt$\Xl$fI~@HH $8 |$$fInf/|$v$PAD$ ID$A$f/^fA*t$5t$*HH\$w$8\$uufIn\$Y$P\$\$XD$f/D$v=fDI$AD$ID$f$PAD$ID$A $f(f-A*\l$|$XfI~HH$8u|$$fInf/|$vwf=LA*|$l$"HH%$8d$fInd$Y$Pnd$\$XL$f/L$v$t(HBfHnAD$A $AD$HVefHnf.ATISfH~H $ |f$$Hgf/$fHnf(rf$f/ FD$fHn$Bf$d$f/f(rQf/f/@f(f(4AD$fLID$A$H[A\fDAD$fLID$A$H[A\fAD$fLID$A$H[A\f.AD$fLID$A$H[A\f. f;xYf/f(vYI@ATf(1IUfSHf/D$f(Hl$ f( oH$H)$HHf( oH)$ f( H$$H mNf/ CT$`fT$f/D$ Df(5ff/H$HD$H$8T$f/>wOfL$T$2\D$HH$e$8T$$Pff/wf(T$fdMI$AD$L$fTAD$HL[]A\f$Pff/vY mf/ f\D$HH$$8t$Pt*AD$LID$A $H[]A\$HfHnAD$A $AD$0I$LAD$ID$H[]A\I$LAD$ID$H[]A\fzfPYD$- AV1f(عATIfUSHf/$Hl$f(H$Hf( kHHHjN)$f( kH$ Hc)$f( [H$$8% f/ T$0fT$f/fI~G gAf(ff/H$HD$H$(uofInfT$f/Zf/z;@$@fInT$/\$HH$&$(T$t$@AD$ID$A $6fJI$AD$ $fTAD$HL[]A\A^ÐI$AD$ID$@I$AD$ID$@$u-HfHnAD$A $AD${DHALfHnDf(\4$fI~fHHL$$(t@-hfInYfI~-f(\$HH$$(fInf$@f/vY fIn AVf(1ATfIUSHf/D$f(Hl$ f( hH$H)$HHf( hH>)$ f( )H$$H# sf/ T$fH˂T$f/D$fHnf(ff/D$H$HHX$8'|$ff/wCL$D$_,\D$HH$$8$Pf/7wL$ffY df/vD$YP3뒐fFI$AD$L$fTAD$HL[]A\A^I$AD$ID$@f(\t$fI~HHL$-$8t$PtCAD$ID$A $ufDI$AD$ID$P$u-Hf<fHnAD$A $AD$Dfff.ffHf/f/uf/H8f.}Yf(f(-X^f/=f(\f(Yf/w9Yf/w/f.Eфf.EфfDf(f(f@H@ H8DfGHGÐfGHGf^= f(\@f/vf/lf/bf/Xf(H|$f(HD$f(bl$d$HD$/fGHGf-p~f(lfATf(1IUfSHf(df/H$Hl$ H)$HHf(cH%X)$ f(H$$H}f/f/f(f/f/f(7f/f(IDx}f(Xf(fT |A\A\f/ bI$AD$f(fUAT$.D#}I$AD$fTAD$HL[]A\f(I$LAD$AD$H[]A\DH$HT$H|$t$$$$8f$$t$|$T$f/$Pf(4$T$|$]x4$HH\$$84$f|$T$t$PAD$ID$A$$Pf($$T$|$w$$HH\$$8$$f|$T$tkf.I$AD$ID$BI$AD$ID$"$tAD$A$Al$H"UfHnfDATf(1IUSHf(`H$Hl$ H)$HHf(`H1)$ f(H$0HT$Hff/H$f( Lzf/f/f/f/f(8f/NDyf(Xf(fT|A\A\f/w_I$AD$fUA|$/fD yI$AD$fTAD$HL[]A\f(I$LAD$AL$H[]A\DH$H\$Ht$l$$$v$8$$l$t$\$f/Df(f(,$$P\$t$t,$HH\$,$$8t$\$t$PAD$ID$A $f(f($$$P\$t$It$$HH\$l$$$8t$\$tkf.I$AD$ID$:I$AD$ID$$t(H.fHnAD$A $AD$HQfHnf.ATf(1IUSHf(]H$Hl$ H)$HHf(]H=.)$ f(H$0HQ$Hff/H$5vf/f/f(f/f/f(8f/NDmvf(Xf(fT qxA\A\f/ [I$AD$fUAT$/fD vI$AD$fTAD$HL[]A\f(I$LAD$At$H[]A\DH$H\$H|$l$$$$8$$l$|$\$f/Df(f(,$$P\$|$Iq,$HH\$l,$$8|$\$t$PAD$ID$A $f(f($$$P\$|$p$$HH\$$$$8|$\$tkf.I$AD$ID$:I$AD$ID$$t(H>+fHnAD$A $AD$HNfHnf.f(fHf/f/f/f/H8f/f/)H|$f(H|$sD$ D$L$HD$tmf@ H@H8f.fGHGffGHGf rf@H@H8DfGHGÐfGHGff(nHD$AWf(1AVfAUATIUSHf/$f(,XHl$0H$HHH)$f(XH:L)$0f(H$$X|7f/ f/fI~fI~f(fInf/f/qH$H\$H$H\$f/'Ll$wpfDfInfInL\$qD$T$ \$\$$ zHH\$i$H\$#$`ff/wf(\$$ @f\6I$AD$ $fTAD$HL[]A\A]A^A_DfInfInl\$HH$ $Hu{$`ff/wf(fI$AD$ID$wI$AD$ID$WI$AD$ID$7$`tRAD$ID$A $ D$`AD$ ID$A$f.$t fAD$A $AD$HnIfHnfAVf(1AUATIUSHD$f(THl$@H$(HHH)$f(TH&)$@f(cH$PHH$hff/H$ F .4f/4f/fI~f/f/H$Hd$H\$$XjfInfT$\$f/f/$Ll$ w?HH\$T$A$XT$\$fInL$p\$T$nD$ T$0\D$T$\$$0t$pAD$ ID$A$2D$ 2I$AD$fTAD$HL[]A\A]A^f$pfInT$i\D$HH$0=$XT$t$pAD$ID$A $tfI$AD$ID$LI$AD$ID$,I$AD$ID$ \D$fI~DHHL$0m$Xt4@$t(H&#fHnAD$A $AD$HEfHnfAWf(1AVAUATIUSH$f(tQHl$0H$HHH)$f(YQH")$0f(H$@HcE$Xff/H$% 0f/f/fI~f/fI~f/H$Hd$H"$HBfInf\$f/f/ !Ll$w1DHH\$$H\$fInfInL$`\$jD$T$ \$\$$ t$`AD$ ID$A$-$ /I$AD$fTAD$HL[]A\A]A^A_Ð$`fInfIne\$HH$ $Ht$`AD$ID$A ${I$AD$ID$[I$AD$ID$;I$AD$ID$\$fI~fDHHL$ $Ht<@$t(HfHnAD$A $AD$HBfHnfAWf(1AVfAUATIUSHf/$f(NHl$0H$HHH)$f(NH)$0f(H$$Xl-f/ f/fI~cf/fI~4f/d$$H$HH$HpfInfT$Ll$f/w\"fLgD$T$ \$T$$ RHHT$q$HT$T$fInfIn$`f/Rwb\$T$$ DfL,I$AD$ $fTAD$HL[]A\A]A^A_DI$AD$ID$@I$AD$ID$@f(\4$fI~fHHL$ m$Ht$`tSAD$ID$A $LfD$`AD$ ID$A$ f.$t fAD$A $AD$HffHnffHf/rSf/f(f/v_f(HY3ef/wef@H@Hf.fGHGffGHGff(H|$f/eHD$f(f(rf@ H@H@fGHGÐATf(f(fIHf/-Adf/r{f/f/f/f/Dcf(Xf(fT5eA\A\f/5tIvrHGfU@I$AD$ID$HLA\@I$LAD$ID$HA\@f(f(\$Ex\$xcAD$^ID$A$DHGHGoDHGHGODI$AD$ ID$+fAV1f(ATIfUSHf(Hf/H$Hl$ HH)$Hf(jHH)$ f(H$0Ht<$HH$.bf/f/f(f/f/f/f(=aXf(fT c\\f/ \GvzfI$AD$fUAt$I$AD$ID$HL[]A\A^DI$AD$ID$@H$H\$HT$l$$$~$8uqT$\$f$$l$Yf/fI~f/H`fHn\fI~DHHL$ $8t$PAD$ID$A $fI$AD$ID$I$AD$ID$f/5`t$s\@$PfIn,$,$f/L$f(\$w~HH7$8,$t $PfIn$$$$f/D$f(\$w&HH$$$8$$t$PAD$ ID$A$fD\fI~HHL$u$8tc$u(H"9fHnAD$A $AD$SffDATf(fIHf/f(^f/r{f/f/f/f/ DZ^f(Xf(fT5^`A\A\f/5CvrHGfU@I$AD$ID$HLA\@I$LAD$ID$HA\@f(f(f(l$rl$xgAD$^ID$A$fHGHGgDHGHGGDI$AD$ ID$#f(fHf/f/f/f/f(f(\f/f/f/D\f(Xf(fT^A\A\f/(BfGfUDf@H@Ðf/vf@@fD0\fDfGHGff@fU@Xf(f(H(f(H|$BZHD$$L$f(<$@H@8H(fDATf(1IUfSHf([Af/H$Hl$0H)$HHf(fDt$hf.zf/tAdDE1W$hH&H$t)fAFIFABEEL$Et $Et $=$hI\fAFIFA%jIfAFAfUANf/f/L$$$hI\$H5HfHnfAFAAf;Et$$@a|$ue$||$v_Et$$EtD$pD$|$wt!l$x$$$fDɃ$$@D)$ f/fTvfW,K$fA($@A\Y$0DŽ$|fA(\$8f/v(f(fWJffW-0KfWJ)$0$u X$0f.z f/@f(Yf/.f(Yf/^$Pf(AXH#fD$D$D$H$tD)$f($f)$` t$hf.z f/A$f/rf/$f/$o$f/WD$uf(fA(fD(ڸPE1AA L$P$Pf(E19f/D$wE1E1E1D$v1E1D$u 8tZP=f(Yf/fA(fA(E1APf(AA uff/D$uf(fA(fD(ڸPE1AAXf(f(fTfTf/v\fD.zfD/tD$wD$DD$xD$vfE(fD(fD(fD(f(fA(AfA(۽AfA(D$`\$HfTl$@YL$XDD$8t$0DT$(D\$ T$Dd$萝l$@DT$(fY_D~=oFfD(D\$ t$0EXDD$8DY 0D\$HfA(A\fD(fDTfD/?Dd$T$At$hf.zf/tA:f/L$E1!$fD($fD(f(A\A\E\A\A^^$AY$YAY$0\D$$D$D$wE1E1E1D$v1E1$D$uD$$$D$ /tLP=f(Yf/rtfA(fA(E1Af(PAAf/Bf/D$uf(fA(fD(ڸPE1AA\t$hf.z f/PAf(f(fTfTf/v\fD.zfD/tD$wD$DD$xD$vfE(fD(fD(fD(f(fA(AfA(۽AfA(D$`\$HfTl$@YL$XDD$8t$0DT$(D\$ T$Dd$ol$@DT$(fY>A~=NCfD(Dd$T$EXD\$ DY At$0DD$8\$HfA(A\fD(fDTfD/AE11ff.fATIHf/@vE\^LAD$$L$f($ID$A$HA\fGLHGHA\ATIHf/@vM\$$}\$$LAD$ID$YXA$HA\HLGHGHA\ATIHf/?vM\$$\$$LAD$ID$Y\A$HA\HLGHGHA\ATIHT$$臵T$\$AD$ID$L^A$HA\fDfHf/rcf/r=XH>Yf/wc >f@H@HfGHGffGHGfX`>H|$XY&HD$f(ff.AVf(1ATfIUSHf(#f/H$Hl$ H)$HHf(#H)$ f(cH$$HU-=f/Cf/f(}f/wf/f(Xf(fTu?\U=\M=f/"f/v"f/wH$HT$Hd$\$b$8umT$fH<\$d$XY<fHnf/f/t\fI~HHL$$8t$PAD$ID$A $2DfT<I$AD$fTAD$HL[]A\A^f.fI$AD$Al$ff/~fD$Pf(T$d$XXY;d$HH\$$8H;d$T$fHnt$Pf(T$\$XXY7;\$HH\$|$8H;\$T$fHntj$H fHnAD$A $AD$fI$AD$ID$fI$AD$ID$FI$AD$fUAL$f.f(\fI~HHL$}$8t@f*f.AVf(1ATfIUSHf(f/H$Hl$ H)$HHf(H+)$ f(#H$$H5m9f/rf/f(f/f/f(Xf(fT9;\9\9f/I$AD$fUAL$18I$AD$fTAD$HL[]A\A^fDf(I$AD$At$fH$HT$Hl$\$軜$8fHH8T$\$l$fHnXf/XY 8fI~f.$PXY 7f/f(HH\$\$$8H7f\$fHnt$PAD$ID$A$fDf(l$\$HH覛$8l$fu$PXY 7f/vfInl$l$\ffIn\$\$HH\$"$8H6f\$fHn$tEAD$A$Ad$fI$AD$ID$%h뱐fHf/f(f(f(H8Yf(X^f/^f/5Yf/f/ 5f/f/f/H5H<$H|$d$fHnL$H$fc5YD$d$X5ffGHGf 05f(f/vfH~f(fHnf@H@H8Df(f(fD 4f(fATf(1IUfD(SHf(f( H$H$T$H)$HHf(nH)L$pf( z)$f(ʞH$Hk)D$Pf)D$`)$f(MH$H5)$f(>H$)$f(6)$fA()$f())$f()DD$)$f("|$)D$0f()D$@fo")D$ f(ԩT$|$HT$Pf(f(LD$ 1YDD$D~P5H|$0D :3fATf(fA(Ic4HDxHYXHyY4HH(YY^XHu 2f/sfW-5$ ff/rwfD/rpfD/fE/f/f(AXfDTD\D\fD/I$AD$fAUA\$'DI$AD$fATAD$HĠL[]A\AI$LAD$fATAD$HĠ[]A\H$HT$HDD$|$$uv|$DD$T$fD/$ f(T$DD$.DD$HHA\$覕$DD$T$t$ tvAD$ID$A $$ f(T$|$4.|$HH\$&$|$T$t|$tGH fHnAD$A $AD$`I$AD$ID$AH fHn@ATf(1IUSHf(H$Hl$ H)$HHf(H-)$ f(}H$0Hf$Hff/H$f( /f/rnf/f/f(=v/Xf(fT-~1\\f/-I$AD$fUAt$.D +/I$AD$fTAD$HL[]A\I$LAD$fTAD$H[]A\H$HT$Hd$\$$8us\$d$T$f/$Pf(T$d$+d$HH\$蔒$8d$T$t$Pt~AD$ID$A $$Pf(T$\$"+\$HH\$$8\$T$t{$u-HfHnAD$A $AD$VDff.Hz_f/ -f(%f/r f/sIf(}@fTfUfVf@fGHGÐH8 <-H|$T$(\$ N &-衅\$  $f(%$$T$(f(f(6HD$$L$f(,$@H@(H8ÐfGHGfAVf(1ATIUSHf(H$Hl$ H)$HHf(rH)$ f(KH$0H$Hff/H$-f/f/-ڮf/5f/X5*+f(fT-6-\\f/-f/w +I$AD$AD$1 sI$AD$fTAD$HL[]A\A^fDf(I$AD$fTfUfVAD$fI$AD$ID$@H$H\$HT$d${$8T$ f(~\$d$fI~f(fIn$P\$d$M4d$HH\$$8d$\$t$Pt!AD$ID$A $@$u-HvfHnAD$A $AD$nDHYfHnff.fAT1f(IUfSHf(f/H$Hl$ HH)$Hf(\H)$ f(5H$0H$HH$f/L$ (f(\$d$| (>f.f(\$d$t$f/ tf/X'f(fT)\\f/Z ff/w'I$AD$AD$-f$I$AD$fTAD$HL[]A\@f(L I$AD$fTfUfVAL$H[]A\I$LAD$ID$H[]A\H$H\$Hd$l$$8l$d$\$uiDf(f($P\$l$d$1d$HH\$貊$8d$l$\$t$Pt&AD$ID$A$f$u% AD$A$AL$n ِAW1f(AVfATIUSHf( f/H$Hl$HH)$Hf( H)$f(H$ H$8H$|f/rnf.rf/X-$f(fT'\\f/z vpff/w$I$AD$AD$1@fDI$AD$fTAD$HL[]A\A^A_ $f(\$H$$$x $O}\$ fI~f(xfI~3@fInfIn$$$@.$$\$HH>$($$t$@t_AD$ID$A $I$AD$ID$I$AD$ID$$t%fAD$A $AD$DHfHnf.fL$d$غL$fD$f\$T$.E„t.DЄ.кE„t.DЄ.a[/%P N-F /=H,fH*.& HHHHPcHDH(H1H)к(fDH~Q((YYY\X(Ht'((A(AYYYY\XD(HH9~/A((vV%A(TT/@D.E„h.E„W(^^\$T$~D$Dd$L$~L$\$T$~D$x/((w aML$D$(\D$D$yf(`((YYY(\X>(((Y(YYX\(YYYY\X(A(^ YX(YX^(\}YY(-e(A^Y(\YXFAX^YY|ff.USHXfD$8T$8l$<=ffʃ.V((TD$HT/%CwI/5:w@.E„f.E„W- (f/v (((/%/%/Yl$YT$ X(g~Y'l$T$ f~vf.>XD$Lr/v / (l$d$Xt$L$ ӕd$t$D$ (\ (d$L$袕DD$  g=;t$d$D(DXl$DY?A/L$A/A(l$(AYDL$$\L$t$d$DD$ٔDD$AX}l$(DL$$=L$t$(d$DD$3/(A^/.%nTY/|$ f.=3Y/. YAX^(Y5DXXT$d$ AY(ۓd$ T$f.((l$T$ ٓ{T$ l$f~((詓=a(fnXT߅uW\$0D$4~D$0HX[]DC.%</3(fTY/(D$ XD$ Y^YD$HW-C/\(\G ((T$l$ ^^(讒zXul$ T$f~@T$ tWǃrT$ (؅uW(fD.%.5|._X\$HXU(uf pA(YYT$ (̅tW (ÑT$ (\D(TY"/T$ f.f``YDOD\A/TD.b(EXYA^Y!Xl$,DL$(AXL$$t$d$YDD$T$ӐT$XtDD$d$=t$L$$(DL$(l$,fD/v{(l$(\YD$ DD$$DL$L$t$d$Ct$d$=L$DL$(DD$$l$(^rfD$ l$(DD$$YDL$t$d$L$ˏL$XrL$d$=t$DL$(DD$$l$(fD/TY/f(D$ XD$ Y^Y=6fW-(X(f.(X@(DD$d$l$(DL$$L$t$躎d$DD$((A^/7=t$L$=aDL$$l$(`(/%MY5D$ T$d$YYt$ DD$ d$(T$Y%A(^/A(A\YfYfT$d$ \YD$ 荍d$ T$@(T$DD$cDD$DXW=SD$ AY(8%4YD$ T$cA(\Y5 ff.@SH`fD$Hd$H\$L.((((TTV/-'wM/5wDf.E„.E„L$@D$D~D$@H`[Ðfè/v (((/-Q/-w/O((d$$\$ 8Ct\$ d$$f~((\$$d$ d$ \$$=H}(fnX=@/=}D(D(DWDWv (((/-)|$\$($$/-w/A(A(DD$$DL$ `ks$$(|$DL$ DD$$f~\$(A(A()<$\$$d$ (<$\$$(fnXWd$ ((TTTTVV/=h3X=|$\=/v /=p(\$,d$Xt$ ,$(|$0pt$ ,$D$$(\=((t$((|$ =L$$,$t$(D(XY d$/\$,/S/&(\$8Yd$4\DD$,t$l$( $~ $Xq\$8 $=d$4t$f~DD$,l$(/(^/k.5D$ TY/T|$0f.Yf/|$ [D(|$ A.^(DXD$ YA^Y-XX$d$$t$ Y(lt$ d$$$( A(A(DL$$DD$ ^^(R]p$$\$(XDD$ DL$$(|$f~fD`((\$$d$ ^^(oXd$ \$$f~@ .5ke /LD$ TY/*(D$0XD$$Y^;YD *fD\A/D.(EXYA^Y=X\$<d$8XDD$4t$,l$YL$(<$譆<$XiL$(l$kt$,d$8f~DD$4\$<)f.-.5.%Xf.(\$8d$4L$,DD$t$(,$t$(L$,f~,$DD$(d$4\$8^/R\$$d$ jd$ \$$k-w((TTfnV(TTVYY(\$$d$ T\$$d$ fDD$ TY/r2|$0f.Y=/(\$8\YD$0d$4L$,DD$l$(4$艄\$84$l$(DD$(L$,d$4^f~2 D((Xf/QD$ TY/$d$$\t$ YD$0fY\$$Yd$ X(kY\$$d$ f~YDL$$YDD$ X(k(|$\$(Yc$$DL$$DD$ f~6XD$0YD$ \$8d$4L$,DD$t$(,$XD$ (f,$t$(L$,d$4f~DD$\$8s ('/5 ;D$04$YD$ \$Yd$(YL$$[L$$4$d$(Y5^\$A(A\Y='*f.= Y f(|$0X|$$Y^Y@(\$($$L$$证L$$X D$ Y(臁L$ $$5x\$(YA(\l$ Y-[HHfD$(d$(-t$,D$8f(.((Tzu /.+.D(DT/=CmD/5_c/&D A.sm%A/[( (A\YA/YQ(t$YDD$|$$$X^(bc|$D $$A.DD$t$YKA(A(t$\AXA/AXY(d$$$Y=qd$t$-]((TTTV(TVDT$8f~4$#$(̸f~$$XT p#$)TVс.=y)=Y)fnYY((YYX^Y($E^$(T$ \$$~D$ HHfDA/>'XjD$0f.5:]fETAYf/6\$(f. YfA/fD.YEXA^YXDXAYf.Q0f(f(T$$a>$T$fH~f(f(afHnD~(X 8fATufW Hh[]fD(f.5f/fA(ffATY[f/f(D$(X$Y^Y ~D$XfW\[f(\Zfpf(f(\$$^^f(`<$X\$fH~fff.f(Qf(A^f/,$tfW*A,$ufW-Hhf([]fDf.f.f.dXD$XXZf(ND pfA(YY,$tfW5Bf(_,$ZfA(fATYFZf/l$(ff.3- Y\f/`f.vf(AXY^YXAXYf.QXD\$|$t$d$@T$8DL$0DT$ Gt$|$D\$f(DT$ DL$0T$8d$@D~ D-f/v2f(f\YD$(f.gQf(^DD$(fAYf.QAX|$t$D\$d$@T$8DL$0DT$ FD\$t$|$f(#Hrf/HpXfETAYf/ \YD$(DXfWf(f(X <f(f(f/5& DY\$(YfA.YfD(eEQYfA(A^ fA(\Y7f.Yff(L$(X $Y^ Y4f.QAXYf.QHYfHngE\AYmYl\YD$(f.t$,$;,$t$|$,$;|$,$af(d$DL$,$U;d$,$DL$f(d$@T$8DL$0DT$ D\$|$t$;d$@T$8DL$0DT$ D\$|$t$d$HT$@DL$8L$0DT$ D\$|$t$:d$HT$@DL$8L$0DT$ D\$|$t$fA(t$,$|$K:t$,$H!DL$fD(fHn]d$@T$8DL$0DT$ D\$|$t$9d$@T$8DL$0DT$ D\$|$t$d$@T$8DL$0DT$ D\$|$t$9d$@D~.T$8DL$0DT$ D\$|$t$0f(d$@T$8DL$0DT$ D\$t$|$9|$t$T$8d$@f(D\$DT$ D~DL$0ff.ff.~tf(f(f(fTfTSf(Hp-!f/wCf/w=ff.E„f.E„Hp[f.fèf/vfH~f(fHnf/5f/5wf/f(f(d$$.XY4$d$fH~f(f(\$$$WfHn$$X w~-g\$~I@f/fD(fD(~-:fDWfDWvfH~f(fHnf/5)l$ \$0d$1f/5wf/efA(fA(DD$D $IWt3D $DD$d$\$0fH~f(l$ fA(fA()l$\$$$VfHn$$X w~Wf(l$\$f(f(fTHpfTfTfT[fVfVD-8X-dl$l- f/v f/d$ %f(\$8X|$t$f(d$@KV|$t$$fD(f(|$0D\ fA(DL$V,$lt$DL$fD(XY->|$0d$ \$8f/~82Of/,f(fY\f. QX\$Pd$HDD$8DL$ |$0t$l$1~\$Pd$HDD$8fH~DL$ |$0t$l$f/f(^f/(f.=XZfA(fTYOf/L$@ff.+%YffA/fD.f(EXYA^Y XXfYf.) QffA(˕fA(DL$D$^^f( TK0X{D$DL$d$\$0f(l$ fH~f.`f(f(\$$$^^f(S/$$X \$fH~yfHfHnf.=F@f/VfA(fTYMf/f(D$@X$Y^|YDfD\fA/3fD.Hf(EXYA^Y 6X:fEXYfD.oQXDL$0|$t$\$Pd$Hl$8DD$ a;t$|$DL$0fH~DD$ l$8d$H\$P~# f.f.f.lXff.f(QfH~f(^f/uM\$$$@8$$\$~~-%f(f(fTfHnHpfTfTfT[fVfVf.YYf(f(\$$$8Q\$$$~fA(fTYKf/sI yf/gf(f\YD$@f.Qf(^fH~DL$@ff.ysYDXf(f("f/fA(fTYKf/\YD$@f(fY\$Y$$Xf(P,\$$$YefH~YDL$YD$Xf(,Y.f(l$ \$0d$DL$D$fH~DXD$@fAYf.oQAX|$0t$DL$\$Pd$Hl$8DD$ -8DL$t$|$0fH~f(f/=)-DYL$@Yf(fYfA.OEQA^YyDfA(A\Y f Yff(D$@X$Y^Yff.QX-Y-f.QYHfHnf(E\ bAYk JYtIf\YD$@f.~\$d$<$s-<$d$\$f(=fA(\$0d$L$<$8-\$0<$Hd$fD(L$fHnh\$Xd$PL$Hl$8DD$ DL$0|$t$,\$Xd$PL$Hl$8DD$ DL$0|$t$'\$Pd$Hl$8DD$ DL$0|$t$l,~\$Pd$Hl$8DD$ DL$0|$t$f(\$d$4$,\$d$4$f(f(\$d$,$+\$d$f,$f(f(\$Pd$Hl$8DD$ DL$0|$t$+t$|$DL$0DD$ fH~l$8d$H\$P~ \$Pd$Hl$8DD$ DL$0|$t$#+\$Pd$Hl$8DD$ DL$0|$t$\$f(d$<$`\$Pd$Hl$8DD$ DL$0|$t$*\$Pd$Hl$8DD$ DL$0|$t$3fDf(f(f(HH~5f(D$8ffTf.zu-f/f.Zf.fD(fDTf/fD/yѻf/GD vfA.DfA/Rf( A\YfA/Yf(d$ YDD$|$$X^f(m2|$$H-DDD$d$ YfLnfA.fA(CfA(d$\AXfA/AXY=f(T$,$H,$YT~tT$d$~5Pf(fTHHfTfVf(f(fTfUfVf(fH~\$8fH~f(XTCH H fT-%fT)fV݁f.=A)=@^J)H fHnYYf(YYX^Y%f( $( $f(f(HHf.fA/MXyD$4D f(HH^f($.$f(ظf( A\YfA/Y^d$ T$DD$<$f(/<$-"BHsDD$YT$d$ fLnf.f(l$Y$\f(Fd$$Y~%~5 l$fpf.fD.D$8X%Af(~-f(fTfTfTf(fVY@^d$T$D$f(.-!AD`D$T$Yd$~jfA(DT$(d$ fWT$l$)$Ef($DT$(l$T$AYd$ ~5XfT%f(f(^f(^lfA(d$T$D$\! DsD$T$\d$f(AYYf(YX^f(8f(DR@HL$\$f.{#f.{f(Hf(f(fDf.z:f.zL~%f(f(f(fT-fTfTfVf(Hf(f(fTfDf(f.f.~%df(f(f(f(fTfTSHpf/wCf/w=ff.E„f.E„Hpf(f([ff¨f/vfH~f(fHnf/-f/-wf/~f(f(\$$CI$\$fH~f(f(T$$B$~=df(fHnX[T$~%5f(f(fTHpfTfTfT[fVfVf/fD(fD(~=fDWfDWvfH~f(fHnf/-)|$ \$0T$f/-wf/fA(fA(DD$D $B<D $DD$T$\$0fH~f(|$ fA(fA()|$\$$Af(|$\$f($fHn~%X'f.XDD$lf/v f/=f(\$8T$ Xt$l$f(|$@+At$l$$fD(f(t$0D\ jfA(DL$@<$%Ll$DL$fD(XY=t$0T$ \$8f/~%2b:f/,f(fY\f. QX\$PT$HDD$8DL$ t$0l$|$i~%\$PT$HDD$8fH~DL$ t$0l$|$f/f(^f/v0f.58jfA(fTYi:f/L$@ff.KEYffA/fD.f(EXYA^Y XXYff.I QffA(fA(DL$D$^^f(?+X[D$DL$T$\$0f(|$ fH~f.@f(f(T$$^^f(>$XT$fH~ifHfHnf.5VPȯf/^fA(fTY8f/f(D$@X$Y^\YD_fD\fA/SfD.hf(EXYA^Y XfEXYfD.QXDL$0t$l$\$PT$H|$8DD$ A&l$t$DL$0fH~DD$ |$8T$H\$P~%#f.f.f. LXf(ff. f(QfH~f(^f/MU\$$#$\$~%f(~-f(fTHpfHn[fTfTfVf(fTfVfDЭYYf(f(\$$<\$$~%}f(fA(fTY6f/sI If/of(f\YD$@f.Qf(^fH~DL$@ff.icYuDXf(f(f/(fA(fTY5f/\YD$@f(fYDL$YD$Xf(Y>f(|$ \$0T$DL$D$fH~DY\$Y$Xf(\$$YfH~rXf(f(D$@fAYf.wQAXt$0l$DL$\$PT$H|$8DD$ "DL$l$t$0fH~Xf(f/5@)=rDYL$@Yf(fYfA.OEQA^YaDfA(A\Y f Yff(D$@X$Y^Yff.QX=nY=Vf.QYHMfHnf(E\ "AYkK YT f\YD$@f.n\$T$4$34$T$\$f(%fA(\$0T$L$4$\$04$HΩT$fD(L$fHnh\$XT$PL$H|$8DD$ DL$0t$l$\$XT$PL$H|$8DD$ DL$0t$l$\$PT$H|$8DD$ DL$0t$l$,~%\$PT$H|$8DD$ DL$0t$l$|f(\$T$,$\$T$,$f(f(\$T$<$\$T$f<$f(f(\$PT$H|$8DD$ DL$0t$l$Rl$t$DL$0DD$ fH~|$8T$H\$P~%\$PT$H|$8DD$ DL$0t$l$\$PT$H|$8DD$ DL$0t$l$\$f(T$4$`\$PT$H|$8DD$ DL$0t$l$g\$PT$H|$8DD$ DL$0t$l$+fDHHf(f(~-f(D$8ff.fTzu f/f.Nf.f(fTLf/zf/pf/>D=fA.l/f/%f( ξA\Yf/Yf(\$ Y|$t$$X^f(7t$$H%M/|$\$ YfLnfA..f(AXD\f(f/XAY@f(T$\$$$3$$Y!~5A\$T$~-f(fTHHfTfVf(fTfUf(fVf(fH~L$8fH~f(X $.H H fT=Կ%fT)fVρf.5)=@^B)H fHnYYf(YYX^Y)f($$f(f(f(HHfDf/f(f(XBD$4fD%лHH^f(f($$f(f(%f( TA\Yf/Y^T$ \$|$4$f(4$%,H=|$Y\$T$ fLnDf(\$Yd$$\f(z1\$$YϺ~5~-׼d$@8f.f.L$8X +f(f(~fTfTfTfVZf^T$\$<$f(<$%+D $\$YT$~54|DL$(T$ fW\$f(d$)4$r0f(4$DL$(d$\$AYT$ ~-ǻfXf(fT%f(f(^^pf(T$\$<$. <$%ysD @\$\T$AYfDYf(f(YX^%f(D ߸_ff.l$l$l$(l$8E„t-E„t# @E„t+E„t'f.@PN@Ҟ:L$l$("H|$IH|$QH|$`HD$HcH=HT$HD$H?H1H)к!fDH~AHtHH9~E„E„U@ @|$(|$8|$|$|$l$l$|$l$yTff.USHH$ۼ$۬$Á۬$۬$۬$w\w\۬$E„۬$E„HĨ[]D@v-r-p<-n6H<$ "|$XZE->X$v H$H ɉŁ|$ |$`|$<$|$@H,|$0l$ |$P|$ |$l$@<$|$@,l$0H `l$ l$0Ԛ|$`H|$`|$@|$0<$+l$0H<$H l$`l$Pl$0l$ -B- <,$ 1}l$@,$,$۬$,$ A|$H|$<$*Y^,$l$%Df$$$$*Y^<$|$_AX$$$$I*l$ H tEHĨ[] @f<$tH<$XZ,$ufDnh,$ q f۬$l$@l$݋KfD۬$۬$-۬$fD-H ۬$|$۬$<$)AYAZ<$0|$A[]-:t۬$۬$-۬$gfD<$tH |$<$o(H ,$m,$ =l$@۬$\|$pH|$p|$`|$@|$0<$'l$0H<$NH l$0l$Pl$`l$pDvb|$`H|$`|$@|$0l$P<$8'l$@AYAZl$ l$`l$PfD|$`H|$`|$@|$0l$Pl$<$&l$H<$|H l$ l$0l$`l$P7^ܕ,$ u۬$|$ l$@l$l$ ЈF۬$۬$fD|$0H|$p|$0<$|$`%l$0l$@A[X-l$Pl$`*|$0H|$0|$ l$Pl$<$\%l$ l$0_AX-9l$0fD S1+f.|$H|$l$P<$ |$ H|$ <$$H|$ l$@ <$$l$ H l$ jH۬$۬$[w]we۬$E„۬$E„ HĘf fDH$Āv- - w- U $$$$S#_AX<$h|$AYAZ$$$$#l$ H fD۬$۬$v-H-Fw-Hf.H |$|$@<$|$0"_AX<$|$AYAZl$ l$H |$<$U"l$ H ۬$t۬$;HĘ-(XT$v H |$ |$`|$<$|$@!|$0l$ |$P|$ |$l$@<$|$@!l$0H ʃl$ l$0>|$pH|$p|$`|$0<$ l$0H|$P<$0|$@۬$H l$`l$Pl$0-W-},$ zl$@,$D,$N fD۬$,$H|$<$ AYAZ,$f-H |$@|$|$0<$A[X<$ |$XZl$ l$]f-H ۬$|$۬$<$A[X<$|$XZJf.  ,$ ۬$l$@l$p8D۬$?|$pH|$p|$`|$@|$0<$l$0H<$1|$@l$PH l$Pl$`l$p@-U|$pH|$p|$`<$|$@|$0l$`۬$XZ-l$0l$`O DH<$XZ۬$t۬$l$ lH |$<$`H f.,$ -r-l$@ f.f|$pH|$p|$`|$@l$P<$۬$|$0A[Xl$0l$Pl$pl$`۬$,$ U H|$l$P<$Y^,$H<$: l~|$Y^f|$ H|$ <$ 4~|$Y^l$l$ Tf|$pH|$p|$`|$@l$Pl$<$Tl$H<$|$@l$PH l$Pl$pl$`\ fD}GfH|$@|$ l$Pl$<$l$ l$@_AX-VfD}D}۬$l$@l$ ||$H<$<H|$ l$0 |<$l$ H | d|HXl$`l$p|$0z u l$pl$`l$pl$`8<-V fDPN, T-fD|$H|$l$p<$_AX ,$l$<$wl$`H |$<$H z,$l$`tl$p fDl$0-l$`HT$xHD$h%) -A)Ѓ B_)|$@D$Hl$@l$pl$`%D<$t$ht$hA[X,$HXÐPf|XyD$@@l$pHX<$H<$MXZ,$@ f. -l|$H|$<$ZXZ ʅ,$l$fD-^l$0-ԅl$`tl$p|$H<$Yx^ *$l$ D@|$ H<$|$ HD$ T$(RPL$ H l$ 6tl$`$@l$pl$`H<$|$  wL$L$AYAZl$MDl$pl$`fzwpw$&Ht$(t$(t$(t$(H {{Hz% fDz(l$ u H@@f.H۬$۬$۬$۬$_wiwe۬$E„۬$E„@۬$۬$HĘfDH$Āv--w- $$$$[_AX<$p|$AYAZ$$$$l$ H ۬$t۬$HĘ۬$۬$v-|-w-f.H |$|$@<$|$0`_AX<$u|$AYAZl$ l$H |$<$%l$ H @-0X\t$v H |$ |$`|$<$|$@|$0l$ |$P|$ |$l$@<$|$@l$0H sl$ l$0R|$pH|$p|$`|$0<$ l$0H|$P<$D|$@۬$H l$`l$Pl$0-{-E,$ l$@r,$h,$rf.۬$,$rH|$<$AYAZ,$f-H |$@|$|$0<$A[X<$|$XZl$ l$f-H ۬$|$۬$<$A[X<$|$XZRf. *,$ '~۬$l$@l$qXd۬$Oq|$pH|$p|$`|$@|$0<$l$0H<$A|$@l$PH l$Pl$`l$p@-}۬$'!۬$۬$Tf.|$pH|$p|$`<$|$@ |$0l$`۬$XZ-}l$0l$`_ DH<$XZ۬$t۬$l$ |H |$<$P H f.,$ |r-l$@yof.v|$pH|$p|$`|$@l$P<$ ۬$|$0A[Xl$0l$Pl$pl$`۬$۬$f{,$ 5{ H|$l$P<$ Y^,$|$ H|$ <$ Dn|$Y^l$l$ fH<$ n|$Y^af|$pH|$p|$`|$@l$Pl$<$4 l$H<$|$@l$PH l$Pl$pl$`(zm=V{H|$@|$ l$Pl$<$ l$ l$@_AX-zVfDmDl۬$l$@l$ l|$H<$, H|$ l$0 l<$ l$ H ql TlHXx|$0l$`l$pz u l$`l$pl$pl$`x*.-HyB@.x Vx-x |$H|$۬$<$_AX w,$l$w<$wl$pH |$<$H j,$l$ptl$`@ f.l$0-wl$pHT$hHD$x%) -Ew)Ѓ 6_)|$@D$Hl$@l$`l$pt$xt$xA[Xl$`HXT Xil$pl$`D$@@l$`HXÐt$ht$ha۬$XZ@ f. v-|v|$H|$<$jXZ u,$l$fD-udl$0-ul$ptl$`D|$H<$Yh^ Bu$l$ D@|$ H<$u|$ HD$ T$(RPL$ H l$ Qtl$p(@l$`l$pH<$|$  gL$L$AYAZl$EDl$`l$pfgg$9fD$D$D$D$D$~D$fD$L$D$ffD$D$D$D$D$~D$WfD$D$D$D$D$~D$fD$D$D$D$D$~D$fD$D$D$D$D$~D$gfD$D$D$D$D$~D$fD$D$D$D$D$~D$fD$D$D$D$D$~D$fD$D$D$D$D$~D$wfD$D$D$D$D$~D$Wff.f(f(f(ff.@[ff.Kff.ff.{ff.Kff.ff.ff.+ff.+ff.ff.l$l$|$|$ff. ff.ff.ff.ff.ff.+ff.[ff.ff.f.+ff.ff.ff.;ff. ff.{ff.kff.ff.ff.ff. ff.ff.ff.ff.f.wQff.fff.ff.ff.{ff.{ff.ff.l$wff.ff.ff. ff.ff..z+f.{f/w b(Du(f afDYoYoHYoHf.Y$n.({((fH\/w$/sOHf.uXm(fWT$ yT$ HXf.L$ PL$ HXÐ.({((fH\/w$/sOHf.uX`(fW9T$ YnT$ HXfL$ YnL$ HXff.{WHL$ HfL$ .z/uT (HD..8tXHuff(.H(L$ T$T$fL$ .(\^z(/u#.z>/u9^T(HfD..8t\l_fD%8lk((T.v,,f6_U*(T\(V\._zX_H ^(fSHHL$ D$L$ T$(f.(.\^/(T.z /-Nkj((T.v,,fL^U*(T\(V\.%)^vX^H[D..8pX\%]_^TU(^H[(ff.z:ff.{ ff/w 6f(fuf(f fDYkYxEHWYwkHf.Y<cf.f({&f(fH\f/w f/sJHDuX<f(ÐfWT$ T$HXfL$L$HXÐf.f({&f(fH\f/w f/sJHDuXf(ÐfWT$-HYhjT$HXÐL$ Y@jL$HXfff.{VHL$WfL$f.zf/ufT if(Hf.f.8tXHDu fff(f.Hf(L$$$fL$f.f(\^z-f/u'f.zAf/u;^fTǃf(HfDf.f.8t\@%Pf(f(fTf.v3H,fMfUH*f(fT\f(fV\f.nXH@^f(ÐSHHL$$L$$f(ff.f(f.\^f/f(fTf.z f/-Wf(f(fTf.v3H,fTfUH*f(fT\f(fV\f.%vXH[f.f.f.8[X\%~Jf^fTf(fD^H[f(l$z({wÐul$Xl$-fl$-fHt$t$HfDl$|$Off.@Hl$ l${ w$sVHuH|$H<$H<$>l$0H H|$ H<$H<$ l$@H Hff.Hl$ l${ w$sVHuH|$H<$jH<$l$0H H|$ H<$6H<$Zl$@H HHl$ l$0{|H |$|$ <$H ,$z0u1t f.HD8tHfuHqHl$0H<$|$@t$8t$8Bl$@l$PH z>u@ ffDzDuNl$ tH@8t |$D$fD$ l$ l$UvHDl$ Hff.@SHH l$@<$t$8t$8DH l$0l$ t fDzt~ fD|$D$fD$ l$ l$Tv f.;H[@8t{l$ tD;l$ H[fAu DA1ADuDDADÐt,1ȅu1f.u1ÉDIHHuI1ILHuL@ILÐHt+HHDH1HHHuH1HHHu1HHHHtDI1ILHuL@ILÐHt+HHDH1HHHuH1HHHu1HAA1A)1D)ʅt1ȅuADff.fHHIH?H?I1HI)H1LH)HtH1HHHuILfHHIH?H?I1HI)H1LH)HtH1HHHuILf1)֙1)ׅt*fD1ȅu1f.tHHH?H1H)HHH1H)Ht0HHf.H1HHHuH1HHHtHfDHHH?H1H)HHH1H)Ht0HHf.H1HHHuH1HHHtHfD@w @ljÐ1ff.f@w @ljÐ1ff.f@w @ljÐ1ff.f@w@ffw ljf1ff.ffw ljf1ff.ffw ljf1ff.ffw Éff BÉ BÉ BÉGHHH@HBff.HHH@HBff.HHH@HBff.HHH?HH?HGf.HHH@HBff.HHH@HBff.HHH@HBff.HHH?HH?HGf.U)lj@33ljff.U)lj@33ljff.ff%UU)ljff33f%33fffff.ff%UU)ljff33f%33fffff.%UUUU)lj%33333333lj%iff.fHUHHUUUUUUUUHHH!H33333333H)HHH!H!HHHHHH!HHH8fDHHfHUUUUUUUUHHH!H33333333H)HHH!H!HHHHHH!HHH8fDHwHf1)ljU)lj@33ljDf1)ljff%UU)ljff33f%33fffÐH1)HfHHH?H1H)HDHHH?H1H)HDH ZH~HH=f.UHH]nHHinvalid input argument_err_test_function_cython_3_1_6eval_genlaguerreinvalid value for ninvalid value for pinvalid signm or signnfailed to allocate memoryVinvalid condition on `p - 1`takes no arguments%.200s() %s (%zd given)takes exactly one argumentBad call flags for CyFunctiontakes no keyword arguments%.200s() %scannot import name %S__loader__loader__file__origin__package__parent__path__submodule_search_locationseval_hermitenormhyperuneeds an argumentan integer is requiredkeywords must be strings__pyx_capi___set_actionvoid *qstdtritComputational errorUnknown error.chndtrixeval_hermitefloat divisionscipy.special._boxcox.boxcoxxlampdtrikchdtrivchndtrincchndtridfchndtrstdtridfshpgdtriasclgdtrixnrdtrisdnctdtridfnctdtrincstdnrdtrimnomprnbdtrinbtdtriabtdtribbtdtrinxnbtdtriknbdtrikncfdtridfdncfdtrincncfdtridfnstdtr__init__exactlyname '%U' is not defineditemsscipy.special._ufuncs.geterr__enter____exit__keysscipy.special._ufuncs.seterrscipy/special/_ufuncs.pyxbuiltinscython_runtime__builtins__does not matchnumpydtypeflatiterbroadcastndarraygenericnumberunsignedintegercomplexfloatingflexiblecharacterscipy.special._ufuncs_cxx_export_beta_pdf_float_export_beta_pdf_double_export_beta_ppf_float_export_beta_ppf_double_export_binom_cdf_float_export_binom_cdf_double_export_binom_isf_float_export_binom_isf_double_export_binom_pmf_float_export_binom_pmf_double_export_binom_ppf_float_export_binom_ppf_double_export_binom_sf_float_export_binom_sf_double_export_cauchy_isf_float_export_cauchy_isf_double_export_cauchy_ppf_float_export_cauchy_ppf_double_export_hypergeom_cdf_float_export_hypergeom_cdf_double_export_hypergeom_mean_float_export_hypergeom_mean_double_export_hypergeom_pmf_float_export_hypergeom_pmf_double_export_hypergeom_sf_float_export_hypergeom_sf_double_export_invgauss_isf_float_export_invgauss_isf_double_export_invgauss_ppf_float_export_invgauss_ppf_double_export_landau_cdf_float_export_landau_cdf_double_export_landau_isf_float_export_landau_isf_double_export_landau_pdf_float_export_landau_pdf_double_export_landau_ppf_float_export_landau_ppf_double_export_landau_sf_float_export_landau_sf_double_export_nbinom_cdf_float_export_nbinom_cdf_double_export_nbinom_isf_float_export_nbinom_isf_double_export_nbinom_mean_float_export_nbinom_mean_double_export_nbinom_pmf_float_export_nbinom_pmf_double_export_nbinom_ppf_float_export_nbinom_ppf_double_export_nbinom_sf_float_export_nbinom_sf_double_export_nbinom_skewness_float_export_nbinom_variance_float_export_ncf_isf_float_export_ncf_isf_double_export_ncf_mean_float_export_ncf_mean_double_export_ncf_pdf_float_export_ncf_pdf_double_export_ncf_sf_float_export_ncf_sf_double_export_ncf_skewness_float_export_ncf_skewness_double_export_ncf_variance_float_export_ncf_variance_double_export_nct_isf_float_export_nct_isf_double_export_nct_mean_float_export_nct_mean_double_export_nct_pdf_float_export_nct_pdf_double_export_nct_sf_float_export_nct_sf_double_export_nct_skewness_float_export_nct_skewness_double_export_nct_variance_float_export_nct_variance_double_export_ncx2_cdf_float_export_ncx2_cdf_double_export_ncx2_isf_float_export_ncx2_isf_double_export_ncx2_pdf_float_export_ncx2_pdf_double_export_ncx2_ppf_float_export_ncx2_ppf_double_export_ncx2_sf_float_export_ncx2_sf_double_export_skewnorm_cdf_float_export_skewnorm_cdf_double_export_skewnorm_isf_float_export_skewnorm_isf_double_export_skewnorm_ppf_float_export_skewnorm_ppf_double_export__stirling2_inexact_export_ibeta_float_export_ibeta_double_export_ibetac_float_export_ibetac_double_export_ibetac_inv_float_export_ibetac_inv_double_export_ibeta_inv_float_export_ibeta_inv_double_export_fellint_RC_export_cellint_RC_export_fellint_RD_export_cellint_RD_export_fellint_RF_export_cellint_RF_export_fellint_RG_export_cellint_RG_export_fellint_RJ_export_cellint_RJ_export_erfinv_float_export_erfinv_double_export_hyp1f1_double_export_ncf_cdf_float_export_ncf_cdf_double_export_ncf_ppf_float_export_ncf_ppf_double_export_nct_cdf_float_export_nct_cdf_double_export_nct_ppf_float_export_nct_ppf_double_export_powm1_float_export_powm1_double_export_wrightomega_export_wrightomega_realscipy.special._ellip_harm_2numpy._core._multiarray_umathnumpy.core._multiarray_umath_ARRAY_API_ARRAY_API is NULL pointernumpy.import_array_UFUNC_API_UFUNC_API not found_UFUNC_API is NULL pointernumpy.import_ufunc_beta_pdf_beta_ppf_binom_cdf_binom_isf_binom_pmf_binom_ppf_binom_sf_cauchy_isf_cauchy_ppf_cosine_cdf_cosine_invcdf_ellip_harm_factorial_hypergeom_cdf_hypergeom_mean_hypergeom_pmf_hypergeom_sf_hypergeom_skewness_hypergeom_variance_igam_fac_invgauss_isf_invgauss_ppf_kolmogc_kolmogci_kolmogp_lanczos_sum_expg_scaled_landau_cdf_landau_isf_landau_pdf_landau_ppf_landau_sf_lgam1p_nbinom_cdf_nbinom_isf_nbinom_kurtosis_excess_nbinom_mean_nbinom_pmf_nbinom_ppf_nbinom_sf_nbinom_skewness_nbinom_variance_ncf_isf_ncf_kurtosis_excess_ncf_mean_ncf_pdf_ncf_sf_ncf_skewness_ncf_variance_nct_isf_nct_kurtosis_excess_nct_mean_nct_pdf_nct_sf_nct_skewness_nct_variance_ncx2_cdf_ncx2_isf_ncx2_pdf_ncx2_ppf_ncx2_sf_sf_error_test_functionPrivate function; do not use._skewnorm_cdf_skewnorm_isf_skewnorm_ppf_smirnovc_smirnovci_smirnovp_struve_asymp_large_z_struve_bessel_series_struve_power_seriesagmbetaincbetainccbetainccinvbetaincinvchdtrchdtrcchdtrielliprcelliprdelliprfelliprgelliprjerfcinverfinveval_chebyceval_chebyseval_chebyteval_chebyueval_gegenbauereval_jacobieval_laguerreeval_legendreeval_sh_chebyteval_sh_chebyueval_sh_jacobieval_sh_legendreexpnfdtrcgdtrgdtrcgdtribhyp0f1inv_boxcoxinv_boxcox1pkl_divkolmogikolmogorovlpmvnbdtrnbdtrcnbdtrincfdtrncfdtrinctdtrnctdtritndtrindtri_expowens_tpdtrpdtrcpdtripochpowm1pseudo_huberrel_entrroundshichisicismirnovsmirnovispencetklmbdainit scipy.special._ufuncs__reduce____module____dictoffset____vectorcalloffset____weaklistoffset__func_doc__doc__func_name__name____qualname__func_dict__dict__func_globals__globals__func_closure__closure__func_code__code__func_defaults__defaults____kwdefaults____annotations___is_coroutineCythonUnboundCMethodpolynomial defined only for alpha > -1__int__ returned non-int (type %.200s). The ability to return an instance of a strict subclass of int is deprecated, and may be removed in a future version of Python.__int__ returned non-int (type %.200s)Interpreter change detected - this module can only be loaded into one interpreter per process.polynomial only defined for nonnegative nShared Cython type %.200s is not a type objectShared Cython type %.200s has the wrong size, try recompilingvalue too large to convert to sf_error_tcan't convert negative value to sf_error_tunbound method %.200S() needs an argumentvoid (sf_error_t, sf_action_t)C function %.200s.%.200s has wrong signature (expected %.500s, got %.500s)%.200s does not export expected C function %.200sC variable %.200s.%.200s has wrong signature (expected %.500s, got %.500s)%.200s does not export expected C variable %.200s%.200s.%.200s is not a type object%.200s.%.200s size changed, may indicate binary incompatibility. Expected %zd from C header, got %zd from PyObject%.200s() keywords must be strings%s() got multiple values for keyword argument '%U'cannot fit '%.200s' into an index-sized integernon-integer arg n is deprecated, removed in SciPy 1.7.xcalling %R should have returned an instance of BaseException, not %Rraise: exception class must be a subclass of BaseExceptionInput parameter %s is out of rangeAnswer appears to be lower than lowest search bound (%g)Answer appears to be higher than highest search bound (%g)Two internal parameters that should sum to 1.0 do not.%s() got an unexpected keyword argument '%U'floating point number truncated to an integer__annotations__ must be set to a dict object__name__ must be set to a string object__qualname__ must be set to a string object__kwdefaults__ must be set to a dict objectchanges to cyfunction.__kwdefaults__ will not currently affect the values used in function calls__defaults__ must be set to a tuple objectchanges to cyfunction.__defaults__ will not currently affect the values used in function callsvalue too large to convert to sf_action_tcan't convert negative value to sf_action_tfunction's dictionary may not be deletedsetting function's dictionary to a non-dict while calling a Python objectNULL result without error in PyObject_Callscipy.special._hyp0f1._hyp0f1_cmplxscipy.special._hyp0f1._hyp0f1_realscipy.special._hyp0f1._hyp0f1_asyscipy.special._boxcox.boxcox1pdictionary changed size during iteration'NoneType' object is not iterableneed more than %zd value%.1s to unpacktoo many values to unpack (expected %zd)%.200s() takes %.8s %zd positional argument%.1s (%zd given)scipy/special/_ufuncs_extra_code.pxiscipy.special._ufuncs.errstate.__init__'%.200s' object is not subscriptable'NoneType' object has no attribute '%.30s'argument after ** must be a mapping, not NoneTypescipy.special._ufuncs.errstate.__enter__scipy.special._ufuncs.errstate.__exit__scipy/special/_ufuncs_extra_code_common.pxiModule '_ufuncs' has already been imported. Re-initialisation is not supported.compile time Python version %d.%d of module '%.100s' %s runtime version %d.%d_export_hypergeom_skewness_float_export_hypergeom_skewness_double_export_hypergeom_variance_float_export_hypergeom_variance_double_export_nbinom_kurtosis_excess_float_export_nbinom_kurtosis_excess_double_export_nbinom_skewness_double_export_nbinom_variance_double_export_ncf_kurtosis_excess_float_export_ncf_kurtosis_excess_double_export_nct_kurtosis_excess_float_export_nct_kurtosis_excess_double_ARRAY_API is not PyCapsule objectmodule compiled against ABI version 0x%x but this version of numpy is 0x%xmodule was compiled against NumPy C-API version 0x%x (NumPy 1.23) but the running NumPy has C-API version 0x%x. Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem.FATAL: module compiled as unknown endianFATAL: module compiled as little endian, but detected different endianness at runtime../../tmp/build-env-99e64tom/lib/python3.12/site-packages/numpy/__init__.cython-30.pxd_multiarray_umath failed to import_UFUNC_API is not PyCapsule object_beta_pdf(x, a, b) Probability density function of beta distribution. Parameters ---------- x : array_like Real-valued such that :math:`0 \leq x \leq 1`, the upper limit of integration a, b : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_beta_ppf(x, a, b) Percent point function of beta distribution. Parameters ---------- x : array_like Real-valued such that :math:`0 \leq x \leq 1`, the upper limit of integration a, b : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_binom_cdf(x, n, p) Cumulative density function of binomial distribution. Parameters ---------- x : array_like Real-valued n : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_binom_isf(x, n, p) Inverse survival function of binomial distribution. Parameters ---------- x : array_like Real-valued n : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_binom_pmf(x, n, p) Probability mass function of binomial distribution. Parameters ---------- x : array_like Real-valued n : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_binom_ppf(x, n, p) Percent point function of binomial distribution. Parameters ---------- x : array_like Real-valued n : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_binom_sf(x, n, p) Survival function of binomial distribution. Parameters ---------- x : array_like Real-valued n : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_cauchy_isf(p, loc, scale) Inverse survival function of the Cauchy distribution. Parameters ---------- p : array_like Probabilities loc : array_like Location parameter of the distribution. scale : array_like Scale parameter of the distribution. Returns ------- scalar or ndarray_cauchy_ppf(p, loc, scale) Percent point function (i.e. quantile) of the Cauchy distribution. Parameters ---------- p : array_like Probabilities loc : array_like Location parameter of the distribution. scale : array_like Scale parameter of the distribution. Returns ------- scalar or ndarray_cosine_cdf(x) Cumulative distribution function (CDF) of the cosine distribution:: { 0, x < -pi cdf(x) = { (pi + x + sin(x))/(2*pi), -pi <= x <= pi { 1, x > pi Parameters ---------- x : array_like `x` must contain real numbers. Returns ------- scalar or ndarray The cosine distribution CDF evaluated at `x`._cosine_invcdf(p) Inverse of the cumulative distribution function (CDF) of the cosine distribution. The CDF of the cosine distribution is:: cdf(x) = (pi + x + sin(x))/(2*pi) This function computes the inverse of cdf(x). Parameters ---------- p : array_like `p` must contain real numbers in the interval ``0 <= p <= 1``. `nan` is returned for values of `p` outside the interval [0, 1]. Returns ------- scalar or ndarray The inverse of the cosine distribution CDF evaluated at `p`.Internal function, use `ellip_harm` instead.Internal function, do not use._hypergeom_cdf(x, r, N, M) Cumulative density function of hypergeometric distribution. Parameters ---------- x : array_like Real-valued r, N, M : array_like Positive, integer-valued parameter Returns ------- scalar or ndarray_hypergeom_mean(r, N, M) Mean of hypergeometric distribution. Parameters ---------- r, N, M : array_like Positive, integer-valued parameter Returns ------- scalar or ndarray_hypergeom_pmf(x, r, N, M) Probability mass function of hypergeometric distribution. Parameters ---------- x : array_like Real-valued r, N, M : array_like Positive, integer-valued parameter Returns ------- scalar or ndarray_hypergeom_sf(x, r, N, M) Survival function of hypergeometric distribution. Parameters ---------- x : array_like Real-valued r, N, M : array_like Positive, integer-valued parameter Returns ------- scalar or ndarray_hypergeom_skewness(r, N, M) Skewness of hypergeometric distribution. Parameters ---------- r, N, M : array_like Positive, integer-valued parameter Returns ------- scalar or ndarray_hypergeom_variance(r, N, M) Mean of hypergeometric distribution. Parameters ---------- r, N, M : array_like Positive, integer-valued parameter Returns ------- scalar or ndarray_invgauss_isf(x, mu, s) Inverse survival function of inverse gaussian distribution. Parameters ---------- x : array_like Positive real-valued mu : array_like Positive, real-valued parameters s : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_invgauss_ppf(x, mu) Percent point function of inverse gaussian distribution. Parameters ---------- x : array_like Positive real-valued mu : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_landau_cdf(x, loc, scale) Cumulative distribution function of the Landau distribution. Parameters ---------- x : array_like Real-valued argument loc : array_like Real-valued distribution location scale : array_like Positive, real-valued distribution scale Returns ------- scalar or ndarray_landau_isf(p, loc, scale) Inverse survival function of the Landau distribution. Parameters ---------- p : array_like Real-valued argument between 0 and 1 loc : array_like Real-valued distribution location scale : array_like Positive, real-valued distribution scale Returns ------- scalar or ndarray_landau_pdf(x, loc, scale) Probability density function of the Landau distribution. Parameters ---------- x : array_like Real-valued argument loc : array_like Real-valued distribution location scale : array_like Positive, real-valued distribution scale Returns ------- scalar or ndarray_landau_ppf(p, loc, scale) Percent point function of the Landau distribution. Parameters ---------- p : array_like Real-valued argument between 0 and 1 loc : array_like Real-valued distribution location scale : array_like Positive, real-valued distribution scale Returns ------- scalar or ndarray_landau_sf(x, loc, scale) Survival function of the Landau distribution. Parameters ---------- x : array_like Real-valued argument loc : array_like Real-valued distribution location scale : array_like Positive, real-valued distribution scale Returns ------- scalar or ndarray_nbinom_cdf(x, r, p) Cumulative density function of negative binomial distribution. Parameters ---------- x : array_like Real-valued r : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_nbinom_isf(x, r, p) Inverse survival function of negative binomial distribution. Parameters ---------- x : array_like Real-valued r : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_nbinom_kurtosis_excess(r, p) Kurtosis excess of negative binomial distribution. Parameters ---------- r : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_nbinom_mean(r, p) Mean of negative binomial distribution. Parameters ---------- r : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_nbinom_pmf(x, r, p) Probability mass function of negative binomial distribution. Parameters ---------- x : array_like Real-valued r : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_nbinom_ppf(x, r, p) Percent point function of negative binomial distribution. Parameters ---------- x : array_like Real-valued r : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_nbinom_sf(x, r, p) Survival function of negative binomial distribution. Parameters ---------- x : array_like Real-valued r : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_nbinom_skewness(r, p) Skewness of negative binomial distribution. Parameters ---------- r : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_nbinom_variance(r, p) Variance of negative binomial distribution. Parameters ---------- r : array_like Positive, integer-valued parameter p : array_like Positive, real-valued parameter Returns ------- scalar or ndarray_ncf_isf(x, v1, v2, l) Inverse survival function of noncentral F-distribution. Parameters ---------- x : array_like Positive real-valued v1, v2, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncf_kurtosis_excess(v1, v2, l) Kurtosis excess of noncentral F-distribution. Parameters ---------- v1, v2, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncf_mean(v1, v2, l) Mean of noncentral F-distribution. Parameters ---------- v1, v2, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncf_pdf(x, v1, v2, l) Probability density function of noncentral F-distribution. Parameters ---------- x : array_like Positive real-valued v1, v2, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncf_sf(x, v1, v2, l) Survival function of noncentral F-distribution. Parameters ---------- x : array_like Positive real-valued v1, v2, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncf_skewness(v1, v2, l) Skewness of noncentral F-distribution. Parameters ---------- v1, v2, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncf_variance(v1, v2, l) Variance of noncentral F-distribution. Parameters ---------- v1, v2, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_nct_isf(x, v, l) Inverse survival function of noncentral t-distribution. Parameters ---------- x : array_like Real-valued v : array_like Positive, real-valued parameters l : array_like Real-valued parameters Returns ------- scalar or ndarray_nct_kurtosis_excess(v, l) Kurtosis excess of noncentral t-distribution. Parameters ---------- v : array_like Positive, real-valued parameters l : array_like Real-valued parameters Returns ------- scalar or ndarray_nct_mean(v, l) Mean of noncentral t-distribution. Parameters ---------- v : array_like Positive, real-valued parameters l : array_like Real-valued parameters Returns ------- scalar or ndarray_nct_pdf(x, v, l) Probability density function of noncentral t-distribution. Parameters ---------- x : array_like Real-valued v : array_like Positive, real-valued parameters l : array_like Real-valued parameters Returns ------- scalar or ndarray_nct_sf(x, v, l) Survival function of noncentral t-distribution. Parameters ---------- x : array_like Real-valued v : array_like Positive, real-valued parameters l : array_like Real-valued parameters Returns ------- scalar or ndarray_nct_skewness(v, l) Skewness of noncentral t-distribution. Parameters ---------- v : array_like Positive, real-valued parameters l : array_like Real-valued parameters Returns ------- scalar or ndarray_nct_variance(v, l) Variance of noncentral t-distribution. Parameters ---------- v : array_like Positive, real-valued parameters l : array_like Real-valued parameters Returns ------- scalar or ndarray_ncx2_cdf(x, k, l) Cumulative density function of Non-central chi-squared distribution. Parameters ---------- x : array_like Positive real-valued k, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncx2_isf(x, k, l) Inverse survival function of Non-central chi-squared distribution. Parameters ---------- x : array_like Positive real-valued k, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncx2_pdf(x, k, l) Probability density function of Non-central chi-squared distribution. Parameters ---------- x : array_like Positive real-valued k, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncx2_ppf(x, k, l) Percent point function of Non-central chi-squared distribution. Parameters ---------- x : array_like Positive real-valued k, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_ncx2_sf(x, k, l) Survival function of Non-central chi-squared distribution. Parameters ---------- x : array_like Positive real-valued k, l : array_like Positive, real-valued parameters Returns ------- scalar or ndarray_skewnorm_cdf(x, l, sc, sh) Cumulative density function of skewnorm distribution. Parameters ---------- x : array_like Real-valued l : array_like Real-valued parameters sc : array_like Positive, Real-valued parameters sh : array_like Real-valued parameters Returns ------- scalar or ndarray_skewnorm_isf(x, l, sc, sh) Inverse survival function of skewnorm distribution. Parameters ---------- x : array_like Real-valued l : array_like Real-valued parameters sc : array_like Positive, Real-valued parameters sh : array_like Real-valued parameters Returns ------- scalar or ndarray_skewnorm_ppf(x, l, sc, sh) Percent point function of skewnorm distribution. Parameters ---------- x : array_like Real-valued l : array_like Real-valued parameters sc : array_like Positive, Real-valued parameters sh : array_like Real-valued parameters Returns ------- scalar or ndarray_smirnovc(n, d) Internal function, do not use._smirnovp(n, p) Internal function, do not use._struve_asymp_large_z(v, z, is_h) Internal function for testing `struve` & `modstruve` Evaluates using asymptotic expansion Returns ------- v, err_struve_bessel_series(v, z, is_h) Internal function for testing `struve` & `modstruve` Evaluates using Bessel function series Returns ------- v, err_struve_power_series(v, z, is_h) Internal function for testing `struve` & `modstruve` Evaluates using power series Returns ------- v, erragm(a, b, out=None) Compute the arithmetic-geometric mean of `a` and `b`. Start with a_0 = a and b_0 = b and iteratively compute:: a_{n+1} = (a_n + b_n)/2 b_{n+1} = sqrt(a_n*b_n) a_n and b_n converge to the same limit as n increases; their common limit is agm(a, b). Parameters ---------- a, b : array_like Real values only. If the values are both negative, the result is negative. If one value is negative and the other is positive, `nan` is returned. out : ndarray, optional Optional output array for the function values Returns ------- scalar or ndarray The arithmetic-geometric mean of `a` and `b`. Examples -------- >>> import numpy as np >>> from scipy.special import agm >>> a, b = 24.0, 6.0 >>> agm(a, b) 13.458171481725614 Compare that result to the iteration: >>> while a != b: ... a, b = (a + b)/2, np.sqrt(a*b) ... print("a = %19.16f b=%19.16f" % (a, b)) ... a = 15.0000000000000000 b=12.0000000000000000 a = 13.5000000000000000 b=13.4164078649987388 a = 13.4582039324993694 b=13.4581390309909850 a = 13.4581714817451772 b=13.4581714817060547 a = 13.4581714817256159 b=13.4581714817256159 When array-like arguments are given, broadcasting applies: >>> a = np.array([[1.5], [3], [6]]) # a has shape (3, 1). >>> b = np.array([6, 12, 24, 48]) # b has shape (4,). >>> agm(a, b) array([[ 3.36454287, 5.42363427, 9.05798751, 15.53650756], [ 4.37037309, 6.72908574, 10.84726853, 18.11597502], [ 6. , 8.74074619, 13.45817148, 21.69453707]])bdtr(k, n, p, out=None) Binomial distribution cumulative distribution function. Sum of the terms 0 through `floor(k)` of the Binomial probability density. .. math:: \mathrm{bdtr}(k, n, p) = \sum_{j=0}^{\lfloor k \rfloor} {{n}\choose{j}} p^j (1-p)^{n-j} Parameters ---------- k : array_like Number of successes (double), rounded down to the nearest integer. n : array_like Number of events (int). p : array_like Probability of success in a single event (float). out : ndarray, optional Optional output array for the function values Returns ------- y : scalar or ndarray Probability of `floor(k)` or fewer successes in `n` independent events with success probabilities of `p`. Notes ----- The terms are not summed directly; instead the regularized incomplete beta function is employed, according to the formula, .. math:: \mathrm{bdtr}(k, n, p) = I_{1 - p}(n - \lfloor k \rfloor, \lfloor k \rfloor + 1). Wrapper for the Cephes [1]_ routine `bdtr`. References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/bdtrc(k, n, p, out=None) Binomial distribution survival function. Sum of the terms `floor(k) + 1` through `n` of the binomial probability density, .. math:: \mathrm{bdtrc}(k, n, p) = \sum_{j=\lfloor k \rfloor +1}^n {{n}\choose{j}} p^j (1-p)^{n-j} Parameters ---------- k : array_like Number of successes (double), rounded down to nearest integer. n : array_like Number of events (int) p : array_like Probability of success in a single event. out : ndarray, optional Optional output array for the function values Returns ------- y : scalar or ndarray Probability of `floor(k) + 1` or more successes in `n` independent events with success probabilities of `p`. See Also -------- bdtr betainc Notes ----- The terms are not summed directly; instead the regularized incomplete beta function is employed, according to the formula, .. math:: \mathrm{bdtrc}(k, n, p) = I_{p}(\lfloor k \rfloor + 1, n - \lfloor k \rfloor). Wrapper for the Cephes [1]_ routine `bdtrc`. References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/bdtri(k, n, y, out=None) Inverse function to `bdtr` with respect to `p`. Finds the event probability `p` such that the sum of the terms 0 through `k` of the binomial probability density is equal to the given cumulative probability `y`. Parameters ---------- k : array_like Number of successes (float), rounded down to the nearest integer. n : array_like Number of events (float) y : array_like Cumulative probability (probability of `k` or fewer successes in `n` events). out : ndarray, optional Optional output array for the function values Returns ------- p : scalar or ndarray The event probability such that `bdtr(\lfloor k \rfloor, n, p) = y`. See Also -------- bdtr betaincinv Notes ----- The computation is carried out using the inverse beta integral function and the relation,:: 1 - p = betaincinv(n - k, k + 1, y). Wrapper for the Cephes [1]_ routine `bdtri`. References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/bdtrik(y, n, p, out=None) Inverse function to `bdtr` with respect to `k`. Finds the number of successes `k` such that the sum of the terms 0 through `k` of the Binomial probability density for `n` events with probability `p` is equal to the given cumulative probability `y`. Parameters ---------- y : array_like Cumulative probability (probability of `k` or fewer successes in `n` events). n : array_like Number of events (float). p : array_like Success probability (float). out : ndarray, optional Optional output array for the function values Returns ------- k : scalar or ndarray The number of successes `k` such that `bdtr(k, n, p) = y`. See Also -------- bdtr Notes ----- Formula 26.5.24 of [1]_ is used to reduce the binomial distribution to the cumulative incomplete beta distribution. Computation of `k` involves a search for a value that produces the desired value of `y`. The search relies on the monotonicity of `y` with `k`. Wrapper for the CDFLIB [2]_ Fortran routine `cdfbin`. References ---------- .. [1] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. .. [2] Barry Brown, James Lovato, and Kathy Russell, CDFLIB: Library of Fortran Routines for Cumulative Distribution Functions, Inverses, and Other Parameters.bdtrin(k, y, p, out=None) Inverse function to `bdtr` with respect to `n`. Finds the number of events `n` such that the sum of the terms 0 through `k` of the Binomial probability density for events with probability `p` is equal to the given cumulative probability `y`. Parameters ---------- k : array_like Number of successes (float). y : array_like Cumulative probability (probability of `k` or fewer successes in `n` events). p : array_like Success probability (float). out : ndarray, optional Optional output array for the function values Returns ------- n : scalar or ndarray The number of events `n` such that `bdtr(k, n, p) = y`. See Also -------- bdtr Notes ----- Formula 26.5.24 of [1]_ is used to reduce the binomial distribution to the cumulative incomplete beta distribution. Computation of `n` involves a search for a value that produces the desired value of `y`. The search relies on the monotonicity of `y` with `n`. Wrapper for the CDFLIB [2]_ Fortran routine `cdfbin`. References ---------- .. [1] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. .. [2] Barry Brown, James Lovato, and Kathy Russell, CDFLIB: Library of Fortran Routines for Cumulative Distribution Functions, Inverses, and Other Parameters.betainc(a, b, x, out=None) Regularized incomplete beta function. Computes the regularized incomplete beta function, defined as [1]_: .. math:: I_x(a, b) = \frac{\Gamma(a+b)}{\Gamma(a)\Gamma(b)} \int_0^x t^{a-1}(1-t)^{b-1}dt, for :math:`0 \leq x \leq 1`. This function is the cumulative distribution function for the beta distribution; its range is [0, 1]. Parameters ---------- a, b : array_like Positive, real-valued parameters x : array_like Real-valued such that :math:`0 \leq x \leq 1`, the upper limit of integration out : ndarray, optional Optional output array for the function values Returns ------- scalar or ndarray Value of the regularized incomplete beta function See Also -------- beta : beta function betaincinv : inverse of the regularized incomplete beta function betaincc : complement of the regularized incomplete beta function scipy.stats.beta : beta distribution Notes ----- The term *regularized* in the name of this function refers to the scaling of the function by the gamma function terms shown in the formula. When not qualified as *regularized*, the name *incomplete beta function* often refers to just the integral expression, without the gamma terms. One can use the function `beta` from `scipy.special` to get this "nonregularized" incomplete beta function by multiplying the result of ``betainc(a, b, x)`` by ``beta(a, b)``. ``betainc(a, b, x)`` is treated as a two parameter family of functions of a single variable `x`, rather than as a function of three variables. This impacts only the limiting cases ``a = 0``, ``b = 0``, ``a = inf``, ``b = inf``. In general .. math:: \lim_{(a, b) \rightarrow (a_0, b_0)} \mathrm{betainc}(a, b, x) is treated as a pointwise limit in ``x``. Thus for example, ``betainc(0, b, 0)`` equals ``0`` for ``b > 0``, although it would be indeterminate when considering the simultaneous limit ``(a, x) -> (0+, 0+)``. This function wraps the ``ibeta`` routine from the Boost Math C++ library [2]_. References ---------- .. [1] NIST Digital Library of Mathematical Functions https://dlmf.nist.gov/8.17 .. [2] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. Examples -------- Let :math:`B(a, b)` be the `beta` function. >>> import scipy.special as sc The coefficient in terms of `gamma` is equal to :math:`1/B(a, b)`. Also, when :math:`x=1` the integral is equal to :math:`B(a, b)`. Therefore, :math:`I_{x=1}(a, b) = 1` for any :math:`a, b`. >>> sc.betainc(0.2, 3.5, 1.0) 1.0 It satisfies :math:`I_x(a, b) = x^a F(a, 1-b, a+1, x)/ (aB(a, b))`, where :math:`F` is the hypergeometric function `hyp2f1`: >>> a, b, x = 1.4, 3.1, 0.5 >>> x**a * sc.hyp2f1(a, 1 - b, a + 1, x)/(a * sc.beta(a, b)) 0.8148904036225295 >>> sc.betainc(a, b, x) 0.8148904036225296 This functions satisfies the relationship :math:`I_x(a, b) = 1 - I_{1-x}(b, a)`: >>> sc.betainc(2.2, 3.1, 0.4) 0.49339638807619446 >>> 1 - sc.betainc(3.1, 2.2, 1 - 0.4) 0.49339638807619446betaincc(a, b, x, out=None) Complement of the regularized incomplete beta function. Computes the complement of the regularized incomplete beta function, defined as [1]_: .. math:: \bar{I}_x(a, b) = 1 - I_x(a, b) = 1 - \frac{\Gamma(a+b)}{\Gamma(a)\Gamma(b)} \int_0^x t^{a-1}(1-t)^{b-1}dt, for :math:`0 \leq x \leq 1`. Parameters ---------- a, b : array_like Positive, real-valued parameters x : array_like Real-valued such that :math:`0 \leq x \leq 1`, the upper limit of integration out : ndarray, optional Optional output array for the function values Returns ------- scalar or ndarray Value of the regularized incomplete beta function See Also -------- betainc : regularized incomplete beta function betaincinv : inverse of the regularized incomplete beta function betainccinv : inverse of the complement of the regularized incomplete beta function beta : beta function scipy.stats.beta : beta distribution Notes ----- .. versionadded:: 1.11.0 Like `betainc`, ``betaincc(a, b, x)`` is treated as a two parameter family of functions of a single variable `x`, rather than as a function of three variables. See the `betainc` docstring for more info on how this impacts limiting cases. This function wraps the ``ibetac`` routine from the Boost Math C++ library [2]_. References ---------- .. [1] NIST Digital Library of Mathematical Functions https://dlmf.nist.gov/8.17 .. [2] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. Examples -------- >>> from scipy.special import betaincc, betainc The naive calculation ``1 - betainc(a, b, x)`` loses precision when the values of ``betainc(a, b, x)`` are close to 1: >>> 1 - betainc(0.5, 8, [0.9, 0.99, 0.999]) array([2.0574632e-09, 0.0000000e+00, 0.0000000e+00]) By using ``betaincc``, we get the correct values: >>> betaincc(0.5, 8, [0.9, 0.99, 0.999]) array([2.05746321e-09, 1.97259354e-17, 1.96467954e-25])betainccinv(a, b, y, out=None) Inverse of the complemented regularized incomplete beta function. Computes :math:`x` such that: .. math:: y = 1 - I_x(a, b) = 1 - \frac{\Gamma(a+b)}{\Gamma(a)\Gamma(b)} \int_0^x t^{a-1}(1-t)^{b-1}dt, where :math:`I_x` is the normalized incomplete beta function `betainc` and :math:`\Gamma` is the `gamma` function [1]_. Parameters ---------- a, b : array_like Positive, real-valued parameters y : array_like Real-valued input out : ndarray, optional Optional output array for function values Returns ------- scalar or ndarray Value of the inverse of the regularized incomplete beta function See Also -------- betainc : regularized incomplete beta function betaincc : complement of the regularized incomplete beta function Notes ----- .. versionadded:: 1.11.0 This function wraps the ``ibetac_inv`` routine from the Boost Math C++ library [2]_. References ---------- .. [1] NIST Digital Library of Mathematical Functions https://dlmf.nist.gov/8.17 .. [2] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. Examples -------- >>> from scipy.special import betainccinv, betaincc This function is the inverse of `betaincc` for fixed values of :math:`a` and :math:`b`. >>> a, b = 1.2, 3.1 >>> y = betaincc(a, b, 0.2) >>> betainccinv(a, b, y) 0.2 >>> a, b = 7, 2.5 >>> x = betainccinv(a, b, 0.875) >>> betaincc(a, b, x) 0.875betaincinv(a, b, y, out=None) Inverse of the regularized incomplete beta function. Computes :math:`x` such that: .. math:: y = I_x(a, b) = \frac{\Gamma(a+b)}{\Gamma(a)\Gamma(b)} \int_0^x t^{a-1}(1-t)^{b-1}dt, where :math:`I_x` is the normalized incomplete beta function `betainc` and :math:`\Gamma` is the `gamma` function [1]_. Parameters ---------- a, b : array_like Positive, real-valued parameters y : array_like Real-valued input out : ndarray, optional Optional output array for function values Returns ------- scalar or ndarray Value of the inverse of the regularized incomplete beta function See Also -------- betainc : regularized incomplete beta function gamma : gamma function Notes ----- This function wraps the ``ibeta_inv`` routine from the Boost Math C++ library [2]_. References ---------- .. [1] NIST Digital Library of Mathematical Functions https://dlmf.nist.gov/8.17 .. [2] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. Examples -------- >>> import scipy.special as sc This function is the inverse of `betainc` for fixed values of :math:`a` and :math:`b`. >>> a, b = 1.2, 3.1 >>> y = sc.betainc(a, b, 0.2) >>> sc.betaincinv(a, b, y) 0.2 >>> >>> a, b = 7.5, 0.4 >>> x = sc.betaincinv(a, b, 0.5) >>> sc.betainc(a, b, x) 0.5boxcox(x, lmbda, out=None) Compute the Box-Cox transformation. The Box-Cox transformation is:: y = (x**lmbda - 1) / lmbda if lmbda != 0 log(x) if lmbda == 0 Returns `nan` if ``x < 0``. Returns `-inf` if ``x == 0`` and ``lmbda < 0``. Parameters ---------- x : array_like Data to be transformed. lmbda : array_like Power parameter of the Box-Cox transform. out : ndarray, optional Optional output array for the function values Returns ------- y : scalar or ndarray Transformed data. Notes ----- .. versionadded:: 0.14.0 Examples -------- >>> from scipy.special import boxcox >>> boxcox([1, 4, 10], 2.5) array([ 0. , 12.4 , 126.09110641]) >>> boxcox(2, [0, 1, 2]) array([ 0.69314718, 1. , 1.5 ])boxcox1p(x, lmbda, out=None) Compute the Box-Cox transformation of 1 + `x`. The Box-Cox transformation computed by `boxcox1p` is:: y = ((1+x)**lmbda - 1) / lmbda if lmbda != 0 log(1+x) if lmbda == 0 Returns `nan` if ``x < -1``. Returns `-inf` if ``x == -1`` and ``lmbda < 0``. Parameters ---------- x : array_like Data to be transformed. lmbda : array_like Power parameter of the Box-Cox transform. out : ndarray, optional Optional output array for the function values Returns ------- y : scalar or ndarray Transformed data. Notes ----- .. versionadded:: 0.14.0 Examples -------- >>> from scipy.special import boxcox1p >>> boxcox1p(1e-4, [0, 0.5, 1]) array([ 9.99950003e-05, 9.99975001e-05, 1.00000000e-04]) >>> boxcox1p([0.01, 0.1], 0.25) array([ 0.00996272, 0.09645476])btdtria(p, b, x, out=None) Inverse of `betainc` with respect to `a`. This is the inverse of the beta cumulative distribution function, `betainc`, considered as a function of `a`, returning the value of `a` for which `betainc(a, b, x) = p`, or .. math:: p = \int_0^x \frac{\Gamma(a + b)}{\Gamma(a)\Gamma(b)} t^{a-1} (1-t)^{b-1}\,dt Parameters ---------- p : array_like Cumulative probability, in [0, 1]. b : array_like Shape parameter (`b` > 0). x : array_like The quantile, in [0, 1]. out : ndarray, optional Optional output array for the function values Returns ------- a : scalar or ndarray The value of the shape parameter `a` such that `betainc(a, b, x) = p`. See Also -------- btdtrib : Inverse of the beta cumulative distribution function, with respect to `b`. Notes ----- Wrapper for the CDFLIB [1]_ Fortran routine `cdfbet`. The cumulative distribution function `p` is computed using a routine by DiDinato and Morris [2]_. Computation of `a` involves a search for a value that produces the desired value of `p`. The search relies on the monotonicity of `p` with `a`. References ---------- .. [1] Barry Brown, James Lovato, and Kathy Russell, CDFLIB: Library of Fortran Routines for Cumulative Distribution Functions, Inverses, and Other Parameters. .. [2] DiDinato, A. R. and Morris, A. H., Algorithm 708: Significant Digit Computation of the Incomplete Beta Function Ratios. ACM Trans. Math. Softw. 18 (1993), 360-373.btdtria(a, p, x, out=None) Inverse of `betainc` with respect to `b`. This is the inverse of the beta cumulative distribution function, `betainc`, considered as a function of `b`, returning the value of `b` for which `betainc(a, b, x) = p`, or .. math:: p = \int_0^x \frac{\Gamma(a + b)}{\Gamma(a)\Gamma(b)} t^{a-1} (1-t)^{b-1}\,dt Parameters ---------- a : array_like Shape parameter (`a` > 0). p : array_like Cumulative probability, in [0, 1]. x : array_like The quantile, in [0, 1]. out : ndarray, optional Optional output array for the function values Returns ------- b : scalar or ndarray The value of the shape parameter `b` such that `betainc(a, b, x) = p`. See Also -------- btdtria : Inverse of the beta cumulative distribution function, with respect to `a`. Notes ----- Wrapper for the CDFLIB [1]_ Fortran routine `cdfbet`. The cumulative distribution function `p` is computed using a routine by DiDinato and Morris [2]_. Computation of `b` involves a search for a value that produces the desired value of `p`. The search relies on the monotonicity of `p` with `b`. References ---------- .. [1] Barry Brown, James Lovato, and Kathy Russell, CDFLIB: Library of Fortran Routines for Cumulative Distribution Functions, Inverses, and Other Parameters. .. [2] DiDinato, A. R. and Morris, A. H., Algorithm 708: Significant Digit Computation of the Incomplete Beta Function Ratios. ACM Trans. Math. Softw. 18 (1993), 360-373.chdtr(v, x, out=None) Chi square cumulative distribution function. Returns the area under the left tail (from 0 to `x`) of the Chi square probability density function with `v` degrees of freedom: .. math:: \frac{1}{2^{v/2} \Gamma(v/2)} \int_0^x t^{v/2 - 1} e^{-t/2} dt Here :math:`\Gamma` is the Gamma function; see `gamma`. This integral can be expressed in terms of the regularized lower incomplete gamma function `gammainc` as ``gammainc(v / 2, x / 2)``. [1]_ Parameters ---------- v : array_like Degrees of freedom. x : array_like Upper bound of the integral. out : ndarray, optional Optional output array for the function results. Returns ------- scalar or ndarray Values of the cumulative distribution function. See Also -------- chdtrc, chdtri, chdtriv, gammainc References ---------- .. [1] Chi-Square distribution, https://www.itl.nist.gov/div898/handbook/eda/section3/eda3666.htm Examples -------- >>> import numpy as np >>> import scipy.special as sc It can be expressed in terms of the regularized lower incomplete gamma function. >>> v = 1 >>> x = np.arange(4) >>> sc.chdtr(v, x) array([0. , 0.68268949, 0.84270079, 0.91673548]) >>> sc.gammainc(v / 2, x / 2) array([0. , 0.68268949, 0.84270079, 0.91673548])chdtrc(v, x, out=None) Chi square survival function. Returns the area under the right hand tail (from `x` to infinity) of the Chi square probability density function with `v` degrees of freedom: .. math:: \frac{1}{2^{v/2} \Gamma(v/2)} \int_x^\infty t^{v/2 - 1} e^{-t/2} dt Here :math:`\Gamma` is the Gamma function; see `gamma`. This integral can be expressed in terms of the regularized upper incomplete gamma function `gammaincc` as ``gammaincc(v / 2, x / 2)``. [1]_ Parameters ---------- v : array_like Degrees of freedom. x : array_like Lower bound of the integral. out : ndarray, optional Optional output array for the function results. Returns ------- scalar or ndarray Values of the survival function. See Also -------- chdtr, chdtri, chdtriv, gammaincc References ---------- .. [1] Chi-Square distribution, https://www.itl.nist.gov/div898/handbook/eda/section3/eda3666.htm Examples -------- >>> import numpy as np >>> import scipy.special as sc It can be expressed in terms of the regularized upper incomplete gamma function. >>> v = 1 >>> x = np.arange(4) >>> sc.chdtrc(v, x) array([1. , 0.31731051, 0.15729921, 0.08326452]) >>> sc.gammaincc(v / 2, x / 2) array([1. , 0.31731051, 0.15729921, 0.08326452])chdtri(v, p, out=None) Inverse to `chdtrc` with respect to `x`. Returns `x` such that ``chdtrc(v, x) == p``. Parameters ---------- v : array_like Degrees of freedom. p : array_like Probability. out : ndarray, optional Optional output array for the function results. Returns ------- x : scalar or ndarray Value so that the probability a Chi square random variable with `v` degrees of freedom is greater than `x` equals `p`. See Also -------- chdtrc, chdtr, chdtriv References ---------- .. [1] Chi-Square distribution, https://www.itl.nist.gov/div898/handbook/eda/section3/eda3666.htm Examples -------- >>> import scipy.special as sc It inverts `chdtrc`. >>> v, p = 1, 0.3 >>> sc.chdtrc(v, sc.chdtri(v, p)) 0.3 >>> x = 1 >>> sc.chdtri(v, sc.chdtrc(v, x)) 1.0chdtriv(p, x, out=None) Inverse to `chdtr` with respect to `v`. Returns `v` such that ``chdtr(v, x) == p``. Parameters ---------- p : array_like Probability that the Chi square random variable is less than or equal to `x`. x : array_like Nonnegative input. out : ndarray, optional Optional output array for the function results. Returns ------- scalar or ndarray Degrees of freedom. See Also -------- chdtr, chdtrc, chdtri References ---------- .. [1] Chi-Square distribution, https://www.itl.nist.gov/div898/handbook/eda/section3/eda3666.htm Examples -------- >>> import scipy.special as sc It inverts `chdtr`. >>> p, x = 0.5, 1 >>> sc.chdtr(sc.chdtriv(p, x), x) 0.5000000000202172 >>> v = 1 >>> sc.chdtriv(sc.chdtr(v, x), v) 1.0000000000000013chndtr(x, df, nc, out=None) Non-central chi square cumulative distribution function The cumulative distribution function is given by: .. math:: P(\chi^{\prime 2} \vert \nu, \lambda) =\sum_{j=0}^{\infty} e^{-\lambda /2} \frac{(\lambda /2)^j}{j!} P(\chi^{\prime 2} \vert \nu + 2j), where :math:`\nu > 0` is the degrees of freedom (``df``) and :math:`\lambda \geq 0` is the non-centrality parameter (``nc``). Parameters ---------- x : array_like Upper bound of the integral; must satisfy ``x >= 0`` df : array_like Degrees of freedom; must satisfy ``df > 0`` nc : array_like Non-centrality parameter; must satisfy ``nc >= 0`` out : ndarray, optional Optional output array for the function results Returns ------- x : scalar or ndarray Value of the non-central chi square cumulative distribution function. See Also -------- chndtrix, chndtridf, chndtrincchndtridf(x, p, nc, out=None) Inverse to `chndtr` vs `df` Calculated using a search to find a value for `df` that produces the desired value of `p`. Parameters ---------- x : array_like Upper bound of the integral; must satisfy ``x >= 0`` p : array_like Probability; must satisfy ``0 <= p < 1`` nc : array_like Non-centrality parameter; must satisfy ``nc >= 0`` out : ndarray, optional Optional output array for the function results Returns ------- df : scalar or ndarray Degrees of freedom See Also -------- chndtr, chndtrix, chndtrincchndtrinc(x, df, p, out=None) Inverse to `chndtr` vs `nc` Calculated using a search to find a value for `df` that produces the desired value of `p`. Parameters ---------- x : array_like Upper bound of the integral; must satisfy ``x >= 0`` df : array_like Degrees of freedom; must satisfy ``df > 0`` p : array_like Probability; must satisfy ``0 <= p < 1`` out : ndarray, optional Optional output array for the function results Returns ------- nc : scalar or ndarray Non-centrality See Also -------- chndtr, chndtrix, chndtrincchndtrix(p, df, nc, out=None) Inverse to `chndtr` vs `x` Calculated using a search to find a value for `x` that produces the desired value of `p`. Parameters ---------- p : array_like Probability; must satisfy ``0 <= p < 1`` df : array_like Degrees of freedom; must satisfy ``df > 0`` nc : array_like Non-centrality parameter; must satisfy ``nc >= 0`` out : ndarray, optional Optional output array for the function results Returns ------- x : scalar or ndarray Value so that the probability a non-central Chi square random variable with `df` degrees of freedom and non-centrality, `nc`, is greater than `x` equals `p`. See Also -------- chndtr, chndtridf, chndtrincelliprc(x, y, out=None) Degenerate symmetric elliptic integral. The function RC is defined as [1]_ .. math:: R_{\mathrm{C}}(x, y) = \frac{1}{2} \int_0^{+\infty} (t + x)^{-1/2} (t + y)^{-1} dt = R_{\mathrm{F}}(x, y, y) Parameters ---------- x, y : array_like Real or complex input parameters. `x` can be any number in the complex plane cut along the negative real axis. `y` must be non-zero. out : ndarray, optional Optional output array for the function values Returns ------- R : scalar or ndarray Value of the integral. If `y` is real and negative, the Cauchy principal value is returned. If both of `x` and `y` are real, the return value is real. Otherwise, the return value is complex. See Also -------- elliprf : Completely-symmetric elliptic integral of the first kind. elliprd : Symmetric elliptic integral of the second kind. elliprg : Completely-symmetric elliptic integral of the second kind. elliprj : Symmetric elliptic integral of the third kind. Notes ----- RC is a degenerate case of the symmetric integral RF: ``elliprc(x, y) == elliprf(x, y, y)``. It is an elementary function rather than an elliptic integral. The code implements Carlson's algorithm based on the duplication theorems and series expansion up to the 7th order. [2]_ .. versionadded:: 1.8.0 References ---------- .. [1] B. C. Carlson, ed., Chapter 19 in "Digital Library of Mathematical Functions," NIST, US Dept. of Commerce. https://dlmf.nist.gov/19.16.E6 .. [2] B. C. Carlson, "Numerical computation of real or complex elliptic integrals," Numer. Algorithm, vol. 10, no. 1, pp. 13-26, 1995. https://arxiv.org/abs/math/9409227 https://doi.org/10.1007/BF02198293 Examples -------- Basic homogeneity property: >>> import numpy as np >>> from scipy.special import elliprc >>> x = 1.2 + 3.4j >>> y = 5. >>> scale = 0.3 + 0.4j >>> elliprc(scale*x, scale*y) (0.5484493976710874-0.4169557678995833j) >>> elliprc(x, y)/np.sqrt(scale) (0.5484493976710874-0.41695576789958333j) When the two arguments coincide, the integral is particularly simple: >>> x = 1.2 + 3.4j >>> elliprc(x, x) (0.4299173120614631-0.3041729818745595j) >>> 1/np.sqrt(x) (0.4299173120614631-0.30417298187455954j) Another simple case: the first argument vanishes: >>> y = 1.2 + 3.4j >>> elliprc(0, y) (0.6753125346116815-0.47779380263880866j) >>> np.pi/2/np.sqrt(y) (0.6753125346116815-0.4777938026388088j) When `x` and `y` are both positive, we can express :math:`R_C(x,y)` in terms of more elementary functions. For the case :math:`0 \le x < y`, >>> x = 3.2 >>> y = 6. >>> elliprc(x, y) 0.44942991498453444 >>> np.arctan(np.sqrt((y-x)/x))/np.sqrt(y-x) 0.44942991498453433 And for the case :math:`0 \le y < x`, >>> x = 6. >>> y = 3.2 >>> elliprc(x,y) 0.4989837501576147 >>> np.log((np.sqrt(x)+np.sqrt(x-y))/np.sqrt(y))/np.sqrt(x-y) 0.49898375015761476elliprd(x, y, z, out=None) Symmetric elliptic integral of the second kind. The function RD is defined as [1]_ .. math:: R_{\mathrm{D}}(x, y, z) = \frac{3}{2} \int_0^{+\infty} [(t + x) (t + y)]^{-1/2} (t + z)^{-3/2} dt Parameters ---------- x, y, z : array_like Real or complex input parameters. `x` or `y` can be any number in the complex plane cut along the negative real axis, but at most one of them can be zero, while `z` must be non-zero. out : ndarray, optional Optional output array for the function values Returns ------- R : scalar or ndarray Value of the integral. If all of `x`, `y`, and `z` are real, the return value is real. Otherwise, the return value is complex. See Also -------- elliprc : Degenerate symmetric elliptic integral. elliprf : Completely-symmetric elliptic integral of the first kind. elliprg : Completely-symmetric elliptic integral of the second kind. elliprj : Symmetric elliptic integral of the third kind. Notes ----- RD is a degenerate case of the elliptic integral RJ: ``elliprd(x, y, z) == elliprj(x, y, z, z)``. The code implements Carlson's algorithm based on the duplication theorems and series expansion up to the 7th order. [2]_ .. versionadded:: 1.8.0 References ---------- .. [1] B. C. Carlson, ed., Chapter 19 in "Digital Library of Mathematical Functions," NIST, US Dept. of Commerce. https://dlmf.nist.gov/19.16.E5 .. [2] B. C. Carlson, "Numerical computation of real or complex elliptic integrals," Numer. Algorithm, vol. 10, no. 1, pp. 13-26, 1995. https://arxiv.org/abs/math/9409227 https://doi.org/10.1007/BF02198293 Examples -------- Basic homogeneity property: >>> import numpy as np >>> from scipy.special import elliprd >>> x = 1.2 + 3.4j >>> y = 5. >>> z = 6. >>> scale = 0.3 + 0.4j >>> elliprd(scale*x, scale*y, scale*z) (-0.03703043835680379-0.24500934665683802j) >>> elliprd(x, y, z)*np.power(scale, -1.5) (-0.0370304383568038-0.24500934665683805j) All three arguments coincide: >>> x = 1.2 + 3.4j >>> elliprd(x, x, x) (-0.03986825876151896-0.14051741840449586j) >>> np.power(x, -1.5) (-0.03986825876151894-0.14051741840449583j) The so-called "second lemniscate constant": >>> elliprd(0, 2, 1)/3 0.5990701173677961 >>> from scipy.special import gamma >>> gamma(0.75)**2/np.sqrt(2*np.pi) 0.5990701173677959elliprf(x, y, z, out=None) Completely-symmetric elliptic integral of the first kind. The function RF is defined as [1]_ .. math:: R_{\mathrm{F}}(x, y, z) = \frac{1}{2} \int_0^{+\infty} [(t + x) (t + y) (t + z)]^{-1/2} dt Parameters ---------- x, y, z : array_like Real or complex input parameters. `x`, `y`, or `z` can be any number in the complex plane cut along the negative real axis, but at most one of them can be zero. out : ndarray, optional Optional output array for the function values Returns ------- R : scalar or ndarray Value of the integral. If all of `x`, `y`, and `z` are real, the return value is real. Otherwise, the return value is complex. See Also -------- elliprc : Degenerate symmetric integral. elliprd : Symmetric elliptic integral of the second kind. elliprg : Completely-symmetric elliptic integral of the second kind. elliprj : Symmetric elliptic integral of the third kind. Notes ----- The code implements Carlson's algorithm based on the duplication theorems and series expansion up to the 7th order (cf.: https://dlmf.nist.gov/19.36.i) and the AGM algorithm for the complete integral. [2]_ .. versionadded:: 1.8.0 References ---------- .. [1] B. C. Carlson, ed., Chapter 19 in "Digital Library of Mathematical Functions," NIST, US Dept. of Commerce. https://dlmf.nist.gov/19.16.E1 .. [2] B. C. Carlson, "Numerical computation of real or complex elliptic integrals," Numer. Algorithm, vol. 10, no. 1, pp. 13-26, 1995. https://arxiv.org/abs/math/9409227 https://doi.org/10.1007/BF02198293 Examples -------- Basic homogeneity property: >>> import numpy as np >>> from scipy.special import elliprf >>> x = 1.2 + 3.4j >>> y = 5. >>> z = 6. >>> scale = 0.3 + 0.4j >>> elliprf(scale*x, scale*y, scale*z) (0.5328051227278146-0.4008623567957094j) >>> elliprf(x, y, z)/np.sqrt(scale) (0.5328051227278147-0.4008623567957095j) All three arguments coincide: >>> x = 1.2 + 3.4j >>> elliprf(x, x, x) (0.42991731206146316-0.30417298187455954j) >>> 1/np.sqrt(x) (0.4299173120614631-0.30417298187455954j) The so-called "first lemniscate constant": >>> elliprf(0, 1, 2) 1.3110287771460598 >>> from scipy.special import gamma >>> gamma(0.25)**2/(4*np.sqrt(2*np.pi)) 1.3110287771460598elliprg(x, y, z, out=None) Completely-symmetric elliptic integral of the second kind. The function RG is defined as [1]_ .. math:: R_{\mathrm{G}}(x, y, z) = \frac{1}{4} \int_0^{+\infty} [(t + x) (t + y) (t + z)]^{-1/2} \left(\frac{x}{t + x} + \frac{y}{t + y} + \frac{z}{t + z}\right) t dt Parameters ---------- x, y, z : array_like Real or complex input parameters. `x`, `y`, or `z` can be any number in the complex plane cut along the negative real axis. out : ndarray, optional Optional output array for the function values Returns ------- R : scalar or ndarray Value of the integral. If all of `x`, `y`, and `z` are real, the return value is real. Otherwise, the return value is complex. See Also -------- elliprc : Degenerate symmetric integral. elliprd : Symmetric elliptic integral of the second kind. elliprf : Completely-symmetric elliptic integral of the first kind. elliprj : Symmetric elliptic integral of the third kind. Notes ----- The implementation uses the relation [1]_ .. math:: 2 R_{\mathrm{G}}(x, y, z) = z R_{\mathrm{F}}(x, y, z) - \frac{1}{3} (x - z) (y - z) R_{\mathrm{D}}(x, y, z) + \sqrt{\frac{x y}{z}} and the symmetry of `x`, `y`, `z` when at least one non-zero parameter can be chosen as the pivot. When one of the arguments is close to zero, the AGM method is applied instead. Other special cases are computed following Ref. [2]_ .. versionadded:: 1.8.0 References ---------- .. [1] B. C. Carlson, "Numerical computation of real or complex elliptic integrals," Numer. Algorithm, vol. 10, no. 1, pp. 13-26, 1995. https://arxiv.org/abs/math/9409227 https://doi.org/10.1007/BF02198293 .. [2] B. C. Carlson, ed., Chapter 19 in "Digital Library of Mathematical Functions," NIST, US Dept. of Commerce. https://dlmf.nist.gov/19.16.E1 https://dlmf.nist.gov/19.20.ii Examples -------- Basic homogeneity property: >>> import numpy as np >>> from scipy.special import elliprg >>> x = 1.2 + 3.4j >>> y = 5. >>> z = 6. >>> scale = 0.3 + 0.4j >>> elliprg(scale*x, scale*y, scale*z) (1.195936862005246+0.8470988320464167j) >>> elliprg(x, y, z)*np.sqrt(scale) (1.195936862005246+0.8470988320464165j) Simplifications: >>> elliprg(0, y, y) 1.756203682760182 >>> 0.25*np.pi*np.sqrt(y) 1.7562036827601817 >>> elliprg(0, 0, z) 1.224744871391589 >>> 0.5*np.sqrt(z) 1.224744871391589 The surface area of a triaxial ellipsoid with semiaxes ``a``, ``b``, and ``c`` is given by .. math:: S = 4 \pi a b c R_{\mathrm{G}}(1 / a^2, 1 / b^2, 1 / c^2). >>> def ellipsoid_area(a, b, c): ... r = 4.0 * np.pi * a * b * c ... return r * elliprg(1.0 / (a * a), 1.0 / (b * b), 1.0 / (c * c)) >>> print(ellipsoid_area(1, 3, 5)) 108.62688289491807elliprj(x, y, z, p, out=None) Symmetric elliptic integral of the third kind. The function RJ is defined as [1]_ .. math:: R_{\mathrm{J}}(x, y, z, p) = \frac{3}{2} \int_0^{+\infty} [(t + x) (t + y) (t + z)]^{-1/2} (t + p)^{-1} dt .. warning:: This function should be considered experimental when the inputs are unbalanced. Check correctness with another independent implementation. Parameters ---------- x, y, z, p : array_like Real or complex input parameters. `x`, `y`, or `z` are numbers in the complex plane cut along the negative real axis (subject to further constraints, see Notes), and at most one of them can be zero. `p` must be non-zero. out : ndarray, optional Optional output array for the function values Returns ------- R : scalar or ndarray Value of the integral. If all of `x`, `y`, `z`, and `p` are real, the return value is real. Otherwise, the return value is complex. If `p` is real and negative, while `x`, `y`, and `z` are real, non-negative, and at most one of them is zero, the Cauchy principal value is returned. [1]_ [2]_ See Also -------- elliprc : Degenerate symmetric integral. elliprd : Symmetric elliptic integral of the second kind. elliprf : Completely-symmetric elliptic integral of the first kind. elliprg : Completely-symmetric elliptic integral of the second kind. Notes ----- The code implements Carlson's algorithm based on the duplication theorems and series expansion up to the 7th order. [3]_ The algorithm is slightly different from its earlier incarnation as it appears in [1]_, in that the call to `elliprc` (or ``atan``/``atanh``, see [4]_) is no longer needed in the inner loop. Asymptotic approximations are used where arguments differ widely in the order of magnitude. [5]_ The input values are subject to certain sufficient but not necessary constraints when input arguments are complex. Notably, ``x``, ``y``, and ``z`` must have non-negative real parts, unless two of them are non-negative and complex-conjugates to each other while the other is a real non-negative number. [1]_ If the inputs do not satisfy the sufficient condition described in Ref. [1]_ they are rejected outright with the output set to NaN. In the case where one of ``x``, ``y``, and ``z`` is equal to ``p``, the function ``elliprd`` should be preferred because of its less restrictive domain. .. versionadded:: 1.8.0 References ---------- .. [1] B. C. Carlson, "Numerical computation of real or complex elliptic integrals," Numer. Algorithm, vol. 10, no. 1, pp. 13-26, 1995. https://arxiv.org/abs/math/9409227 https://doi.org/10.1007/BF02198293 .. [2] B. C. Carlson, ed., Chapter 19 in "Digital Library of Mathematical Functions," NIST, US Dept. of Commerce. https://dlmf.nist.gov/19.20.iii .. [3] B. C. Carlson, J. FitzSimmons, "Reduction Theorems for Elliptic Integrands with the Square Root of Two Quadratic Factors," J. Comput. Appl. Math., vol. 118, nos. 1-2, pp. 71-85, 2000. https://doi.org/10.1016/S0377-0427(00)00282-X .. [4] F. Johansson, "Numerical Evaluation of Elliptic Functions, Elliptic Integrals and Modular Forms," in J. Blumlein, C. Schneider, P. Paule, eds., "Elliptic Integrals, Elliptic Functions and Modular Forms in Quantum Field Theory," pp. 269-293, 2019 (Cham, Switzerland: Springer Nature Switzerland) https://arxiv.org/abs/1806.06725 https://doi.org/10.1007/978-3-030-04480-0 .. [5] B. C. Carlson, J. L. Gustafson, "Asymptotic Approximations for Symmetric Elliptic Integrals," SIAM J. Math. Anls., vol. 25, no. 2, pp. 288-303, 1994. https://arxiv.org/abs/math/9310223 https://doi.org/10.1137/S0036141092228477 Examples -------- Basic homogeneity property: >>> import numpy as np >>> from scipy.special import elliprj >>> x = 1.2 + 3.4j >>> y = 5. >>> z = 6. >>> p = 7. >>> scale = 0.3 - 0.4j >>> elliprj(scale*x, scale*y, scale*z, scale*p) (0.10834905565679157+0.19694950747103812j) >>> elliprj(x, y, z, p)*np.power(scale, -1.5) (0.10834905565679556+0.19694950747103854j) Reduction to simpler elliptic integral: >>> elliprj(x, y, z, z) (0.08288462362195129-0.028376809745123258j) >>> from scipy.special import elliprd >>> elliprd(x, y, z) (0.08288462362195136-0.028376809745123296j) All arguments coincide: >>> elliprj(x, x, x, x) (-0.03986825876151896-0.14051741840449586j) >>> np.power(x, -1.5) (-0.03986825876151894-0.14051741840449583j)entr(x, out=None) Elementwise function for computing entropy. .. math:: \text{entr}(x) = \begin{cases} - x \log(x) & x > 0 \\ 0 & x = 0 \\ -\infty & \text{otherwise} \end{cases} Parameters ---------- x : ndarray Input array. out : ndarray, optional Optional output array for the function values Returns ------- res : scalar or ndarray The value of the elementwise entropy function at the given points `x`. See Also -------- kl_div, rel_entr, scipy.stats.entropy Notes ----- .. versionadded:: 0.15.0 This function is concave. The origin of this function is in convex programming; see [1]_. Given a probability distribution :math:`p_1, \ldots, p_n`, the definition of entropy in the context of *information theory* is .. math:: \sum_{i = 1}^n \mathrm{entr}(p_i). To compute the latter quantity, use `scipy.stats.entropy`. References ---------- .. [1] Boyd, Stephen and Lieven Vandenberghe. *Convex optimization*. Cambridge University Press, 2004. :doi:`https://doi.org/10.1017/CBO9780511804441`erfcinv(y, out=None) Inverse of the complementary error function. Computes the inverse of the complementary error function. In the complex domain, there is no unique complex number w satisfying erfc(w)=z. This indicates a true inverse function would be multivalued. When the domain restricts to the real, 0 < x < 2, there is a unique real number satisfying erfc(erfcinv(x)) = erfcinv(erfc(x)). It is related to inverse of the error function by erfcinv(1-x) = erfinv(x) Parameters ---------- y : ndarray Argument at which to evaluate. Domain: [0, 2] out : ndarray, optional Optional output array for the function values Returns ------- erfcinv : scalar or ndarray The inverse of erfc of y, element-wise See Also -------- erf : Error function of a complex argument erfc : Complementary error function, ``1 - erf(x)`` erfinv : Inverse of the error function Examples -------- >>> import numpy as np >>> import matplotlib.pyplot as plt >>> from scipy.special import erfcinv >>> erfcinv(0.5) 0.4769362762044699 >>> y = np.linspace(0.0, 2.0, num=11) >>> erfcinv(y) array([ inf, 0.9061938 , 0.59511608, 0.37080716, 0.17914345, -0. , -0.17914345, -0.37080716, -0.59511608, -0.9061938 , -inf]) Plot the function: >>> y = np.linspace(0, 2, 200) >>> fig, ax = plt.subplots() >>> ax.plot(y, erfcinv(y)) >>> ax.grid(True) >>> ax.set_xlabel('y') >>> ax.set_title('erfcinv(y)') >>> plt.show()erfinv(y, out=None) Inverse of the error function. Computes the inverse of the error function. In the complex domain, there is no unique complex number w satisfying erf(w)=z. This indicates a true inverse function would be multivalued. When the domain restricts to the real, -1 < x < 1, there is a unique real number satisfying erf(erfinv(x)) = x. Parameters ---------- y : ndarray Argument at which to evaluate. Domain: [-1, 1] out : ndarray, optional Optional output array for the function values Returns ------- erfinv : scalar or ndarray The inverse of erf of y, element-wise See Also -------- erf : Error function of a complex argument erfc : Complementary error function, ``1 - erf(x)`` erfcinv : Inverse of the complementary error function Notes ----- This function wraps the ``erf_inv`` routine from the Boost Math C++ library [1]_. References ---------- .. [1] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. Examples -------- >>> import numpy as np >>> import matplotlib.pyplot as plt >>> from scipy.special import erfinv, erf >>> erfinv(0.5) 0.4769362762044699 >>> y = np.linspace(-1.0, 1.0, num=9) >>> x = erfinv(y) >>> x array([ -inf, -0.81341985, -0.47693628, -0.22531206, 0. , 0.22531206, 0.47693628, 0.81341985, inf]) Verify that ``erf(erfinv(y))`` is ``y``. >>> erf(x) array([-1. , -0.75, -0.5 , -0.25, 0. , 0.25, 0.5 , 0.75, 1. ]) Plot the function: >>> y = np.linspace(-1, 1, 200) >>> fig, ax = plt.subplots() >>> ax.plot(y, erfinv(y)) >>> ax.grid(True) >>> ax.set_xlabel('y') >>> ax.set_title('erfinv(y)') >>> plt.show()eval_chebyc(n, x, out=None) Evaluate Chebyshev polynomial of the first kind on [-2, 2] at a point. These polynomials are defined as .. math:: C_n(x) = 2 T_n(x/2) where :math:`T_n` is a Chebyshev polynomial of the first kind. See 22.5.11 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the result is determined via the relation to `eval_chebyt`. x : array_like Points at which to evaluate the Chebyshev polynomial out : ndarray, optional Optional output array for the function values Returns ------- C : scalar or ndarray Values of the Chebyshev polynomial See Also -------- roots_chebyc : roots and quadrature weights of Chebyshev polynomials of the first kind on [-2, 2] chebyc : Chebyshev polynomial object numpy.polynomial.chebyshev.Chebyshev : Chebyshev series eval_chebyt : evaluate Chebycshev polynomials of the first kind References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. Examples -------- >>> import numpy as np >>> import scipy.special as sc They are a scaled version of the Chebyshev polynomials of the first kind. >>> x = np.linspace(-2, 2, 6) >>> sc.eval_chebyc(3, x) array([-2. , 1.872, 1.136, -1.136, -1.872, 2. ]) >>> 2 * sc.eval_chebyt(3, x / 2) array([-2. , 1.872, 1.136, -1.136, -1.872, 2. ])eval_chebys(n, x, out=None) Evaluate Chebyshev polynomial of the second kind on [-2, 2] at a point. These polynomials are defined as .. math:: S_n(x) = U_n(x/2) where :math:`U_n` is a Chebyshev polynomial of the second kind. See 22.5.13 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the result is determined via the relation to `eval_chebyu`. x : array_like Points at which to evaluate the Chebyshev polynomial out : ndarray, optional Optional output array for the function values Returns ------- S : scalar or ndarray Values of the Chebyshev polynomial See Also -------- roots_chebys : roots and quadrature weights of Chebyshev polynomials of the second kind on [-2, 2] chebys : Chebyshev polynomial object eval_chebyu : evaluate Chebyshev polynomials of the second kind References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. Examples -------- >>> import numpy as np >>> import scipy.special as sc They are a scaled version of the Chebyshev polynomials of the second kind. >>> x = np.linspace(-2, 2, 6) >>> sc.eval_chebys(3, x) array([-4. , 0.672, 0.736, -0.736, -0.672, 4. ]) >>> sc.eval_chebyu(3, x / 2) array([-4. , 0.672, 0.736, -0.736, -0.672, 4. ])eval_chebyt(n, x, out=None) Evaluate Chebyshev polynomial of the first kind at a point. The Chebyshev polynomials of the first kind can be defined via the Gauss hypergeometric function :math:`{}_2F_1` as .. math:: T_n(x) = {}_2F_1(n, -n; 1/2; (1 - x)/2). When :math:`n` is an integer the result is a polynomial of degree :math:`n`. See 22.5.47 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the result is determined via the relation to the Gauss hypergeometric function. x : array_like Points at which to evaluate the Chebyshev polynomial out : ndarray, optional Optional output array for the function values Returns ------- T : scalar or ndarray Values of the Chebyshev polynomial See Also -------- roots_chebyt : roots and quadrature weights of Chebyshev polynomials of the first kind chebyu : Chebychev polynomial object eval_chebyu : evaluate Chebyshev polynomials of the second kind hyp2f1 : Gauss hypergeometric function numpy.polynomial.chebyshev.Chebyshev : Chebyshev series Notes ----- This routine is numerically stable for `x` in ``[-1, 1]`` at least up to order ``10000``. References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_chebyu(n, x, out=None) Evaluate Chebyshev polynomial of the second kind at a point. The Chebyshev polynomials of the second kind can be defined via the Gauss hypergeometric function :math:`{}_2F_1` as .. math:: U_n(x) = (n + 1) {}_2F_1(-n, n + 2; 3/2; (1 - x)/2). When :math:`n` is an integer the result is a polynomial of degree :math:`n`. See 22.5.48 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the result is determined via the relation to the Gauss hypergeometric function. x : array_like Points at which to evaluate the Chebyshev polynomial out : ndarray, optional Optional output array for the function values Returns ------- U : scalar or ndarray Values of the Chebyshev polynomial See Also -------- roots_chebyu : roots and quadrature weights of Chebyshev polynomials of the second kind chebyu : Chebyshev polynomial object eval_chebyt : evaluate Chebyshev polynomials of the first kind hyp2f1 : Gauss hypergeometric function References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_gegenbauer(n, alpha, x, out=None) Evaluate Gegenbauer polynomial at a point. The Gegenbauer polynomials can be defined via the Gauss hypergeometric function :math:`{}_2F_1` as .. math:: C_n^{(\alpha)} = \frac{(2\alpha)_n}{\Gamma(n + 1)} {}_2F_1(-n, 2\alpha + n; \alpha + 1/2; (1 - z)/2). When :math:`n` is an integer the result is a polynomial of degree :math:`n`. See 22.5.46 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the result is determined via the relation to the Gauss hypergeometric function. alpha : array_like Parameter x : array_like Points at which to evaluate the Gegenbauer polynomial out : ndarray, optional Optional output array for the function values Returns ------- C : scalar or ndarray Values of the Gegenbauer polynomial See Also -------- roots_gegenbauer : roots and quadrature weights of Gegenbauer polynomials gegenbauer : Gegenbauer polynomial object hyp2f1 : Gauss hypergeometric function References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_genlaguerre(n, alpha, x, out=None) Evaluate generalized Laguerre polynomial at a point. The generalized Laguerre polynomials can be defined via the confluent hypergeometric function :math:`{}_1F_1` as .. math:: L_n^{(\alpha)}(x) = \binom{n + \alpha}{n} {}_1F_1(-n, \alpha + 1, x). When :math:`n` is an integer the result is a polynomial of degree :math:`n`. See 22.5.54 in [AS]_ for details. The Laguerre polynomials are the special case where :math:`\alpha = 0`. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the result is determined via the relation to the confluent hypergeometric function. alpha : array_like Parameter; must have ``alpha > -1`` x : array_like Points at which to evaluate the generalized Laguerre polynomial out : ndarray, optional Optional output array for the function values Returns ------- L : scalar or ndarray Values of the generalized Laguerre polynomial See Also -------- roots_genlaguerre : roots and quadrature weights of generalized Laguerre polynomials genlaguerre : generalized Laguerre polynomial object hyp1f1 : confluent hypergeometric function eval_laguerre : evaluate Laguerre polynomials References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_hermite(n, x, out=None) Evaluate physicist's Hermite polynomial at a point. Defined by .. math:: H_n(x) = (-1)^n e^{x^2} \frac{d^n}{dx^n} e^{-x^2}; :math:`H_n` is a polynomial of degree :math:`n`. See 22.11.7 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial x : array_like Points at which to evaluate the Hermite polynomial out : ndarray, optional Optional output array for the function values Returns ------- H : scalar or ndarray Values of the Hermite polynomial See Also -------- roots_hermite : roots and quadrature weights of physicist's Hermite polynomials hermite : physicist's Hermite polynomial object numpy.polynomial.hermite.Hermite : Physicist's Hermite series eval_hermitenorm : evaluate Probabilist's Hermite polynomials References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_hermitenorm(n, x, out=None) Evaluate probabilist's (normalized) Hermite polynomial at a point. Defined by .. math:: He_n(x) = (-1)^n e^{x^2/2} \frac{d^n}{dx^n} e^{-x^2/2}; :math:`He_n` is a polynomial of degree :math:`n`. See 22.11.8 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial x : array_like Points at which to evaluate the Hermite polynomial out : ndarray, optional Optional output array for the function values Returns ------- He : scalar or ndarray Values of the Hermite polynomial See Also -------- roots_hermitenorm : roots and quadrature weights of probabilist's Hermite polynomials hermitenorm : probabilist's Hermite polynomial object numpy.polynomial.hermite_e.HermiteE : Probabilist's Hermite series eval_hermite : evaluate physicist's Hermite polynomials References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_jacobi(n, alpha, beta, x, out=None) Evaluate Jacobi polynomial at a point. The Jacobi polynomials can be defined via the Gauss hypergeometric function :math:`{}_2F_1` as .. math:: P_n^{(\alpha, \beta)}(x) = \frac{(\alpha + 1)_n}{\Gamma(n + 1)} {}_2F_1(-n, 1 + \alpha + \beta + n; \alpha + 1; (1 - z)/2) where :math:`(\cdot)_n` is the Pochhammer symbol; see `poch`. When :math:`n` is an integer the result is a polynomial of degree :math:`n`. See 22.5.42 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer the result is determined via the relation to the Gauss hypergeometric function. alpha : array_like Parameter beta : array_like Parameter x : array_like Points at which to evaluate the polynomial out : ndarray, optional Optional output array for the function values Returns ------- P : scalar or ndarray Values of the Jacobi polynomial See Also -------- roots_jacobi : roots and quadrature weights of Jacobi polynomials jacobi : Jacobi polynomial object hyp2f1 : Gauss hypergeometric function References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_laguerre(n, x, out=None) Evaluate Laguerre polynomial at a point. The Laguerre polynomials can be defined via the confluent hypergeometric function :math:`{}_1F_1` as .. math:: L_n(x) = {}_1F_1(-n, 1, x). See 22.5.16 and 22.5.54 in [AS]_ for details. When :math:`n` is an integer the result is a polynomial of degree :math:`n`. Parameters ---------- n : array_like Degree of the polynomial. If not an integer the result is determined via the relation to the confluent hypergeometric function. x : array_like Points at which to evaluate the Laguerre polynomial out : ndarray, optional Optional output array for the function values Returns ------- L : scalar or ndarray Values of the Laguerre polynomial See Also -------- roots_laguerre : roots and quadrature weights of Laguerre polynomials laguerre : Laguerre polynomial object numpy.polynomial.laguerre.Laguerre : Laguerre series eval_genlaguerre : evaluate generalized Laguerre polynomials References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_legendre(n, x, out=None) Evaluate Legendre polynomial at a point. The Legendre polynomials can be defined via the Gauss hypergeometric function :math:`{}_2F_1` as .. math:: P_n(x) = {}_2F_1(-n, n + 1; 1; (1 - x)/2). When :math:`n` is an integer the result is a polynomial of degree :math:`n`. See 22.5.49 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the result is determined via the relation to the Gauss hypergeometric function. x : array_like Points at which to evaluate the Legendre polynomial out : ndarray, optional Optional output array for the function values Returns ------- P : scalar or ndarray Values of the Legendre polynomial See Also -------- roots_legendre : roots and quadrature weights of Legendre polynomials legendre : Legendre polynomial object hyp2f1 : Gauss hypergeometric function numpy.polynomial.legendre.Legendre : Legendre series References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. Examples -------- >>> import numpy as np >>> from scipy.special import eval_legendre Evaluate the zero-order Legendre polynomial at x = 0 >>> eval_legendre(0, 0) 1.0 Evaluate the first-order Legendre polynomial between -1 and 1 >>> X = np.linspace(-1, 1, 5) # Domain of Legendre polynomials >>> eval_legendre(1, X) array([-1. , -0.5, 0. , 0.5, 1. ]) Evaluate Legendre polynomials of order 0 through 4 at x = 0 >>> N = range(0, 5) >>> eval_legendre(N, 0) array([ 1. , 0. , -0.5 , 0. , 0.375]) Plot Legendre polynomials of order 0 through 4 >>> X = np.linspace(-1, 1) >>> import matplotlib.pyplot as plt >>> for n in range(0, 5): ... y = eval_legendre(n, X) ... plt.plot(X, y, label=r'$P_{}(x)$'.format(n)) >>> plt.title("Legendre Polynomials") >>> plt.xlabel("x") >>> plt.ylabel(r'$P_n(x)$') >>> plt.legend(loc='lower right') >>> plt.show()eval_sh_chebyt(n, x, out=None) Evaluate shifted Chebyshev polynomial of the first kind at a point. These polynomials are defined as .. math:: T_n^*(x) = T_n(2x - 1) where :math:`T_n` is a Chebyshev polynomial of the first kind. See 22.5.14 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the result is determined via the relation to `eval_chebyt`. x : array_like Points at which to evaluate the shifted Chebyshev polynomial out : ndarray, optional Optional output array for the function values Returns ------- T : scalar or ndarray Values of the shifted Chebyshev polynomial See Also -------- roots_sh_chebyt : roots and quadrature weights of shifted Chebyshev polynomials of the first kind sh_chebyt : shifted Chebyshev polynomial object eval_chebyt : evaluate Chebyshev polynomials of the first kind numpy.polynomial.chebyshev.Chebyshev : Chebyshev series References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_sh_chebyu(n, x, out=None) Evaluate shifted Chebyshev polynomial of the second kind at a point. These polynomials are defined as .. math:: U_n^*(x) = U_n(2x - 1) where :math:`U_n` is a Chebyshev polynomial of the first kind. See 22.5.15 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the result is determined via the relation to `eval_chebyu`. x : array_like Points at which to evaluate the shifted Chebyshev polynomial out : ndarray, optional Optional output array for the function values Returns ------- U : scalar or ndarray Values of the shifted Chebyshev polynomial See Also -------- roots_sh_chebyu : roots and quadrature weights of shifted Chebychev polynomials of the second kind sh_chebyu : shifted Chebyshev polynomial object eval_chebyu : evaluate Chebyshev polynomials of the second kind References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_sh_jacobi(n, p, q, x, out=None) Evaluate shifted Jacobi polynomial at a point. Defined by .. math:: G_n^{(p, q)}(x) = \binom{2n + p - 1}{n}^{-1} P_n^{(p - q, q - 1)}(2x - 1), where :math:`P_n^{(\cdot, \cdot)}` is the n-th Jacobi polynomial. See 22.5.2 in [AS]_ for details. Parameters ---------- n : int Degree of the polynomial. If not an integer, the result is determined via the relation to `binom` and `eval_jacobi`. p : float Parameter q : float Parameter out : ndarray, optional Optional output array for the function values Returns ------- G : scalar or ndarray Values of the shifted Jacobi polynomial. See Also -------- roots_sh_jacobi : roots and quadrature weights of shifted Jacobi polynomials sh_jacobi : shifted Jacobi polynomial object eval_jacobi : evaluate Jacobi polynomials References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.eval_sh_legendre(n, x, out=None) Evaluate shifted Legendre polynomial at a point. These polynomials are defined as .. math:: P_n^*(x) = P_n(2x - 1) where :math:`P_n` is a Legendre polynomial. See 2.2.11 in [AS]_ for details. Parameters ---------- n : array_like Degree of the polynomial. If not an integer, the value is determined via the relation to `eval_legendre`. x : array_like Points at which to evaluate the shifted Legendre polynomial out : ndarray, optional Optional output array for the function values Returns ------- P : scalar or ndarray Values of the shifted Legendre polynomial See Also -------- roots_sh_legendre : roots and quadrature weights of shifted Legendre polynomials sh_legendre : shifted Legendre polynomial object eval_legendre : evaluate Legendre polynomials numpy.polynomial.legendre.Legendre : Legendre series References ---------- .. [AS] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972.expn(n, x, out=None) Generalized exponential integral En. For integer :math:`n \geq 0` and real :math:`x \geq 0` the generalized exponential integral is defined as [dlmf]_ .. math:: E_n(x) = x^{n - 1} \int_x^\infty \frac{e^{-t}}{t^n} dt. Parameters ---------- n : array_like Non-negative integers x : array_like Real argument out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray Values of the generalized exponential integral See Also -------- exp1 : special case of :math:`E_n` for :math:`n = 1` expi : related to :math:`E_n` when :math:`n = 1` References ---------- .. [dlmf] Digital Library of Mathematical Functions, 8.19.2 https://dlmf.nist.gov/8.19#E2 Examples -------- >>> import numpy as np >>> import scipy.special as sc Its domain is nonnegative n and x. >>> sc.expn(-1, 1.0), sc.expn(1, -1.0) (nan, nan) It has a pole at ``x = 0`` for ``n = 1, 2``; for larger ``n`` it is equal to ``1 / (n - 1)``. >>> sc.expn([0, 1, 2, 3, 4], 0) array([ inf, inf, 1. , 0.5 , 0.33333333]) For n equal to 0 it reduces to ``exp(-x) / x``. >>> x = np.array([1, 2, 3, 4]) >>> sc.expn(0, x) array([0.36787944, 0.06766764, 0.01659569, 0.00457891]) >>> np.exp(-x) / x array([0.36787944, 0.06766764, 0.01659569, 0.00457891]) For n equal to 1 it reduces to `exp1`. >>> sc.expn(1, x) array([0.21938393, 0.04890051, 0.01304838, 0.00377935]) >>> sc.exp1(x) array([0.21938393, 0.04890051, 0.01304838, 0.00377935])fdtr(dfn, dfd, x, out=None) F cumulative distribution function. Returns the value of the cumulative distribution function of the F-distribution, also known as Snedecor's F-distribution or the Fisher-Snedecor distribution. The F-distribution with parameters :math:`d_n` and :math:`d_d` is the distribution of the random variable, .. math:: X = \frac{U_n/d_n}{U_d/d_d}, where :math:`U_n` and :math:`U_d` are random variables distributed :math:`\chi^2`, with :math:`d_n` and :math:`d_d` degrees of freedom, respectively. Parameters ---------- dfn : array_like First parameter (positive float). dfd : array_like Second parameter (positive float). x : array_like Argument (nonnegative float). out : ndarray, optional Optional output array for the function values Returns ------- y : scalar or ndarray The CDF of the F-distribution with parameters `dfn` and `dfd` at `x`. See Also -------- fdtrc : F distribution survival function fdtri : F distribution inverse cumulative distribution scipy.stats.f : F distribution Notes ----- The regularized incomplete beta function is used, according to the formula, .. math:: F(d_n, d_d; x) = I_{xd_n/(d_d + xd_n)}(d_n/2, d_d/2). Wrapper for the Cephes [1]_ routine `fdtr`. The F distribution is also available as `scipy.stats.f`. Calling `fdtr` directly can improve performance compared to the ``cdf`` method of `scipy.stats.f` (see last example below). References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ Examples -------- Calculate the function for ``dfn=1`` and ``dfd=2`` at ``x=1``. >>> import numpy as np >>> from scipy.special import fdtr >>> fdtr(1, 2, 1) 0.5773502691896258 Calculate the function at several points by providing a NumPy array for `x`. >>> x = np.array([0.5, 2., 3.]) >>> fdtr(1, 2, x) array([0.4472136 , 0.70710678, 0.77459667]) Plot the function for several parameter sets. >>> import matplotlib.pyplot as plt >>> dfn_parameters = [1, 5, 10, 50] >>> dfd_parameters = [1, 1, 2, 3] >>> linestyles = ['solid', 'dashed', 'dotted', 'dashdot'] >>> parameters_list = list(zip(dfn_parameters, dfd_parameters, ... linestyles)) >>> x = np.linspace(0, 30, 1000) >>> fig, ax = plt.subplots() >>> for parameter_set in parameters_list: ... dfn, dfd, style = parameter_set ... fdtr_vals = fdtr(dfn, dfd, x) ... ax.plot(x, fdtr_vals, label=rf"$d_n={dfn},\, d_d={dfd}$", ... ls=style) >>> ax.legend() >>> ax.set_xlabel("$x$") >>> ax.set_title("F distribution cumulative distribution function") >>> plt.show() The F distribution is also available as `scipy.stats.f`. Using `fdtr` directly can be much faster than calling the ``cdf`` method of `scipy.stats.f`, especially for small arrays or individual values. To get the same results one must use the following parametrization: ``stats.f(dfn, dfd).cdf(x)=fdtr(dfn, dfd, x)``. >>> from scipy.stats import f >>> dfn, dfd = 1, 2 >>> x = 1 >>> fdtr_res = fdtr(dfn, dfd, x) # this will often be faster than below >>> f_dist_res = f(dfn, dfd).cdf(x) >>> fdtr_res == f_dist_res # test that results are equal Truefdtrc(dfn, dfd, x, out=None) F survival function. Returns the complemented F-distribution function (the integral of the density from `x` to infinity). Parameters ---------- dfn : array_like First parameter (positive float). dfd : array_like Second parameter (positive float). x : array_like Argument (nonnegative float). out : ndarray, optional Optional output array for the function values Returns ------- y : scalar or ndarray The complemented F-distribution function with parameters `dfn` and `dfd` at `x`. See Also -------- fdtr : F distribution cumulative distribution function fdtri : F distribution inverse cumulative distribution function scipy.stats.f : F distribution Notes ----- The regularized incomplete beta function is used, according to the formula, .. math:: F(d_n, d_d; x) = I_{d_d/(d_d + xd_n)}(d_d/2, d_n/2). Wrapper for the Cephes [1]_ routine `fdtrc`. The F distribution is also available as `scipy.stats.f`. Calling `fdtrc` directly can improve performance compared to the ``sf`` method of `scipy.stats.f` (see last example below). References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ Examples -------- Calculate the function for ``dfn=1`` and ``dfd=2`` at ``x=1``. >>> import numpy as np >>> from scipy.special import fdtrc >>> fdtrc(1, 2, 1) 0.42264973081037427 Calculate the function at several points by providing a NumPy array for `x`. >>> x = np.array([0.5, 2., 3.]) >>> fdtrc(1, 2, x) array([0.5527864 , 0.29289322, 0.22540333]) Plot the function for several parameter sets. >>> import matplotlib.pyplot as plt >>> dfn_parameters = [1, 5, 10, 50] >>> dfd_parameters = [1, 1, 2, 3] >>> linestyles = ['solid', 'dashed', 'dotted', 'dashdot'] >>> parameters_list = list(zip(dfn_parameters, dfd_parameters, ... linestyles)) >>> x = np.linspace(0, 30, 1000) >>> fig, ax = plt.subplots() >>> for parameter_set in parameters_list: ... dfn, dfd, style = parameter_set ... fdtrc_vals = fdtrc(dfn, dfd, x) ... ax.plot(x, fdtrc_vals, label=rf"$d_n={dfn},\, d_d={dfd}$", ... ls=style) >>> ax.legend() >>> ax.set_xlabel("$x$") >>> ax.set_title("F distribution survival function") >>> plt.show() The F distribution is also available as `scipy.stats.f`. Using `fdtrc` directly can be much faster than calling the ``sf`` method of `scipy.stats.f`, especially for small arrays or individual values. To get the same results one must use the following parametrization: ``stats.f(dfn, dfd).sf(x)=fdtrc(dfn, dfd, x)``. >>> from scipy.stats import f >>> dfn, dfd = 1, 2 >>> x = 1 >>> fdtrc_res = fdtrc(dfn, dfd, x) # this will often be faster than below >>> f_dist_res = f(dfn, dfd).sf(x) >>> f_dist_res == fdtrc_res # test that results are equal Truefdtri(dfn, dfd, p, out=None) The `p`-th quantile of the F-distribution. This function is the inverse of the F-distribution CDF, `fdtr`, returning the `x` such that `fdtr(dfn, dfd, x) = p`. Parameters ---------- dfn : array_like First parameter (positive float). dfd : array_like Second parameter (positive float). p : array_like Cumulative probability, in [0, 1]. out : ndarray, optional Optional output array for the function values Returns ------- x : scalar or ndarray The quantile corresponding to `p`. See Also -------- fdtr : F distribution cumulative distribution function fdtrc : F distribution survival function scipy.stats.f : F distribution Notes ----- The computation is carried out using the relation to the inverse regularized beta function, :math:`I^{-1}_x(a, b)`. Let :math:`z = I^{-1}_p(d_d/2, d_n/2).` Then, .. math:: x = \frac{d_d (1 - z)}{d_n z}. If `p` is such that :math:`x < 0.5`, the following relation is used instead for improved stability: let :math:`z' = I^{-1}_{1 - p}(d_n/2, d_d/2).` Then, .. math:: x = \frac{d_d z'}{d_n (1 - z')}. Wrapper for the Cephes [1]_ routine `fdtri`. The F distribution is also available as `scipy.stats.f`. Calling `fdtri` directly can improve performance compared to the ``ppf`` method of `scipy.stats.f` (see last example below). References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ Examples -------- `fdtri` represents the inverse of the F distribution CDF which is available as `fdtr`. Here, we calculate the CDF for ``df1=1``, ``df2=2`` at ``x=3``. `fdtri` then returns ``3`` given the same values for `df1`, `df2` and the computed CDF value. >>> import numpy as np >>> from scipy.special import fdtri, fdtr >>> df1, df2 = 1, 2 >>> x = 3 >>> cdf_value = fdtr(df1, df2, x) >>> fdtri(df1, df2, cdf_value) 3.000000000000006 Calculate the function at several points by providing a NumPy array for `x`. >>> x = np.array([0.1, 0.4, 0.7]) >>> fdtri(1, 2, x) array([0.02020202, 0.38095238, 1.92156863]) Plot the function for several parameter sets. >>> import matplotlib.pyplot as plt >>> dfn_parameters = [50, 10, 1, 50] >>> dfd_parameters = [0.5, 1, 1, 5] >>> linestyles = ['solid', 'dashed', 'dotted', 'dashdot'] >>> parameters_list = list(zip(dfn_parameters, dfd_parameters, ... linestyles)) >>> x = np.linspace(0, 1, 1000) >>> fig, ax = plt.subplots() >>> for parameter_set in parameters_list: ... dfn, dfd, style = parameter_set ... fdtri_vals = fdtri(dfn, dfd, x) ... ax.plot(x, fdtri_vals, label=rf"$d_n={dfn},\, d_d={dfd}$", ... ls=style) >>> ax.legend() >>> ax.set_xlabel("$x$") >>> title = "F distribution inverse cumulative distribution function" >>> ax.set_title(title) >>> ax.set_ylim(0, 30) >>> plt.show() The F distribution is also available as `scipy.stats.f`. Using `fdtri` directly can be much faster than calling the ``ppf`` method of `scipy.stats.f`, especially for small arrays or individual values. To get the same results one must use the following parametrization: ``stats.f(dfn, dfd).ppf(x)=fdtri(dfn, dfd, x)``. >>> from scipy.stats import f >>> dfn, dfd = 1, 2 >>> x = 0.7 >>> fdtri_res = fdtri(dfn, dfd, x) # this will often be faster than below >>> f_dist_res = f(dfn, dfd).ppf(x) >>> f_dist_res == fdtri_res # test that results are equal Truefdtridfd(dfn, p, x, out=None) Inverse to `fdtr` vs dfd Finds the F density argument dfd such that ``fdtr(dfn, dfd, x) == p``. Parameters ---------- dfn : array_like First parameter (positive float). p : array_like Cumulative probability, in [0, 1]. x : array_like Argument (nonnegative float). out : ndarray, optional Optional output array for the function values Returns ------- dfd : scalar or ndarray `dfd` such that ``fdtr(dfn, dfd, x) == p``. See Also -------- fdtr : F distribution cumulative distribution function fdtrc : F distribution survival function fdtri : F distribution quantile function scipy.stats.f : F distribution Examples -------- Compute the F distribution cumulative distribution function for one parameter set. >>> from scipy.special import fdtridfd, fdtr >>> dfn, dfd, x = 10, 5, 2 >>> cdf_value = fdtr(dfn, dfd, x) >>> cdf_value 0.7700248806501017 Verify that `fdtridfd` recovers the original value for `dfd`: >>> fdtridfd(dfn, cdf_value, x) 5.0gdtr(a, b, x, out=None) Gamma distribution cumulative distribution function. Returns the integral from zero to `x` of the gamma probability density function, .. math:: F = \int_0^x \frac{a^b}{\Gamma(b)} t^{b-1} e^{-at}\,dt, where :math:`\Gamma` is the gamma function. Parameters ---------- a : array_like The rate parameter of the gamma distribution, sometimes denoted :math:`\beta` (float). It is also the reciprocal of the scale parameter :math:`\theta`. b : array_like The shape parameter of the gamma distribution, sometimes denoted :math:`\alpha` (float). x : array_like The quantile (upper limit of integration; float). out : ndarray, optional Optional output array for the function values Returns ------- F : scalar or ndarray The CDF of the gamma distribution with parameters `a` and `b` evaluated at `x`. See Also -------- gdtrc : 1 - CDF of the gamma distribution. scipy.stats.gamma: Gamma distribution Notes ----- The evaluation is carried out using the relation to the incomplete gamma integral (regularized gamma function). Wrapper for the Cephes [1]_ routine `gdtr`. Calling `gdtr` directly can improve performance compared to the ``cdf`` method of `scipy.stats.gamma` (see last example below). References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ Examples -------- Compute the function for ``a=1``, ``b=2`` at ``x=5``. >>> import numpy as np >>> from scipy.special import gdtr >>> import matplotlib.pyplot as plt >>> gdtr(1., 2., 5.) 0.9595723180054873 Compute the function for ``a=1`` and ``b=2`` at several points by providing a NumPy array for `x`. >>> xvalues = np.array([1., 2., 3., 4]) >>> gdtr(1., 1., xvalues) array([0.63212056, 0.86466472, 0.95021293, 0.98168436]) `gdtr` can evaluate different parameter sets by providing arrays with broadcasting compatible shapes for `a`, `b` and `x`. Here we compute the function for three different `a` at four positions `x` and ``b=3``, resulting in a 3x4 array. >>> a = np.array([[0.5], [1.5], [2.5]]) >>> x = np.array([1., 2., 3., 4]) >>> a.shape, x.shape ((3, 1), (4,)) >>> gdtr(a, 3., x) array([[0.01438768, 0.0803014 , 0.19115317, 0.32332358], [0.19115317, 0.57680992, 0.82642193, 0.9380312 ], [0.45618688, 0.87534798, 0.97974328, 0.9972306 ]]) Plot the function for four different parameter sets. >>> a_parameters = [0.3, 1, 2, 6] >>> b_parameters = [2, 10, 15, 20] >>> linestyles = ['solid', 'dashed', 'dotted', 'dashdot'] >>> parameters_list = list(zip(a_parameters, b_parameters, linestyles)) >>> x = np.linspace(0, 30, 1000) >>> fig, ax = plt.subplots() >>> for parameter_set in parameters_list: ... a, b, style = parameter_set ... gdtr_vals = gdtr(a, b, x) ... ax.plot(x, gdtr_vals, label=fr"$a= {a},\, b={b}$", ls=style) >>> ax.legend() >>> ax.set_xlabel("$x$") >>> ax.set_title("Gamma distribution cumulative distribution function") >>> plt.show() The gamma distribution is also available as `scipy.stats.gamma`. Using `gdtr` directly can be much faster than calling the ``cdf`` method of `scipy.stats.gamma`, especially for small arrays or individual values. To get the same results one must use the following parametrization: ``stats.gamma(b, scale=1/a).cdf(x)=gdtr(a, b, x)``. >>> from scipy.stats import gamma >>> a = 2. >>> b = 3 >>> x = 1. >>> gdtr_result = gdtr(a, b, x) # this will often be faster than below >>> gamma_dist_result = gamma(b, scale=1/a).cdf(x) >>> gdtr_result == gamma_dist_result # test that results are equal Truegdtrc(a, b, x, out=None) Gamma distribution survival function. Integral from `x` to infinity of the gamma probability density function, .. math:: F = \int_x^\infty \frac{a^b}{\Gamma(b)} t^{b-1} e^{-at}\,dt, where :math:`\Gamma` is the gamma function. Parameters ---------- a : array_like The rate parameter of the gamma distribution, sometimes denoted :math:`\beta` (float). It is also the reciprocal of the scale parameter :math:`\theta`. b : array_like The shape parameter of the gamma distribution, sometimes denoted :math:`\alpha` (float). x : array_like The quantile (lower limit of integration; float). out : ndarray, optional Optional output array for the function values Returns ------- F : scalar or ndarray The survival function of the gamma distribution with parameters `a` and `b` evaluated at `x`. See Also -------- gdtr: Gamma distribution cumulative distribution function scipy.stats.gamma: Gamma distribution gdtrix Notes ----- The evaluation is carried out using the relation to the incomplete gamma integral (regularized gamma function). Wrapper for the Cephes [1]_ routine `gdtrc`. Calling `gdtrc` directly can improve performance compared to the ``sf`` method of `scipy.stats.gamma` (see last example below). References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ Examples -------- Compute the function for ``a=1`` and ``b=2`` at ``x=5``. >>> import numpy as np >>> from scipy.special import gdtrc >>> import matplotlib.pyplot as plt >>> gdtrc(1., 2., 5.) 0.04042768199451279 Compute the function for ``a=1``, ``b=2`` at several points by providing a NumPy array for `x`. >>> xvalues = np.array([1., 2., 3., 4]) >>> gdtrc(1., 1., xvalues) array([0.36787944, 0.13533528, 0.04978707, 0.01831564]) `gdtrc` can evaluate different parameter sets by providing arrays with broadcasting compatible shapes for `a`, `b` and `x`. Here we compute the function for three different `a` at four positions `x` and ``b=3``, resulting in a 3x4 array. >>> a = np.array([[0.5], [1.5], [2.5]]) >>> x = np.array([1., 2., 3., 4]) >>> a.shape, x.shape ((3, 1), (4,)) >>> gdtrc(a, 3., x) array([[0.98561232, 0.9196986 , 0.80884683, 0.67667642], [0.80884683, 0.42319008, 0.17357807, 0.0619688 ], [0.54381312, 0.12465202, 0.02025672, 0.0027694 ]]) Plot the function for four different parameter sets. >>> a_parameters = [0.3, 1, 2, 6] >>> b_parameters = [2, 10, 15, 20] >>> linestyles = ['solid', 'dashed', 'dotted', 'dashdot'] >>> parameters_list = list(zip(a_parameters, b_parameters, linestyles)) >>> x = np.linspace(0, 30, 1000) >>> fig, ax = plt.subplots() >>> for parameter_set in parameters_list: ... a, b, style = parameter_set ... gdtrc_vals = gdtrc(a, b, x) ... ax.plot(x, gdtrc_vals, label=fr"$a= {a},\, b={b}$", ls=style) >>> ax.legend() >>> ax.set_xlabel("$x$") >>> ax.set_title("Gamma distribution survival function") >>> plt.show() The gamma distribution is also available as `scipy.stats.gamma`. Using `gdtrc` directly can be much faster than calling the ``sf`` method of `scipy.stats.gamma`, especially for small arrays or individual values. To get the same results one must use the following parametrization: ``stats.gamma(b, scale=1/a).sf(x)=gdtrc(a, b, x)``. >>> from scipy.stats import gamma >>> a = 2 >>> b = 3 >>> x = 1. >>> gdtrc_result = gdtrc(a, b, x) # this will often be faster than below >>> gamma_dist_result = gamma(b, scale=1/a).sf(x) >>> gdtrc_result == gamma_dist_result # test that results are equal Truegdtria(p, b, x, out=None) Inverse of `gdtr` vs a. Returns the inverse with respect to the parameter `a` of ``p = gdtr(a, b, x)``, the cumulative distribution function of the gamma distribution. Parameters ---------- p : array_like Probability values. b : array_like `b` parameter values of `gdtr(a, b, x)`. `b` is the "shape" parameter of the gamma distribution. x : array_like Nonnegative real values, from the domain of the gamma distribution. out : ndarray, optional If a fourth argument is given, it must be a numpy.ndarray whose size matches the broadcast result of `a`, `b` and `x`. `out` is then the array returned by the function. Returns ------- a : scalar or ndarray Values of the `a` parameter such that ``p = gdtr(a, b, x)`. ``1/a`` is the "scale" parameter of the gamma distribution. See Also -------- gdtr : CDF of the gamma distribution. gdtrib : Inverse with respect to `b` of `gdtr(a, b, x)`. gdtrix : Inverse with respect to `x` of `gdtr(a, b, x)`. Notes ----- Wrapper for the CDFLIB [1]_ Fortran routine `cdfgam`. The cumulative distribution function `p` is computed using a routine by DiDinato and Morris [2]_. Computation of `a` involves a search for a value that produces the desired value of `p`. The search relies on the monotonicity of `p` with `a`. References ---------- .. [1] Barry Brown, James Lovato, and Kathy Russell, CDFLIB: Library of Fortran Routines for Cumulative Distribution Functions, Inverses, and Other Parameters. .. [2] DiDinato, A. R. and Morris, A. H., Computation of the incomplete gamma function ratios and their inverse. ACM Trans. Math. Softw. 12 (1986), 377-393. Examples -------- First evaluate `gdtr`. >>> from scipy.special import gdtr, gdtria >>> p = gdtr(1.2, 3.4, 5.6) >>> print(p) 0.94378087442 Verify the inverse. >>> gdtria(p, 3.4, 5.6) 1.2gdtrib(a, p, x, out=None) Inverse of `gdtr` vs b. Returns the inverse with respect to the parameter `b` of ``p = gdtr(a, b, x)``, the cumulative distribution function of the gamma distribution. Parameters ---------- a : array_like `a` parameter values of ``gdtr(a, b, x)`. ``1/a`` is the "scale" parameter of the gamma distribution. p : array_like Probability values. x : array_like Nonnegative real values, from the domain of the gamma distribution. out : ndarray, optional If a fourth argument is given, it must be a numpy.ndarray whose size matches the broadcast result of `a`, `b` and `x`. `out` is then the array returned by the function. Returns ------- b : scalar or ndarray Values of the `b` parameter such that `p = gdtr(a, b, x)`. `b` is the "shape" parameter of the gamma distribution. See Also -------- gdtr : CDF of the gamma distribution. gdtria : Inverse with respect to `a` of `gdtr(a, b, x)`. gdtrix : Inverse with respect to `x` of `gdtr(a, b, x)`. Notes ----- The cumulative distribution function `p` is computed using the Cephes [1]_ routines `igam` and `igamc`. Computation of `b` involves a search for a value that produces the desired value of `p` using Chandrupatla's bracketing root finding algorithm [2]_. Note that there are some edge cases where `gdtrib` is extended by taking limits where they are uniquely defined. In particular ``x == 0`` with ``p > 0`` and ``p == 0`` with ``x > 0``. For these edge cases, a numerical result will be returned for ``gdtrib(a, p, x)`` even though ``gdtr(a, gdtrib(a, p, x), x)`` is undefined. References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ .. [2] Chandrupatla, Tirupathi R. "A new hybrid quadratic/bisection algorithm for finding the zero of a nonlinear function without using derivatives". Advances in Engineering Software, 28(3), 145-149. https://doi.org/10.1016/s0965-9978(96)00051-8 Examples -------- First evaluate `gdtr`. >>> from scipy.special import gdtr, gdtrib >>> p = gdtr(1.2, 3.4, 5.6) >>> print(p) 0.94378087442 Verify the inverse. >>> gdtrib(1.2, p, 5.6) 3.3999999999999995gdtrix(a, b, p, out=None) Inverse of `gdtr` vs x. Returns the inverse with respect to the parameter `x` of ``p = gdtr(a, b, x)``, the cumulative distribution function of the gamma distribution. This is also known as the pth quantile of the distribution. Parameters ---------- a : array_like `a` parameter values of ``gdtr(a, b, x)``. ``1/a`` is the "scale" parameter of the gamma distribution. b : array_like `b` parameter values of ``gdtr(a, b, x)``. `b` is the "shape" parameter of the gamma distribution. p : array_like Probability values. out : ndarray, optional If a fourth argument is given, it must be a numpy.ndarray whose size matches the broadcast result of `a`, `b` and `x`. `out` is then the array returned by the function. Returns ------- x : scalar or ndarray Values of the `x` parameter such that `p = gdtr(a, b, x)`. See Also -------- gdtr : CDF of the gamma distribution. gdtria : Inverse with respect to `a` of ``gdtr(a, b, x)``. gdtrib : Inverse with respect to `b` of ``gdtr(a, b, x)``. Notes ----- Wrapper for the CDFLIB [1]_ Fortran routine `cdfgam`. The cumulative distribution function `p` is computed using a routine by DiDinato and Morris [2]_. Computation of `x` involves a search for a value that produces the desired value of `p`. The search relies on the monotonicity of `p` with `x`. References ---------- .. [1] Barry Brown, James Lovato, and Kathy Russell, CDFLIB: Library of Fortran Routines for Cumulative Distribution Functions, Inverses, and Other Parameters. .. [2] DiDinato, A. R. and Morris, A. H., Computation of the incomplete gamma function ratios and their inverse. ACM Trans. Math. Softw. 12 (1986), 377-393. Examples -------- First evaluate `gdtr`. >>> from scipy.special import gdtr, gdtrix >>> p = gdtr(1.2, 3.4, 5.6) >>> print(p) 0.94378087442 Verify the inverse. >>> gdtrix(1.2, 3.4, p) 5.5999999999999996huber(delta, r, out=None) Huber loss function. .. math:: \text{huber}(\delta, r) = \begin{cases} \infty & \delta < 0 \\ \frac{1}{2}r^2 & 0 \le \delta, | r | \le \delta \\ \delta ( |r| - \frac{1}{2}\delta ) & \text{otherwise} \end{cases} Parameters ---------- delta : ndarray Input array, indicating the quadratic vs. linear loss changepoint. r : ndarray Input array, possibly representing residuals. out : ndarray, optional Optional output array for the function values Returns ------- scalar or ndarray The computed Huber loss function values. See Also -------- pseudo_huber : smooth approximation of this function Notes ----- `huber` is useful as a loss function in robust statistics or machine learning to reduce the influence of outliers as compared to the common squared error loss, residuals with a magnitude higher than `delta` are not squared [1]_. Typically, `r` represents residuals, the difference between a model prediction and data. Then, for :math:`|r|\leq\delta`, `huber` resembles the squared error and for :math:`|r|>\delta` the absolute error. This way, the Huber loss often achieves a fast convergence in model fitting for small residuals like the squared error loss function and still reduces the influence of outliers (:math:`|r|>\delta`) like the absolute error loss. As :math:`\delta` is the cutoff between squared and absolute error regimes, it has to be tuned carefully for each problem. `huber` is also convex, making it suitable for gradient based optimization. .. versionadded:: 0.15.0 References ---------- .. [1] Peter Huber. "Robust Estimation of a Location Parameter", 1964. Annals of Statistics. 53 (1): 73 - 101. Examples -------- Import all necessary modules. >>> import numpy as np >>> from scipy.special import huber >>> import matplotlib.pyplot as plt Compute the function for ``delta=1`` at ``r=2`` >>> huber(1., 2.) 1.5 Compute the function for different `delta` by providing a NumPy array or list for `delta`. >>> huber([1., 3., 5.], 4.) array([3.5, 7.5, 8. ]) Compute the function at different points by providing a NumPy array or list for `r`. >>> huber(2., np.array([1., 1.5, 3.])) array([0.5 , 1.125, 4. ]) The function can be calculated for different `delta` and `r` by providing arrays for both with compatible shapes for broadcasting. >>> r = np.array([1., 2.5, 8., 10.]) >>> deltas = np.array([[1.], [5.], [9.]]) >>> print(r.shape, deltas.shape) (4,) (3, 1) >>> huber(deltas, r) array([[ 0.5 , 2. , 7.5 , 9.5 ], [ 0.5 , 3.125, 27.5 , 37.5 ], [ 0.5 , 3.125, 32. , 49.5 ]]) Plot the function for different `delta`. >>> x = np.linspace(-4, 4, 500) >>> deltas = [1, 2, 3] >>> linestyles = ["dashed", "dotted", "dashdot"] >>> fig, ax = plt.subplots() >>> combined_plot_parameters = list(zip(deltas, linestyles)) >>> for delta, style in combined_plot_parameters: ... ax.plot(x, huber(delta, x), label=fr"$\delta={delta}$", ls=style) >>> ax.legend(loc="upper center") >>> ax.set_xlabel("$x$") >>> ax.set_title(r"Huber loss function $h_{\delta}(x)$") >>> ax.set_xlim(-4, 4) >>> ax.set_ylim(0, 8) >>> plt.show()hyp0f1(v, z, out=None) Confluent hypergeometric limit function 0F1. Parameters ---------- v : array_like Real-valued parameter z : array_like Real- or complex-valued argument out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray The confluent hypergeometric limit function Notes ----- This function is defined as: .. math:: _0F_1(v, z) = \sum_{k=0}^{\infty}\frac{z^k}{(v)_k k!}. It's also the limit as :math:`q \to \infty` of :math:`_1F_1(q; v; z/q)`, and satisfies the differential equation :math:`f''(z) + vf'(z) = f(z)`. See [1]_ for more information. References ---------- .. [1] Wolfram MathWorld, "Confluent Hypergeometric Limit Function", http://mathworld.wolfram.com/ConfluentHypergeometricLimitFunction.html Examples -------- >>> import numpy as np >>> import scipy.special as sc It is one when `z` is zero. >>> sc.hyp0f1(1, 0) 1.0 It is the limit of the confluent hypergeometric function as `q` goes to infinity. >>> q = np.array([1, 10, 100, 1000]) >>> v = 1 >>> z = 1 >>> sc.hyp1f1(q, v, z / q) array([2.71828183, 2.31481985, 2.28303778, 2.27992985]) >>> sc.hyp0f1(v, z) 2.2795853023360673 It is related to Bessel functions. >>> n = 1 >>> x = np.linspace(0, 1, 5) >>> sc.jv(n, x) array([0. , 0.12402598, 0.24226846, 0.3492436 , 0.44005059]) >>> (0.5 * x)**n / sc.factorial(n) * sc.hyp0f1(n + 1, -0.25 * x**2) array([0. , 0.12402598, 0.24226846, 0.3492436 , 0.44005059])hyp1f1(a, b, x, out=None) Confluent hypergeometric function 1F1. The confluent hypergeometric function is defined by the series .. math:: {}_1F_1(a; b; x) = \sum_{k = 0}^\infty \frac{(a)_k}{(b)_k k!} x^k. See [dlmf]_ for more details. Here :math:`(\cdot)_k` is the Pochhammer symbol; see `poch`. Parameters ---------- a, b : array_like Real parameters x : array_like Real or complex argument out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray Values of the confluent hypergeometric function See Also -------- hyperu : another confluent hypergeometric function hyp0f1 : confluent hypergeometric limit function hyp2f1 : Gaussian hypergeometric function Notes ----- For real values, this function uses the ``hyp1f1`` routine from the C++ Boost library [2]_, for complex values a C translation of the specfun Fortran library [3]_. References ---------- .. [dlmf] NIST Digital Library of Mathematical Functions https://dlmf.nist.gov/13.2#E2 .. [2] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. .. [3] Zhang, Jin, "Computation of Special Functions", John Wiley and Sons, Inc, 1996. Examples -------- >>> import numpy as np >>> import scipy.special as sc It is one when `x` is zero: >>> sc.hyp1f1(0.5, 0.5, 0) 1.0 It is singular when `b` is a nonpositive integer. >>> sc.hyp1f1(0.5, -1, 0) inf It is a polynomial when `a` is a nonpositive integer. >>> a, b, x = -1, 0.5, np.array([1.0, 2.0, 3.0, 4.0]) >>> sc.hyp1f1(a, b, x) array([-1., -3., -5., -7.]) >>> 1 + (a / b) * x array([-1., -3., -5., -7.]) It reduces to the exponential function when ``a = b``. >>> sc.hyp1f1(2, 2, [1, 2, 3, 4]) array([ 2.71828183, 7.3890561 , 20.08553692, 54.59815003]) >>> np.exp([1, 2, 3, 4]) array([ 2.71828183, 7.3890561 , 20.08553692, 54.59815003])hyperu(a, b, x, out=None) Confluent hypergeometric function U It is defined as the solution to the equation .. math:: x \frac{d^2w}{dx^2} + (b - x) \frac{dw}{dx} - aw = 0 which satisfies the property .. math:: U(a, b, x) \sim x^{-a} as :math:`x \to \infty`. See [dlmf]_ for more details. Parameters ---------- a, b : array_like Real-valued parameters x : array_like Real-valued argument out : ndarray, optional Optional output array for the function values Returns ------- scalar or ndarray Values of `U` References ---------- .. [dlmf] NIST Digital Library of Mathematics Functions https://dlmf.nist.gov/13.2#E6 Examples -------- >>> import numpy as np >>> import scipy.special as sc It has a branch cut along the negative `x` axis. >>> x = np.linspace(-0.1, -10, 5) >>> sc.hyperu(1, 1, x) array([nan, nan, nan, nan, nan]) It approaches zero as `x` goes to infinity. >>> x = np.array([1, 10, 100]) >>> sc.hyperu(1, 1, x) array([0.59634736, 0.09156333, 0.00990194]) It satisfies Kummer's transformation. >>> a, b, x = 2, 1, 1 >>> sc.hyperu(a, b, x) 0.1926947246463881 >>> x**(1 - b) * sc.hyperu(a - b + 1, 2 - b, x) 0.1926947246463881inv_boxcox(y, lmbda, out=None) Compute the inverse of the Box-Cox transformation. Find ``x`` such that:: y = (x**lmbda - 1) / lmbda if lmbda != 0 log(x) if lmbda == 0 Parameters ---------- y : array_like Data to be transformed. lmbda : array_like Power parameter of the Box-Cox transform. out : ndarray, optional Optional output array for the function values Returns ------- x : scalar or ndarray Transformed data. Notes ----- .. versionadded:: 0.16.0 Examples -------- >>> from scipy.special import boxcox, inv_boxcox >>> y = boxcox([1, 4, 10], 2.5) >>> inv_boxcox(y, 2.5) array([1., 4., 10.])inv_boxcox1p(y, lmbda, out=None) Compute the inverse of the Box-Cox transformation. Find ``x`` such that:: y = ((1+x)**lmbda - 1) / lmbda if lmbda != 0 log(1+x) if lmbda == 0 Parameters ---------- y : array_like Data to be transformed. lmbda : array_like Power parameter of the Box-Cox transform. out : ndarray, optional Optional output array for the function values Returns ------- x : scalar or ndarray Transformed data. Notes ----- .. versionadded:: 0.16.0 Examples -------- >>> from scipy.special import boxcox1p, inv_boxcox1p >>> y = boxcox1p([1, 4, 10], 2.5) >>> inv_boxcox1p(y, 2.5) array([1., 4., 10.])kl_div(x, y, out=None) Elementwise function for computing Kullback-Leibler divergence. .. math:: \mathrm{kl\_div}(x, y) = \begin{cases} x \log(x / y) - x + y & x > 0, y > 0 \\ y & x = 0, y \ge 0 \\ \infty & \text{otherwise} \end{cases} Parameters ---------- x, y : array_like Real arguments out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray Values of the Kullback-Liebler divergence. See Also -------- entr, rel_entr, scipy.stats.entropy Notes ----- .. versionadded:: 0.15.0 This function is non-negative and is jointly convex in `x` and `y`. The origin of this function is in convex programming; see [1]_ for details. This is why the function contains the extra :math:`-x + y` terms over what might be expected from the Kullback-Leibler divergence. For a version of the function without the extra terms, see `rel_entr`. References ---------- .. [1] Boyd, Stephen and Lieven Vandenberghe. *Convex optimization*. Cambridge University Press, 2004. :doi:`https://doi.org/10.1017/CBO9780511804441`kn(n, x, out=None) Modified Bessel function of the second kind of integer order `n` Returns the modified Bessel function of the second kind for integer order `n` at real `z`. These are also sometimes called functions of the third kind, Basset functions, or Macdonald functions. Parameters ---------- n : array_like of int Order of Bessel functions (floats will truncate with a warning) x : array_like of float Argument at which to evaluate the Bessel functions out : ndarray, optional Optional output array for the function results. Returns ------- scalar or ndarray Value of the Modified Bessel function of the second kind, :math:`K_n(x)`. See Also -------- kv : Same function, but accepts real order and complex argument kvp : Derivative of this function Notes ----- Wrapper for AMOS [1]_ routine `zbesk`. For a discussion of the algorithm used, see [2]_ and the references therein. References ---------- .. [1] Donald E. Amos, "AMOS, A Portable Package for Bessel Functions of a Complex Argument and Nonnegative Order", http://netlib.org/amos/ .. [2] Donald E. Amos, "Algorithm 644: A portable package for Bessel functions of a complex argument and nonnegative order", ACM TOMS Vol. 12 Issue 3, Sept. 1986, p. 265 Examples -------- Plot the function of several orders for real input: >>> import numpy as np >>> from scipy.special import kn >>> import matplotlib.pyplot as plt >>> x = np.linspace(0, 5, 1000) >>> for N in range(6): ... plt.plot(x, kn(N, x), label='$K_{}(x)$'.format(N)) >>> plt.ylim(0, 10) >>> plt.legend() >>> plt.title(r'Modified Bessel function of the second kind $K_n(x)$') >>> plt.show() Calculate for a single value at multiple orders: >>> kn([4, 5, 6], 1) array([ 44.23241585, 360.9605896 , 3653.83831186])kolmogi(p, out=None) Inverse Survival Function of Kolmogorov distribution It is the inverse function to `kolmogorov`. Returns y such that ``kolmogorov(y) == p``. Parameters ---------- p : float array_like Probability out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray The value(s) of kolmogi(p) See Also -------- kolmogorov : The Survival Function for the distribution scipy.stats.kstwobign : Provides the functionality as a continuous distribution smirnov, smirnovi : Functions for the one-sided distribution Notes ----- `kolmogorov` is used by `stats.kstest` in the application of the Kolmogorov-Smirnov Goodness of Fit test. For historical reasons this function is exposed in `scpy.special`, but the recommended way to achieve the most accurate CDF/SF/PDF/PPF/ISF computations is to use the `stats.kstwobign` distribution. Examples -------- >>> from scipy.special import kolmogi >>> kolmogi([0, 0.1, 0.25, 0.5, 0.75, 0.9, 1.0]) array([ inf, 1.22384787, 1.01918472, 0.82757356, 0.67644769, 0.57117327, 0. ])kolmogorov(y, out=None) Complementary cumulative distribution (Survival Function) function of Kolmogorov distribution. Returns the complementary cumulative distribution function of Kolmogorov's limiting distribution (``D_n*\sqrt(n)`` as n goes to infinity) of a two-sided test for equality between an empirical and a theoretical distribution. It is equal to the (limit as n->infinity of the) probability that ``sqrt(n) * max absolute deviation > y``. Parameters ---------- y : float array_like Absolute deviation between the Empirical CDF (ECDF) and the target CDF, multiplied by sqrt(n). out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray The value(s) of kolmogorov(y) See Also -------- kolmogi : The Inverse Survival Function for the distribution scipy.stats.kstwobign : Provides the functionality as a continuous distribution smirnov, smirnovi : Functions for the one-sided distribution Notes ----- `kolmogorov` is used by `stats.kstest` in the application of the Kolmogorov-Smirnov Goodness of Fit test. For historical reasons this function is exposed in `scpy.special`, but the recommended way to achieve the most accurate CDF/SF/PDF/PPF/ISF computations is to use the `stats.kstwobign` distribution. Examples -------- Show the probability of a gap at least as big as 0, 0.5 and 1.0. >>> import numpy as np >>> from scipy.special import kolmogorov >>> from scipy.stats import kstwobign >>> kolmogorov([0, 0.5, 1.0]) array([ 1. , 0.96394524, 0.26999967]) Compare a sample of size 1000 drawn from a Laplace(0, 1) distribution against the target distribution, a Normal(0, 1) distribution. >>> from scipy.stats import norm, laplace >>> rng = np.random.default_rng() >>> n = 1000 >>> lap01 = laplace(0, 1) >>> x = np.sort(lap01.rvs(n, random_state=rng)) >>> np.mean(x), np.std(x) (-0.05841730131499543, 1.3968109101997568) Construct the Empirical CDF and the K-S statistic Dn. >>> target = norm(0,1) # Normal mean 0, stddev 1 >>> cdfs = target.cdf(x) >>> ecdfs = np.arange(n+1, dtype=float)/n >>> gaps = np.column_stack([cdfs - ecdfs[:n], ecdfs[1:] - cdfs]) >>> Dn = np.max(gaps) >>> Kn = np.sqrt(n) * Dn >>> print('Dn=%f, sqrt(n)*Dn=%f' % (Dn, Kn)) Dn=0.043363, sqrt(n)*Dn=1.371265 >>> print(chr(10).join(['For a sample of size n drawn from a N(0, 1) distribution:', ... ' the approximate Kolmogorov probability that sqrt(n)*Dn>=%f is %f' % ... (Kn, kolmogorov(Kn)), ... ' the approximate Kolmogorov probability that sqrt(n)*Dn<=%f is %f' % ... (Kn, kstwobign.cdf(Kn))])) For a sample of size n drawn from a N(0, 1) distribution: the approximate Kolmogorov probability that sqrt(n)*Dn>=1.371265 is 0.046533 the approximate Kolmogorov probability that sqrt(n)*Dn<=1.371265 is 0.953467 Plot the Empirical CDF against the target N(0, 1) CDF. >>> import matplotlib.pyplot as plt >>> plt.step(np.concatenate([[-3], x]), ecdfs, where='post', label='Empirical CDF') >>> x3 = np.linspace(-3, 3, 100) >>> plt.plot(x3, target.cdf(x3), label='CDF for N(0, 1)') >>> plt.ylim([0, 1]); plt.grid(True); plt.legend(); >>> # Add vertical lines marking Dn+ and Dn- >>> iminus, iplus = np.argmax(gaps, axis=0) >>> plt.vlines([x[iminus]], ecdfs[iminus], cdfs[iminus], ... color='r', linestyle='dashed', lw=4) >>> plt.vlines([x[iplus]], cdfs[iplus], ecdfs[iplus+1], ... color='r', linestyle='dashed', lw=4) >>> plt.show()lpmv(m, v, x, out=None) Associated Legendre function of integer order and real degree. Defined as .. math:: P_v^m = (-1)^m (1 - x^2)^{m/2} \frac{d^m}{dx^m} P_v(x) where .. math:: P_v = \sum_{k = 0}^\infty \frac{(-v)_k (v + 1)_k}{(k!)^2} \left(\frac{1 - x}{2}\right)^k is the Legendre function of the first kind. Here :math:`(\cdot)_k` is the Pochhammer symbol; see `poch`. Parameters ---------- m : array_like Order (int or float). If passed a float not equal to an integer the function returns NaN. v : array_like Degree (float). x : array_like Argument (float). Must have ``|x| <= 1``. out : ndarray, optional Optional output array for the function results Returns ------- pmv : scalar or ndarray Value of the associated Legendre function. See Also -------- lpmn : Compute the associated Legendre function for all orders ``0, ..., m`` and degrees ``0, ..., n``. clpmn : Compute the associated Legendre function at complex arguments. Notes ----- Note that this implementation includes the Condon-Shortley phase. References ---------- .. [1] Zhang, Jin, "Computation of Special Functions", John Wiley and Sons, Inc, 1996.nbdtr(k, n, p, out=None) Negative binomial cumulative distribution function. Returns the sum of the terms 0 through `k` of the negative binomial distribution probability mass function, .. math:: F = \sum_{j=0}^k {{n + j - 1}\choose{j}} p^n (1 - p)^j. In a sequence of Bernoulli trials with individual success probabilities `p`, this is the probability that `k` or fewer failures precede the nth success. Parameters ---------- k : array_like The maximum number of allowed failures (nonnegative int). n : array_like The target number of successes (positive int). p : array_like Probability of success in a single event (float). out : ndarray, optional Optional output array for the function results Returns ------- F : scalar or ndarray The probability of `k` or fewer failures before `n` successes in a sequence of events with individual success probability `p`. See Also -------- nbdtrc : Negative binomial survival function nbdtrik : Negative binomial quantile function scipy.stats.nbinom : Negative binomial distribution Notes ----- If floating point values are passed for `k` or `n`, they will be truncated to integers. The terms are not summed directly; instead the regularized incomplete beta function is employed, according to the formula, .. math:: \mathrm{nbdtr}(k, n, p) = I_{p}(n, k + 1). Wrapper for the Cephes [1]_ routine `nbdtr`. The negative binomial distribution is also available as `scipy.stats.nbinom`. Using `nbdtr` directly can improve performance compared to the ``cdf`` method of `scipy.stats.nbinom` (see last example). References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ Examples -------- Compute the function for ``k=10`` and ``n=5`` at ``p=0.5``. >>> import numpy as np >>> from scipy.special import nbdtr >>> nbdtr(10, 5, 0.5) 0.940765380859375 Compute the function for ``n=10`` and ``p=0.5`` at several points by providing a NumPy array or list for `k`. >>> nbdtr([5, 10, 15], 10, 0.5) array([0.15087891, 0.58809853, 0.88523853]) Plot the function for four different parameter sets. >>> import matplotlib.pyplot as plt >>> k = np.arange(130) >>> n_parameters = [20, 20, 20, 80] >>> p_parameters = [0.2, 0.5, 0.8, 0.5] >>> linestyles = ['solid', 'dashed', 'dotted', 'dashdot'] >>> parameters_list = list(zip(p_parameters, n_parameters, ... linestyles)) >>> fig, ax = plt.subplots(figsize=(8, 8)) >>> for parameter_set in parameters_list: ... p, n, style = parameter_set ... nbdtr_vals = nbdtr(k, n, p) ... ax.plot(k, nbdtr_vals, label=rf"$n={n},\, p={p}$", ... ls=style) >>> ax.legend() >>> ax.set_xlabel("$k$") >>> ax.set_title("Negative binomial cumulative distribution function") >>> plt.show() The negative binomial distribution is also available as `scipy.stats.nbinom`. Using `nbdtr` directly can be much faster than calling the ``cdf`` method of `scipy.stats.nbinom`, especially for small arrays or individual values. To get the same results one must use the following parametrization: ``nbinom(n, p).cdf(k)=nbdtr(k, n, p)``. >>> from scipy.stats import nbinom >>> k, n, p = 5, 3, 0.5 >>> nbdtr_res = nbdtr(k, n, p) # this will often be faster than below >>> stats_res = nbinom(n, p).cdf(k) >>> stats_res, nbdtr_res # test that results are equal (0.85546875, 0.85546875) `nbdtr` can evaluate different parameter sets by providing arrays with shapes compatible for broadcasting for `k`, `n` and `p`. Here we compute the function for three different `k` at four locations `p`, resulting in a 3x4 array. >>> k = np.array([[5], [10], [15]]) >>> p = np.array([0.3, 0.5, 0.7, 0.9]) >>> k.shape, p.shape ((3, 1), (4,)) >>> nbdtr(k, 5, p) array([[0.15026833, 0.62304687, 0.95265101, 0.9998531 ], [0.48450894, 0.94076538, 0.99932777, 0.99999999], [0.76249222, 0.99409103, 0.99999445, 1. ]])nbdtrc(k, n, p, out=None) Negative binomial survival function. Returns the sum of the terms `k + 1` to infinity of the negative binomial distribution probability mass function, .. math:: F = \sum_{j=k + 1}^\infty {{n + j - 1}\choose{j}} p^n (1 - p)^j. In a sequence of Bernoulli trials with individual success probabilities `p`, this is the probability that more than `k` failures precede the nth success. Parameters ---------- k : array_like The maximum number of allowed failures (nonnegative int). n : array_like The target number of successes (positive int). p : array_like Probability of success in a single event (float). out : ndarray, optional Optional output array for the function results Returns ------- F : scalar or ndarray The probability of `k + 1` or more failures before `n` successes in a sequence of events with individual success probability `p`. See Also -------- nbdtr : Negative binomial cumulative distribution function nbdtrik : Negative binomial percentile function scipy.stats.nbinom : Negative binomial distribution Notes ----- If floating point values are passed for `k` or `n`, they will be truncated to integers. The terms are not summed directly; instead the regularized incomplete beta function is employed, according to the formula, .. math:: \mathrm{nbdtrc}(k, n, p) = I_{1 - p}(k + 1, n). Wrapper for the Cephes [1]_ routine `nbdtrc`. The negative binomial distribution is also available as `scipy.stats.nbinom`. Using `nbdtrc` directly can improve performance compared to the ``sf`` method of `scipy.stats.nbinom` (see last example). References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ Examples -------- Compute the function for ``k=10`` and ``n=5`` at ``p=0.5``. >>> import numpy as np >>> from scipy.special import nbdtrc >>> nbdtrc(10, 5, 0.5) 0.059234619140624986 Compute the function for ``n=10`` and ``p=0.5`` at several points by providing a NumPy array or list for `k`. >>> nbdtrc([5, 10, 15], 10, 0.5) array([0.84912109, 0.41190147, 0.11476147]) Plot the function for four different parameter sets. >>> import matplotlib.pyplot as plt >>> k = np.arange(130) >>> n_parameters = [20, 20, 20, 80] >>> p_parameters = [0.2, 0.5, 0.8, 0.5] >>> linestyles = ['solid', 'dashed', 'dotted', 'dashdot'] >>> parameters_list = list(zip(p_parameters, n_parameters, ... linestyles)) >>> fig, ax = plt.subplots(figsize=(8, 8)) >>> for parameter_set in parameters_list: ... p, n, style = parameter_set ... nbdtrc_vals = nbdtrc(k, n, p) ... ax.plot(k, nbdtrc_vals, label=rf"$n={n},\, p={p}$", ... ls=style) >>> ax.legend() >>> ax.set_xlabel("$k$") >>> ax.set_title("Negative binomial distribution survival function") >>> plt.show() The negative binomial distribution is also available as `scipy.stats.nbinom`. Using `nbdtrc` directly can be much faster than calling the ``sf`` method of `scipy.stats.nbinom`, especially for small arrays or individual values. To get the same results one must use the following parametrization: ``nbinom(n, p).sf(k)=nbdtrc(k, n, p)``. >>> from scipy.stats import nbinom >>> k, n, p = 3, 5, 0.5 >>> nbdtr_res = nbdtrc(k, n, p) # this will often be faster than below >>> stats_res = nbinom(n, p).sf(k) >>> stats_res, nbdtr_res # test that results are equal (0.6367187499999999, 0.6367187499999999) `nbdtrc` can evaluate different parameter sets by providing arrays with shapes compatible for broadcasting for `k`, `n` and `p`. Here we compute the function for three different `k` at four locations `p`, resulting in a 3x4 array. >>> k = np.array([[5], [10], [15]]) >>> p = np.array([0.3, 0.5, 0.7, 0.9]) >>> k.shape, p.shape ((3, 1), (4,)) >>> nbdtrc(k, 5, p) array([[8.49731667e-01, 3.76953125e-01, 4.73489874e-02, 1.46902600e-04], [5.15491059e-01, 5.92346191e-02, 6.72234070e-04, 9.29610100e-09], [2.37507779e-01, 5.90896606e-03, 5.55025308e-06, 3.26346760e-13]])nbdtri(k, n, y, out=None) Returns the inverse with respect to the parameter `p` of ``y = nbdtr(k, n, p)``, the negative binomial cumulative distribution function. Parameters ---------- k : array_like The maximum number of allowed failures (nonnegative int). n : array_like The target number of successes (positive int). y : array_like The probability of `k` or fewer failures before `n` successes (float). out : ndarray, optional Optional output array for the function results Returns ------- p : scalar or ndarray Probability of success in a single event (float) such that `nbdtr(k, n, p) = y`. See Also -------- nbdtr : Cumulative distribution function of the negative binomial. nbdtrc : Negative binomial survival function. scipy.stats.nbinom : negative binomial distribution. nbdtrik : Inverse with respect to `k` of `nbdtr(k, n, p)`. nbdtrin : Inverse with respect to `n` of `nbdtr(k, n, p)`. scipy.stats.nbinom : Negative binomial distribution Notes ----- Wrapper for the Cephes [1]_ routine `nbdtri`. The negative binomial distribution is also available as `scipy.stats.nbinom`. Using `nbdtri` directly can improve performance compared to the ``ppf`` method of `scipy.stats.nbinom`. References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ Examples -------- `nbdtri` is the inverse of `nbdtr` with respect to `p`. Up to floating point errors the following holds: ``nbdtri(k, n, nbdtr(k, n, p))=p``. >>> import numpy as np >>> from scipy.special import nbdtri, nbdtr >>> k, n, y = 5, 10, 0.2 >>> cdf_val = nbdtr(k, n, y) >>> nbdtri(k, n, cdf_val) 0.20000000000000004 Compute the function for ``k=10`` and ``n=5`` at several points by providing a NumPy array or list for `y`. >>> y = np.array([0.1, 0.4, 0.8]) >>> nbdtri(3, 5, y) array([0.34462319, 0.51653095, 0.69677416]) Plot the function for three different parameter sets. >>> import matplotlib.pyplot as plt >>> n_parameters = [5, 20, 30, 30] >>> k_parameters = [20, 20, 60, 80] >>> linestyles = ['solid', 'dashed', 'dotted', 'dashdot'] >>> parameters_list = list(zip(n_parameters, k_parameters, linestyles)) >>> cdf_vals = np.linspace(0, 1, 1000) >>> fig, ax = plt.subplots(figsize=(8, 8)) >>> for parameter_set in parameters_list: ... n, k, style = parameter_set ... nbdtri_vals = nbdtri(k, n, cdf_vals) ... ax.plot(cdf_vals, nbdtri_vals, label=rf"$k={k},\ n={n}$", ... ls=style) >>> ax.legend() >>> ax.set_ylabel("$p$") >>> ax.set_xlabel("$CDF$") >>> title = "nbdtri: inverse of negative binomial CDF with respect to $p$" >>> ax.set_title(title) >>> plt.show() `nbdtri` can evaluate different parameter sets by providing arrays with shapes compatible for broadcasting for `k`, `n` and `p`. Here we compute the function for three different `k` at four locations `p`, resulting in a 3x4 array. >>> k = np.array([[5], [10], [15]]) >>> y = np.array([0.3, 0.5, 0.7, 0.9]) >>> k.shape, y.shape ((3, 1), (4,)) >>> nbdtri(k, 5, y) array([[0.37258157, 0.45169416, 0.53249956, 0.64578407], [0.24588501, 0.30451981, 0.36778453, 0.46397088], [0.18362101, 0.22966758, 0.28054743, 0.36066188]])nbdtrik(y, n, p, out=None) Negative binomial percentile function. Returns the inverse with respect to the parameter `k` of ``y = nbdtr(k, n, p)``, the negative binomial cumulative distribution function. Parameters ---------- y : array_like The probability of `k` or fewer failures before `n` successes (float). n : array_like The target number of successes (positive int). p : array_like Probability of success in a single event (float). out : ndarray, optional Optional output array for the function results Returns ------- k : scalar or ndarray The maximum number of allowed failures such that `nbdtr(k, n, p) = y`. See Also -------- nbdtr : Cumulative distribution function of the negative binomial. nbdtrc : Survival function of the negative binomial. nbdtri : Inverse with respect to `p` of `nbdtr(k, n, p)`. nbdtrin : Inverse with respect to `n` of `nbdtr(k, n, p)`. scipy.stats.nbinom : Negative binomial distribution Notes ----- Wrapper for the CDFLIB [1]_ Fortran routine `cdfnbn`. Formula 26.5.26 of [2]_, .. math:: \sum_{j=k + 1}^\infty {{n + j - 1} \choose{j}} p^n (1 - p)^j = I_{1 - p}(k + 1, n), is used to reduce calculation of the cumulative distribution function to that of a regularized incomplete beta :math:`I`. Computation of `k` involves a search for a value that produces the desired value of `y`. The search relies on the monotonicity of `y` with `k`. References ---------- .. [1] Barry Brown, James Lovato, and Kathy Russell, CDFLIB: Library of Fortran Routines for Cumulative Distribution Functions, Inverses, and Other Parameters. .. [2] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. Examples -------- Compute the negative binomial cumulative distribution function for an exemplary parameter set. >>> import numpy as np >>> from scipy.special import nbdtr, nbdtrik >>> k, n, p = 5, 2, 0.5 >>> cdf_value = nbdtr(k, n, p) >>> cdf_value 0.9375 Verify that `nbdtrik` recovers the original value for `k`. >>> nbdtrik(cdf_value, n, p) 5.0 Plot the function for different parameter sets. >>> import matplotlib.pyplot as plt >>> p_parameters = [0.2, 0.5, 0.7, 0.5] >>> n_parameters = [30, 30, 30, 80] >>> linestyles = ['solid', 'dashed', 'dotted', 'dashdot'] >>> parameters_list = list(zip(p_parameters, n_parameters, linestyles)) >>> cdf_vals = np.linspace(0, 1, 1000) >>> fig, ax = plt.subplots(figsize=(8, 8)) >>> for parameter_set in parameters_list: ... p, n, style = parameter_set ... nbdtrik_vals = nbdtrik(cdf_vals, n, p) ... ax.plot(cdf_vals, nbdtrik_vals, label=rf"$n={n},\ p={p}$", ... ls=style) >>> ax.legend() >>> ax.set_ylabel("$k$") >>> ax.set_xlabel("$CDF$") >>> ax.set_title("Negative binomial percentile function") >>> plt.show() The negative binomial distribution is also available as `scipy.stats.nbinom`. The percentile function method ``ppf`` returns the result of `nbdtrik` rounded up to integers: >>> from scipy.stats import nbinom >>> q, n, p = 0.6, 5, 0.5 >>> nbinom.ppf(q, n, p), nbdtrik(q, n, p) (5.0, 4.800428460273882)nbdtrin(k, y, p, out=None) Inverse of `nbdtr` vs `n`. Returns the inverse with respect to the parameter `n` of ``y = nbdtr(k, n, p)``, the negative binomial cumulative distribution function. Parameters ---------- k : array_like The maximum number of allowed failures (nonnegative int). y : array_like The probability of `k` or fewer failures before `n` successes (float). p : array_like Probability of success in a single event (float). out : ndarray, optional Optional output array for the function results Returns ------- n : scalar or ndarray The number of successes `n` such that `nbdtr(k, n, p) = y`. See Also -------- nbdtr : Cumulative distribution function of the negative binomial. nbdtri : Inverse with respect to `p` of `nbdtr(k, n, p)`. nbdtrik : Inverse with respect to `k` of `nbdtr(k, n, p)`. Notes ----- Wrapper for the CDFLIB [1]_ Fortran routine `cdfnbn`. Formula 26.5.26 of [2]_, .. math:: \sum_{j=k + 1}^\infty {{n + j - 1} \choose{j}} p^n (1 - p)^j = I_{1 - p}(k + 1, n), is used to reduce calculation of the cumulative distribution function to that of a regularized incomplete beta :math:`I`. Computation of `n` involves a search for a value that produces the desired value of `y`. The search relies on the monotonicity of `y` with `n`. References ---------- .. [1] Barry Brown, James Lovato, and Kathy Russell, CDFLIB: Library of Fortran Routines for Cumulative Distribution Functions, Inverses, and Other Parameters. .. [2] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. Examples -------- Compute the negative binomial cumulative distribution function for an exemplary parameter set. >>> from scipy.special import nbdtr, nbdtrin >>> k, n, p = 5, 2, 0.5 >>> cdf_value = nbdtr(k, n, p) >>> cdf_value 0.9375 Verify that `nbdtrin` recovers the original value for `n` up to floating point accuracy. >>> nbdtrin(k, cdf_value, p) 1.999999999998137ncfdtr(dfn, dfd, nc, f, out=None) Cumulative distribution function of the non-central F distribution. The non-central F describes the distribution of, .. math:: Z = \frac{X/d_n}{Y/d_d} where :math:`X` and :math:`Y` are independently distributed, with :math:`X` distributed non-central :math:`\chi^2` with noncentrality parameter `nc` and :math:`d_n` degrees of freedom, and :math:`Y` distributed :math:`\chi^2` with :math:`d_d` degrees of freedom. Parameters ---------- dfn : array_like Degrees of freedom of the numerator sum of squares. Range (0, inf). dfd : array_like Degrees of freedom of the denominator sum of squares. Range (0, inf). nc : array_like Noncentrality parameter. Range [0, inf). f : array_like Quantiles, i.e. the upper limit of integration. out : ndarray, optional Optional output array for the function results Returns ------- cdf : scalar or ndarray The calculated CDF. If all inputs are scalar, the return will be a float. Otherwise it will be an array. See Also -------- ncfdtri : Quantile function; inverse of `ncfdtr` with respect to `f`. ncfdtridfd : Inverse of `ncfdtr` with respect to `dfd`. ncfdtridfn : Inverse of `ncfdtr` with respect to `dfn`. ncfdtrinc : Inverse of `ncfdtr` with respect to `nc`. scipy.stats.ncf : Non-central F distribution. Notes ----- This function calculates the CDF of the non-central f distribution using the Boost Math C++ library [1]_. The cumulative distribution function is computed using Formula 26.6.20 of [2]_: .. math:: F(d_n, d_d, n_c, f) = \sum_{j=0}^\infty e^{-n_c/2} \frac{(n_c/2)^j}{j!} I_{x}(\frac{d_n}{2} + j, \frac{d_d}{2}), where :math:`I` is the regularized incomplete beta function, and :math:`x = f d_n/(f d_n + d_d)`. Note that argument order of `ncfdtr` is different from that of the similar ``cdf`` method of `scipy.stats.ncf`: `f` is the last parameter of `ncfdtr` but the first parameter of ``scipy.stats.ncf.cdf``. References ---------- .. [1] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. .. [2] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. Examples -------- >>> import numpy as np >>> from scipy import special >>> from scipy import stats >>> import matplotlib.pyplot as plt Plot the CDF of the non-central F distribution, for nc=0. Compare with the F-distribution from scipy.stats: >>> x = np.linspace(-1, 8, num=500) >>> dfn = 3 >>> dfd = 2 >>> ncf_stats = stats.f.cdf(x, dfn, dfd) >>> ncf_special = special.ncfdtr(dfn, dfd, 0, x) >>> fig = plt.figure() >>> ax = fig.add_subplot(111) >>> ax.plot(x, ncf_stats, 'b-', lw=3) >>> ax.plot(x, ncf_special, 'r-') >>> plt.show()ncfdtri(dfn, dfd, nc, p, out=None) Inverse with respect to `f` of the CDF of the non-central F distribution. See `ncfdtr` for more details. Parameters ---------- dfn : array_like Degrees of freedom of the numerator sum of squares. Range (0, inf). dfd : array_like Degrees of freedom of the denominator sum of squares. Range (0, inf). nc : array_like Noncentrality parameter. Range [0, inf). p : array_like Value of the cumulative distribution function. Must be in the range [0, 1]. out : ndarray, optional Optional output array for the function results Returns ------- f : scalar or ndarray Quantiles, i.e., the upper limit of integration. See Also -------- ncfdtr : CDF of the non-central F distribution. ncfdtridfd : Inverse of `ncfdtr` with respect to `dfd`. ncfdtridfn : Inverse of `ncfdtr` with respect to `dfn`. ncfdtrinc : Inverse of `ncfdtr` with respect to `nc`. scipy.stats.ncf : Non-central F distribution. Notes ----- This function calculates the Quantile of the non-central f distribution using the Boost Math C++ library [1]_. Note that argument order of `ncfdtri` is different from that of the similar ``ppf`` method of `scipy.stats.ncf`. `p` is the last parameter of `ncfdtri` but the first parameter of ``scipy.stats.ncf.ppf``. References ---------- .. [1] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. Examples -------- >>> from scipy.special import ncfdtr, ncfdtri Compute the CDF for several values of `f`: >>> f = [0.5, 1, 1.5] >>> p = ncfdtr(2, 3, 1.5, f) >>> p array([ 0.20782291, 0.36107392, 0.47345752]) Compute the inverse. We recover the values of `f`, as expected: >>> ncfdtri(2, 3, 1.5, p) array([ 0.5, 1. , 1.5])ncfdtridfd(dfn, p, nc, f, out=None) Calculate degrees of freedom (denominator) for the noncentral F-distribution. This is the inverse with respect to `dfd` of `ncfdtr`. See `ncfdtr` for more details. Parameters ---------- dfn : array_like Degrees of freedom of the numerator sum of squares. Range (0, inf). p : array_like Value of the cumulative distribution function. Must be in the range [0, 1]. nc : array_like Noncentrality parameter. Should be in range (0, 1e4). f : array_like Quantiles, i.e., the upper limit of integration. out : ndarray, optional Optional output array for the function results Returns ------- dfd : scalar or ndarray Degrees of freedom of the denominator sum of squares. See Also -------- ncfdtr : CDF of the non-central F distribution. ncfdtri : Quantile function; inverse of `ncfdtr` with respect to `f`. ncfdtridfn : Inverse of `ncfdtr` with respect to `dfn`. ncfdtrinc : Inverse of `ncfdtr` with respect to `nc`. Notes ----- The value of the cumulative noncentral F distribution is not necessarily monotone in either degrees of freedom. There thus may be two values that provide a given CDF value. This routine assumes monotonicity and will find an arbitrary one of the two values. Examples -------- >>> from scipy.special import ncfdtr, ncfdtridfd Compute the CDF for several values of `dfd`: >>> dfd = [1, 2, 3] >>> p = ncfdtr(2, dfd, 0.25, 15) >>> p array([ 0.8097138 , 0.93020416, 0.96787852]) Compute the inverse. We recover the values of `dfd`, as expected: >>> ncfdtridfd(2, p, 0.25, 15) array([ 1., 2., 3.])ncfdtridfn(p, dfd, nc, f, out=None) Calculate degrees of freedom (numerator) for the noncentral F-distribution. This is the inverse with respect to `dfn` of `ncfdtr`. See `ncfdtr` for more details. Parameters ---------- p : array_like Value of the cumulative distribution function. Must be in the range [0, 1]. dfd : array_like Degrees of freedom of the denominator sum of squares. Range (0, inf). nc : array_like Noncentrality parameter. Should be in range (0, 1e4). f : float Quantiles, i.e., the upper limit of integration. out : ndarray, optional Optional output array for the function results Returns ------- dfn : scalar or ndarray Degrees of freedom of the numerator sum of squares. See Also -------- ncfdtr : CDF of the non-central F distribution. ncfdtri : Quantile function; inverse of `ncfdtr` with respect to `f`. ncfdtridfd : Inverse of `ncfdtr` with respect to `dfd`. ncfdtrinc : Inverse of `ncfdtr` with respect to `nc`. Notes ----- The value of the cumulative noncentral F distribution is not necessarily monotone in either degrees of freedom. There thus may be two values that provide a given CDF value. This routine assumes monotonicity and will find an arbitrary one of the two values. Examples -------- >>> from scipy.special import ncfdtr, ncfdtridfn Compute the CDF for several values of `dfn`: >>> dfn = [1, 2, 3] >>> p = ncfdtr(dfn, 2, 0.25, 15) >>> p array([ 0.92562363, 0.93020416, 0.93188394]) Compute the inverse. We recover the values of `dfn`, as expected: >>> ncfdtridfn(p, 2, 0.25, 15) array([ 1., 2., 3.])ncfdtrinc(dfn, dfd, p, f, out=None) Calculate non-centrality parameter for non-central F distribution. This is the inverse with respect to `nc` of `ncfdtr`. See `ncfdtr` for more details. Parameters ---------- dfn : array_like Degrees of freedom of the numerator sum of squares. Range (0, inf). dfd : array_like Degrees of freedom of the denominator sum of squares. Range (0, inf). p : array_like Value of the cumulative distribution function. Must be in the range [0, 1]. f : array_like Quantiles, i.e., the upper limit of integration. out : ndarray, optional Optional output array for the function results Returns ------- nc : scalar or ndarray Noncentrality parameter. See Also -------- ncfdtr : CDF of the non-central F distribution. ncfdtri : Quantile function; inverse of `ncfdtr` with respect to `f`. ncfdtridfd : Inverse of `ncfdtr` with respect to `dfd`. ncfdtridfn : Inverse of `ncfdtr` with respect to `dfn`. Examples -------- >>> from scipy.special import ncfdtr, ncfdtrinc Compute the CDF for several values of `nc`: >>> nc = [0.5, 1.5, 2.0] >>> p = ncfdtr(2, 3, nc, 15) >>> p array([ 0.96309246, 0.94327955, 0.93304098]) Compute the inverse. We recover the values of `nc`, as expected: >>> ncfdtrinc(2, 3, p, 15) array([ 0.5, 1.5, 2. ])nctdtr(df, nc, t, out=None) Cumulative distribution function of the non-central `t` distribution. Parameters ---------- df : array_like Degrees of freedom of the distribution. Should be in range (0, inf). nc : array_like Noncentrality parameter. t : array_like Quantiles, i.e., the upper limit of integration. out : ndarray, optional Optional output array for the function results Returns ------- cdf : scalar or ndarray The calculated CDF. If all inputs are scalar, the return will be a float. Otherwise, it will be an array. See Also -------- nctdtrit : Inverse CDF (iCDF) of the non-central t distribution. nctdtridf : Calculate degrees of freedom, given CDF and iCDF values. nctdtrinc : Calculate non-centrality parameter, given CDF iCDF values. Notes ----- This function calculates the CDF of the non-central t distribution using the Boost Math C++ library [1]_. Note that the argument order of `nctdtr` is different from that of the similar ``cdf`` method of `scipy.stats.nct`: `t` is the last parameter of `nctdtr` but the first parameter of ``scipy.stats.nct.cdf``. References ---------- .. [1] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. Examples -------- >>> import numpy as np >>> from scipy import special >>> from scipy import stats >>> import matplotlib.pyplot as plt Plot the CDF of the non-central t distribution, for nc=0. Compare with the t-distribution from scipy.stats: >>> x = np.linspace(-5, 5, num=500) >>> df = 3 >>> nct_stats = stats.t.cdf(x, df) >>> nct_special = special.nctdtr(df, 0, x) >>> fig = plt.figure() >>> ax = fig.add_subplot(111) >>> ax.plot(x, nct_stats, 'b-', lw=3) >>> ax.plot(x, nct_special, 'r-') >>> plt.show()nctdtridf(p, nc, t, out=None) Calculate degrees of freedom for non-central t distribution. See `nctdtr` for more details. Parameters ---------- p : array_like CDF values, in range (0, 1]. nc : array_like Noncentrality parameter. Should be in range (-1e6, 1e6). t : array_like Quantiles, i.e., the upper limit of integration. out : ndarray, optional Optional output array for the function results Returns ------- df : scalar or ndarray The degrees of freedom. If all inputs are scalar, the return will be a float. Otherwise, it will be an array. See Also -------- nctdtr : CDF of the non-central `t` distribution. nctdtrit : Inverse CDF (iCDF) of the non-central t distribution. nctdtrinc : Calculate non-centrality parameter, given CDF iCDF values. Examples -------- >>> from scipy.special import nctdtr, nctdtridf Compute the CDF for several values of `df`: >>> df = [1, 2, 3] >>> p = nctdtr(df, 0.25, 1) >>> p array([0.67491974, 0.716464 , 0.73349456]) Compute the inverse. We recover the values of `df`, as expected: >>> nctdtridf(p, 0.25, 1) array([1., 2., 3.])nctdtrinc(df, p, t, out=None) Calculate non-centrality parameter for non-central t distribution. See `nctdtr` for more details. Parameters ---------- df : array_like Degrees of freedom of the distribution. Should be in range (0, inf). p : array_like CDF values, in range (0, 1]. t : array_like Quantiles, i.e., the upper limit of integration. out : ndarray, optional Optional output array for the function results Returns ------- nc : scalar or ndarray Noncentrality parameter See Also -------- nctdtr : CDF of the non-central `t` distribution. nctdtrit : Inverse CDF (iCDF) of the non-central t distribution. nctdtridf : Calculate degrees of freedom, given CDF and iCDF values. Examples -------- >>> from scipy.special import nctdtr, nctdtrinc Compute the CDF for several values of `nc`: >>> nc = [0.5, 1.5, 2.5] >>> p = nctdtr(3, nc, 1.5) >>> p array([0.77569497, 0.45524533, 0.1668691 ]) Compute the inverse. We recover the values of `nc`, as expected: >>> nctdtrinc(3, p, 1.5) array([0.5, 1.5, 2.5])nctdtrit(df, nc, p, out=None) Inverse cumulative distribution function of the non-central t distribution. See `nctdtr` for more details. Parameters ---------- df : array_like Degrees of freedom of the distribution. Should be in range (0, inf). nc : array_like Noncentrality parameter. p : array_like CDF values, in range (0, 1]. out : ndarray, optional Optional output array for the function results Returns ------- t : scalar or ndarray Quantiles See Also -------- nctdtr : CDF of the non-central `t` distribution. nctdtridf : Calculate degrees of freedom, given CDF and iCDF values. nctdtrinc : Calculate non-centrality parameter, given CDF iCDF values. Notes ----- This function calculates the quantile of the non-central t distribution using the Boost Math C++ library [1]_. Note that the argument order of `nctdtrit` is different from that of the similar ``ppf`` method of `scipy.stats.nct`: `t` is the last parameter of `nctdtrit` but the first parameter of ``scipy.stats.nct.ppf``. References ---------- .. [1] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. Examples -------- >>> from scipy.special import nctdtr, nctdtrit Compute the CDF for several values of `t`: >>> t = [0.5, 1, 1.5] >>> p = nctdtr(3, 1, t) >>> p array([0.29811049, 0.46922687, 0.6257559 ]) Compute the inverse. We recover the values of `t`, as expected: >>> nctdtrit(3, 1, p) array([0.5, 1. , 1.5])ndtri(y, out=None) Inverse of `ndtr` vs x Returns the argument x for which the area under the standard normal probability density function (integrated from minus infinity to `x`) is equal to y. Parameters ---------- p : array_like Probability out : ndarray, optional Optional output array for the function results Returns ------- x : scalar or ndarray Value of x such that ``ndtr(x) == p``. See Also -------- ndtr : Standard normal cumulative probability distribution ndtri_exp : Inverse of log_ndtr Examples -------- `ndtri` is the percentile function of the standard normal distribution. This means it returns the inverse of the cumulative density `ndtr`. First, let us compute a cumulative density value. >>> import numpy as np >>> from scipy.special import ndtri, ndtr >>> cdf_val = ndtr(2) >>> cdf_val 0.9772498680518208 Verify that `ndtri` yields the original value for `x` up to floating point errors. >>> ndtri(cdf_val) 2.0000000000000004 Plot the function. For that purpose, we provide a NumPy array as argument. >>> import matplotlib.pyplot as plt >>> x = np.linspace(0.01, 1, 200) >>> fig, ax = plt.subplots() >>> ax.plot(x, ndtri(x)) >>> ax.set_title("Standard normal percentile function") >>> plt.show()ndtri_exp(y, out=None) Inverse of `log_ndtr` vs x. Allows for greater precision than `ndtri` composed with `numpy.exp` for very small values of y and for y close to 0. Parameters ---------- y : array_like of float Function argument out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray Inverse of the log CDF of the standard normal distribution, evaluated at y. See Also -------- log_ndtr : log of the standard normal cumulative distribution function ndtr : standard normal cumulative distribution function ndtri : standard normal percentile function Examples -------- >>> import numpy as np >>> import scipy.special as sc `ndtri_exp` agrees with the naive implementation when the latter does not suffer from underflow. >>> sc.ndtri_exp(-1) -0.33747496376420244 >>> sc.ndtri(np.exp(-1)) -0.33747496376420244 For extreme values of y, the naive approach fails >>> sc.ndtri(np.exp(-800)) -inf >>> sc.ndtri(np.exp(-1e-20)) inf whereas `ndtri_exp` is still able to compute the result to high precision. >>> sc.ndtri_exp(-800) -39.88469483825668 >>> sc.ndtri_exp(-1e-20) 9.262340089798409nrdtrimn(p, std, x, out=None) Calculate mean of normal distribution given other params. Parameters ---------- p : array_like CDF values, in range (0, 1]. std : array_like Standard deviation. x : array_like Quantiles, i.e. the upper limit of integration. out : ndarray, optional Optional output array for the function results Returns ------- mn : scalar or ndarray The mean of the normal distribution. See Also -------- scipy.stats.norm : Normal distribution ndtr : Standard normal cumulative probability distribution ndtri : Inverse of standard normal CDF with respect to quantile nrdtrisd : Inverse of normal distribution CDF with respect to standard deviation Examples -------- `nrdtrimn` can be used to recover the mean of a normal distribution if we know the CDF value `p` for a given quantile `x` and the standard deviation `std`. First, we calculate the normal distribution CDF for an exemplary parameter set. >>> from scipy.stats import norm >>> mean = 3. >>> std = 2. >>> x = 6. >>> p = norm.cdf(x, loc=mean, scale=std) >>> p 0.9331927987311419 Verify that `nrdtrimn` returns the original value for `mean`. >>> from scipy.special import nrdtrimn >>> nrdtrimn(p, std, x) 3.0000000000000004nrdtrisd(mn, p, x, out=None) Calculate standard deviation of normal distribution given other params. Parameters ---------- mn : scalar or ndarray The mean of the normal distribution. p : array_like CDF values, in range (0, 1]. x : array_like Quantiles, i.e. the upper limit of integration. out : ndarray, optional Optional output array for the function results Returns ------- std : scalar or ndarray Standard deviation. See Also -------- scipy.stats.norm : Normal distribution ndtr : Standard normal cumulative probability distribution ndtri : Inverse of standard normal CDF with respect to quantile nrdtrimn : Inverse of normal distribution CDF with respect to mean Examples -------- `nrdtrisd` can be used to recover the standard deviation of a normal distribution if we know the CDF value `p` for a given quantile `x` and the mean `mn`. First, we calculate the normal distribution CDF for an exemplary parameter set. >>> from scipy.stats import norm >>> mean = 3. >>> std = 2. >>> x = 6. >>> p = norm.cdf(x, loc=mean, scale=std) >>> p 0.9331927987311419 Verify that `nrdtrisd` returns the original value for `std`. >>> from scipy.special import nrdtrisd >>> nrdtrisd(mean, p, x) 2.0000000000000004owens_t(h, a, out=None) Owen's T Function. The function T(h, a) gives the probability of the event (X > h and 0 < Y < a * X) where X and Y are independent standard normal random variables. Parameters ---------- h: array_like Input value. a: array_like Input value. out : ndarray, optional Optional output array for the function results Returns ------- t: scalar or ndarray Probability of the event (X > h and 0 < Y < a * X), where X and Y are independent standard normal random variables. References ---------- .. [1] M. Patefield and D. Tandy, "Fast and accurate calculation of Owen's T Function", Statistical Software vol. 5, pp. 1-25, 2000. Examples -------- >>> from scipy import special >>> a = 3.5 >>> h = 0.78 >>> special.owens_t(h, a) 0.10877216734852274pdtr(k, m, out=None) Poisson cumulative distribution function. Defined as the probability that a Poisson-distributed random variable with event rate :math:`m` is less than or equal to :math:`k`. More concretely, this works out to be [1]_ .. math:: \exp(-m) \sum_{j = 0}^{\lfloor{k}\rfloor} \frac{m^j}{j!}. Parameters ---------- k : array_like Number of occurrences (nonnegative, real) m : array_like Shape parameter (nonnegative, real) out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray Values of the Poisson cumulative distribution function See Also -------- pdtrc : Poisson survival function pdtrik : inverse of `pdtr` with respect to `k` pdtri : inverse of `pdtr` with respect to `m` References ---------- .. [1] https://en.wikipedia.org/wiki/Poisson_distribution Examples -------- >>> import numpy as np >>> import scipy.special as sc It is a cumulative distribution function, so it converges to 1 monotonically as `k` goes to infinity. >>> sc.pdtr([1, 10, 100, np.inf], 1) array([0.73575888, 0.99999999, 1. , 1. ]) It is discontinuous at integers and constant between integers. >>> sc.pdtr([1, 1.5, 1.9, 2], 1) array([0.73575888, 0.73575888, 0.73575888, 0.9196986 ])pdtrc(k, m, out=None) Poisson survival function Returns the sum of the terms from k+1 to infinity of the Poisson distribution: sum(exp(-m) * m**j / j!, j=k+1..inf) = gammainc( k+1, m). Arguments must both be non-negative doubles. Parameters ---------- k : array_like Number of occurrences (nonnegative, real) m : array_like Shape parameter (nonnegative, real) out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray Values of the Poisson survival function See Also -------- pdtr : Poisson cumulative distribution function pdtrik : inverse of `pdtr` with respect to `k` pdtri : inverse of `pdtr` with respect to `m` Examples -------- >>> import numpy as np >>> import scipy.special as sc It is a survival function, so it decreases to 0 monotonically as `k` goes to infinity. >>> k = np.array([1, 10, 100, np.inf]) >>> sc.pdtrc(k, 1) array([2.64241118e-001, 1.00477664e-008, 3.94147589e-161, 0.00000000e+000]) It can be expressed in terms of the lower incomplete gamma function `gammainc`. >>> sc.gammainc(k + 1, 1) array([2.64241118e-001, 1.00477664e-008, 3.94147589e-161, 0.00000000e+000])pdtri(k, y, out=None) Inverse to `pdtr` vs m Returns the Poisson variable `m` such that the sum from 0 to `k` of the Poisson density is equal to the given probability `y`: calculated by ``gammaincinv(k + 1, y)``. `k` must be a nonnegative integer and `y` between 0 and 1. Parameters ---------- k : array_like Number of occurrences (nonnegative, real) y : array_like Probability out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray Values of the shape parameter `m` such that ``pdtr(k, m) = p`` See Also -------- pdtr : Poisson cumulative distribution function pdtrc : Poisson survival function pdtrik : inverse of `pdtr` with respect to `k` Examples -------- >>> import scipy.special as sc Compute the CDF for several values of `m`: >>> m = [0.5, 1, 1.5] >>> p = sc.pdtr(1, m) >>> p array([0.90979599, 0.73575888, 0.5578254 ]) Compute the inverse. We recover the values of `m`, as expected: >>> sc.pdtri(1, p) array([0.5, 1. , 1.5])pdtrik(p, m, out=None) Inverse to `pdtr` vs `k`. Parameters ---------- p : array_like Probability m : array_like Shape parameter (nonnegative, real) out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray The number of occurrences `k` such that ``pdtr(k, m) = p`` See Also -------- pdtr : Poisson cumulative distribution function pdtrc : Poisson survival function pdtri : inverse of `pdtr` with respect to `m` Examples -------- >>> import scipy.special as sc Compute the CDF for several values of `k`: >>> k = [1, 2, 3] >>> p = sc.pdtr(k, 2) >>> p array([0.40600585, 0.67667642, 0.85712346]) Compute the inverse. We recover the values of `k`, as expected: >>> sc.pdtrik(p, 2) array([1., 2., 3.])poch(z, m, out=None) Pochhammer symbol. The Pochhammer symbol (rising factorial) is defined as .. math:: (z)_m = \frac{\Gamma(z + m)}{\Gamma(z)} For positive integer `m` it reads .. math:: (z)_m = z (z + 1) ... (z + m - 1) See [dlmf]_ for more details. Parameters ---------- z, m : array_like Real-valued arguments. out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray The value of the function. References ---------- .. [dlmf] Nist, Digital Library of Mathematical Functions https://dlmf.nist.gov/5.2#iii Examples -------- >>> import scipy.special as sc It is 1 when m is 0. >>> sc.poch([1, 2, 3, 4], 0) array([1., 1., 1., 1.]) For z equal to 1 it reduces to the factorial function. >>> sc.poch(1, 5) 120.0 >>> 1 * 2 * 3 * 4 * 5 120 It can be expressed in terms of the gamma function. >>> z, m = 3.7, 2.1 >>> sc.poch(z, m) 20.529581933776953 >>> sc.gamma(z + m) / sc.gamma(z) 20.52958193377696powm1(x, y, out=None) Computes ``x**y - 1``. This function is useful when `y` is near 0, or when `x` is near 1. The function is implemented for real types only (unlike ``numpy.power``, which accepts complex inputs). Parameters ---------- x : array_like The base. Must be a real type (i.e. integer or float, not complex). y : array_like The exponent. Must be a real type (i.e. integer or float, not complex). Returns ------- array_like Result of the calculation Notes ----- .. versionadded:: 1.10.0 The underlying code is implemented for single precision and double precision floats only. Unlike `numpy.power`, integer inputs to `powm1` are converted to floating point, and complex inputs are not accepted. Note the following edge cases: * ``powm1(x, 0)`` returns 0 for any ``x``, including 0, ``inf`` and ``nan``. * ``powm1(1, y)`` returns 0 for any ``y``, including ``nan`` and ``inf``. This function wraps the ``powm1`` routine from the Boost Math C++ library [1]_. References ---------- .. [1] The Boost Developers. "Boost C++ Libraries". https://www.boost.org/. Examples -------- >>> import numpy as np >>> from scipy.special import powm1 >>> x = np.array([1.2, 10.0, 0.9999999975]) >>> y = np.array([1e-9, 1e-11, 0.1875]) >>> powm1(x, y) array([ 1.82321557e-10, 2.30258509e-11, -4.68749998e-10]) It can be verified that the relative errors in those results are less than 2.5e-16. Compare that to the result of ``x**y - 1``, where the relative errors are all larger than 8e-8: >>> x**y - 1 array([ 1.82321491e-10, 2.30258035e-11, -4.68750039e-10])pseudo_huber(delta, r, out=None) Pseudo-Huber loss function. .. math:: \mathrm{pseudo\_huber}(\delta, r) = \delta^2 \left( \sqrt{ 1 + \left( \frac{r}{\delta} \right)^2 } - 1 \right) Parameters ---------- delta : array_like Input array, indicating the soft quadratic vs. linear loss changepoint. r : array_like Input array, possibly representing residuals. out : ndarray, optional Optional output array for the function results Returns ------- res : scalar or ndarray The computed Pseudo-Huber loss function values. See Also -------- huber: Similar function which this function approximates Notes ----- Like `huber`, `pseudo_huber` often serves as a robust loss function in statistics or machine learning to reduce the influence of outliers. Unlike `huber`, `pseudo_huber` is smooth. Typically, `r` represents residuals, the difference between a model prediction and data. Then, for :math:`|r|\leq\delta`, `pseudo_huber` resembles the squared error and for :math:`|r|>\delta` the absolute error. This way, the Pseudo-Huber loss often achieves a fast convergence in model fitting for small residuals like the squared error loss function and still reduces the influence of outliers (:math:`|r|>\delta`) like the absolute error loss. As :math:`\delta` is the cutoff between squared and absolute error regimes, it has to be tuned carefully for each problem. `pseudo_huber` is also convex, making it suitable for gradient based optimization. [1]_ [2]_ .. versionadded:: 0.15.0 References ---------- .. [1] Hartley, Zisserman, "Multiple View Geometry in Computer Vision". 2003. Cambridge University Press. p. 619 .. [2] Charbonnier et al. "Deterministic edge-preserving regularization in computed imaging". 1997. IEEE Trans. Image Processing. 6 (2): 298 - 311. Examples -------- Import all necessary modules. >>> import numpy as np >>> from scipy.special import pseudo_huber, huber >>> import matplotlib.pyplot as plt Calculate the function for ``delta=1`` at ``r=2``. >>> pseudo_huber(1., 2.) 1.2360679774997898 Calculate the function at ``r=2`` for different `delta` by providing a list or NumPy array for `delta`. >>> pseudo_huber([1., 2., 4.], 3.) array([2.16227766, 3.21110255, 4. ]) Calculate the function for ``delta=1`` at several points by providing a list or NumPy array for `r`. >>> pseudo_huber(2., np.array([1., 1.5, 3., 4.])) array([0.47213595, 1. , 3.21110255, 4.94427191]) The function can be calculated for different `delta` and `r` by providing arrays for both with compatible shapes for broadcasting. >>> r = np.array([1., 2.5, 8., 10.]) >>> deltas = np.array([[1.], [5.], [9.]]) >>> print(r.shape, deltas.shape) (4,) (3, 1) >>> pseudo_huber(deltas, r) array([[ 0.41421356, 1.6925824 , 7.06225775, 9.04987562], [ 0.49509757, 2.95084972, 22.16990566, 30.90169944], [ 0.49846624, 3.06693762, 27.37435121, 40.08261642]]) Plot the function for different `delta`. >>> x = np.linspace(-4, 4, 500) >>> deltas = [1, 2, 3] >>> linestyles = ["dashed", "dotted", "dashdot"] >>> fig, ax = plt.subplots() >>> combined_plot_parameters = list(zip(deltas, linestyles)) >>> for delta, style in combined_plot_parameters: ... ax.plot(x, pseudo_huber(delta, x), label=rf"$\delta={delta}$", ... ls=style) >>> ax.legend(loc="upper center") >>> ax.set_xlabel("$x$") >>> ax.set_title(r"Pseudo-Huber loss function $h_{\delta}(x)$") >>> ax.set_xlim(-4, 4) >>> ax.set_ylim(0, 8) >>> plt.show() Finally, illustrate the difference between `huber` and `pseudo_huber` by plotting them and their gradients with respect to `r`. The plot shows that `pseudo_huber` is continuously differentiable while `huber` is not at the points :math:`\pm\delta`. >>> def huber_grad(delta, x): ... grad = np.copy(x) ... linear_area = np.argwhere(np.abs(x) > delta) ... grad[linear_area]=delta*np.sign(x[linear_area]) ... return grad >>> def pseudo_huber_grad(delta, x): ... return x* (1+(x/delta)**2)**(-0.5) >>> x=np.linspace(-3, 3, 500) >>> delta = 1. >>> fig, ax = plt.subplots(figsize=(7, 7)) >>> ax.plot(x, huber(delta, x), label="Huber", ls="dashed") >>> ax.plot(x, huber_grad(delta, x), label="Huber Gradient", ls="dashdot") >>> ax.plot(x, pseudo_huber(delta, x), label="Pseudo-Huber", ls="dotted") >>> ax.plot(x, pseudo_huber_grad(delta, x), label="Pseudo-Huber Gradient", ... ls="solid") >>> ax.legend(loc="upper center") >>> plt.show()rel_entr(x, y, out=None) Elementwise function for computing relative entropy. .. math:: \mathrm{rel\_entr}(x, y) = \begin{cases} x \log(x / y) & x > 0, y > 0 \\ 0 & x = 0, y \ge 0 \\ \infty & \text{otherwise} \end{cases} Parameters ---------- x, y : array_like Input arrays out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray Relative entropy of the inputs See Also -------- entr, kl_div, scipy.stats.entropy Notes ----- .. versionadded:: 0.15.0 This function is jointly convex in x and y. The origin of this function is in convex programming; see [1]_. Given two discrete probability distributions :math:`p_1, \ldots, p_n` and :math:`q_1, \ldots, q_n`, the definition of relative entropy in the context of *information theory* is .. math:: \sum_{i = 1}^n \mathrm{rel\_entr}(p_i, q_i). To compute the latter quantity, use `scipy.stats.entropy`. See [2]_ for details. References ---------- .. [1] Boyd, Stephen and Lieven Vandenberghe. *Convex optimization*. Cambridge University Press, 2004. :doi:`https://doi.org/10.1017/CBO9780511804441` .. [2] Kullback-Leibler divergence, https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergenceround(x, out=None) Round to the nearest integer. Returns the nearest integer to `x`. If `x` ends in 0.5 exactly, the nearest even integer is chosen. Parameters ---------- x : array_like Real valued input. out : ndarray, optional Optional output array for the function results. Returns ------- scalar or ndarray The nearest integers to the elements of `x`. The result is of floating type, not integer type. Examples -------- >>> import scipy.special as sc It rounds to even. >>> sc.round([0.5, 1.5]) array([0., 2.])shichi(x, out=None) Hyperbolic sine and cosine integrals. The hyperbolic sine integral is .. math:: \int_0^x \frac{\sinh{t}}{t}dt and the hyperbolic cosine integral is .. math:: \gamma + \log(x) + \int_0^x \frac{\cosh{t} - 1}{t} dt where :math:`\gamma` is Euler's constant and :math:`\log` is the principal branch of the logarithm [1]_. Parameters ---------- x : array_like Real or complex points at which to compute the hyperbolic sine and cosine integrals. out : tuple of ndarray, optional Optional output arrays for the function results Returns ------- si : scalar or ndarray Hyperbolic sine integral at ``x`` ci : scalar or ndarray Hyperbolic cosine integral at ``x`` See Also -------- sici : Sine and cosine integrals. exp1 : Exponential integral E1. expi : Exponential integral Ei. Notes ----- For real arguments with ``x < 0``, ``chi`` is the real part of the hyperbolic cosine integral. For such points ``chi(x)`` and ``chi(x + 0j)`` differ by a factor of ``1j*pi``. For real arguments the function is computed by calling Cephes' [2]_ *shichi* routine. For complex arguments the algorithm is based on Mpmath's [3]_ *shi* and *chi* routines. References ---------- .. [1] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. (See Section 5.2.) .. [2] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ .. [3] Fredrik Johansson and others. "mpmath: a Python library for arbitrary-precision floating-point arithmetic" (Version 0.19) http://mpmath.org/ Examples -------- >>> import numpy as np >>> import matplotlib.pyplot as plt >>> from scipy.special import shichi, sici `shichi` accepts real or complex input: >>> shichi(0.5) (0.5069967498196671, -0.05277684495649357) >>> shichi(0.5 + 2.5j) ((0.11772029666668238+1.831091777729851j), (0.29912435887648825+1.7395351121166562j)) The hyperbolic sine and cosine integrals Shi(z) and Chi(z) are related to the sine and cosine integrals Si(z) and Ci(z) by * Shi(z) = -i*Si(i*z) * Chi(z) = Ci(-i*z) + i*pi/2 >>> z = 0.25 + 5j >>> shi, chi = shichi(z) >>> shi, -1j*sici(1j*z)[0] # Should be the same. ((-0.04834719325101729+1.5469354086921228j), (-0.04834719325101729+1.5469354086921228j)) >>> chi, sici(-1j*z)[1] + 1j*np.pi/2 # Should be the same. ((-0.19568708973868087+1.556276312103824j), (-0.19568708973868087+1.556276312103824j)) Plot the functions evaluated on the real axis: >>> xp = np.geomspace(1e-8, 4.0, 250) >>> x = np.concatenate((-xp[::-1], xp)) >>> shi, chi = shichi(x) >>> fig, ax = plt.subplots() >>> ax.plot(x, shi, label='Shi(x)') >>> ax.plot(x, chi, '--', label='Chi(x)') >>> ax.set_xlabel('x') >>> ax.set_title('Hyperbolic Sine and Cosine Integrals') >>> ax.legend(shadow=True, framealpha=1, loc='lower right') >>> ax.grid(True) >>> plt.show()sici(x, out=None) Sine and cosine integrals. The sine integral is .. math:: \int_0^x \frac{\sin{t}}{t}dt and the cosine integral is .. math:: \gamma + \log(x) + \int_0^x \frac{\cos{t} - 1}{t}dt where :math:`\gamma` is Euler's constant and :math:`\log` is the principal branch of the logarithm [1]_. Parameters ---------- x : array_like Real or complex points at which to compute the sine and cosine integrals. out : tuple of ndarray, optional Optional output arrays for the function results Returns ------- si : scalar or ndarray Sine integral at ``x`` ci : scalar or ndarray Cosine integral at ``x`` See Also -------- shichi : Hyperbolic sine and cosine integrals. exp1 : Exponential integral E1. expi : Exponential integral Ei. Notes ----- For real arguments with ``x < 0``, ``ci`` is the real part of the cosine integral. For such points ``ci(x)`` and ``ci(x + 0j)`` differ by a factor of ``1j*pi``. For real arguments the function is computed by calling Cephes' [2]_ *sici* routine. For complex arguments the algorithm is based on Mpmath's [3]_ *si* and *ci* routines. References ---------- .. [1] Milton Abramowitz and Irene A. Stegun, eds. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover, 1972. (See Section 5.2.) .. [2] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ .. [3] Fredrik Johansson and others. "mpmath: a Python library for arbitrary-precision floating-point arithmetic" (Version 0.19) http://mpmath.org/ Examples -------- >>> import numpy as np >>> import matplotlib.pyplot as plt >>> from scipy.special import sici, exp1 `sici` accepts real or complex input: >>> sici(2.5) (1.7785201734438267, 0.2858711963653835) >>> sici(2.5 + 3j) ((4.505735874563953+0.06863305018999577j), (0.0793644206906966-2.935510262937543j)) For z in the right half plane, the sine and cosine integrals are related to the exponential integral E1 (implemented in SciPy as `scipy.special.exp1`) by * Si(z) = (E1(i*z) - E1(-i*z))/2i + pi/2 * Ci(z) = -(E1(i*z) + E1(-i*z))/2 See [1]_ (equations 5.2.21 and 5.2.23). We can verify these relations: >>> z = 2 - 3j >>> sici(z) ((4.54751388956229-1.3991965806460565j), (1.408292501520851+2.9836177420296055j)) >>> (exp1(1j*z) - exp1(-1j*z))/2j + np.pi/2 # Same as sine integral (4.54751388956229-1.3991965806460565j) >>> -(exp1(1j*z) + exp1(-1j*z))/2 # Same as cosine integral (1.408292501520851+2.9836177420296055j) Plot the functions evaluated on the real axis; the dotted horizontal lines are at pi/2 and -pi/2: >>> x = np.linspace(-16, 16, 150) >>> si, ci = sici(x) >>> fig, ax = plt.subplots() >>> ax.plot(x, si, label='Si(x)') >>> ax.plot(x, ci, '--', label='Ci(x)') >>> ax.legend(shadow=True, framealpha=1, loc='upper left') >>> ax.set_xlabel('x') >>> ax.set_title('Sine and Cosine Integrals') >>> ax.axhline(np.pi/2, linestyle=':', alpha=0.5, color='k') >>> ax.axhline(-np.pi/2, linestyle=':', alpha=0.5, color='k') >>> ax.grid(True) >>> plt.show()smirnov(n, d, out=None) Kolmogorov-Smirnov complementary cumulative distribution function Returns the exact Kolmogorov-Smirnov complementary cumulative distribution function,(aka the Survival Function) of Dn+ (or Dn-) for a one-sided test of equality between an empirical and a theoretical distribution. It is equal to the probability that the maximum difference between a theoretical distribution and an empirical one based on `n` samples is greater than d. Parameters ---------- n : int Number of samples d : float array_like Deviation between the Empirical CDF (ECDF) and the target CDF. out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray The value(s) of smirnov(n, d), Prob(Dn+ >= d) (Also Prob(Dn- >= d)) See Also -------- smirnovi : The Inverse Survival Function for the distribution scipy.stats.ksone : Provides the functionality as a continuous distribution kolmogorov, kolmogi : Functions for the two-sided distribution Notes ----- `smirnov` is used by `stats.kstest` in the application of the Kolmogorov-Smirnov Goodness of Fit test. For historical reasons this function is exposed in `scpy.special`, but the recommended way to achieve the most accurate CDF/SF/PDF/PPF/ISF computations is to use the `stats.ksone` distribution. Examples -------- >>> import numpy as np >>> from scipy.special import smirnov >>> from scipy.stats import norm Show the probability of a gap at least as big as 0, 0.5 and 1.0 for a sample of size 5. >>> smirnov(5, [0, 0.5, 1.0]) array([ 1. , 0.056, 0. ]) Compare a sample of size 5 against N(0, 1), the standard normal distribution with mean 0 and standard deviation 1. `x` is the sample. >>> x = np.array([-1.392, -0.135, 0.114, 0.190, 1.82]) >>> target = norm(0, 1) >>> cdfs = target.cdf(x) >>> cdfs array([0.0819612 , 0.44630594, 0.5453811 , 0.57534543, 0.9656205 ]) Construct the empirical CDF and the K-S statistics (Dn+, Dn-, Dn). >>> n = len(x) >>> ecdfs = np.arange(n+1, dtype=float)/n >>> cols = np.column_stack([x, ecdfs[1:], cdfs, cdfs - ecdfs[:n], ... ecdfs[1:] - cdfs]) >>> with np.printoptions(precision=3): ... print(cols) [[-1.392 0.2 0.082 0.082 0.118] [-0.135 0.4 0.446 0.246 -0.046] [ 0.114 0.6 0.545 0.145 0.055] [ 0.19 0.8 0.575 -0.025 0.225] [ 1.82 1. 0.966 0.166 0.034]] >>> gaps = cols[:, -2:] >>> Dnpm = np.max(gaps, axis=0) >>> print(f'Dn-={Dnpm[0]:f}, Dn+={Dnpm[1]:f}') Dn-=0.246306, Dn+=0.224655 >>> probs = smirnov(n, Dnpm) >>> print(f'For a sample of size {n} drawn from N(0, 1):', ... f' Smirnov n={n}: Prob(Dn- >= {Dnpm[0]:f}) = {probs[0]:.4f}', ... f' Smirnov n={n}: Prob(Dn+ >= {Dnpm[1]:f}) = {probs[1]:.4f}', ... sep='\n') For a sample of size 5 drawn from N(0, 1): Smirnov n=5: Prob(Dn- >= 0.246306) = 0.4711 Smirnov n=5: Prob(Dn+ >= 0.224655) = 0.5245 Plot the empirical CDF and the standard normal CDF. >>> import matplotlib.pyplot as plt >>> plt.step(np.concatenate(([-2.5], x, [2.5])), ... np.concatenate((ecdfs, [1])), ... where='post', label='Empirical CDF') >>> xx = np.linspace(-2.5, 2.5, 100) >>> plt.plot(xx, target.cdf(xx), '--', label='CDF for N(0, 1)') Add vertical lines marking Dn+ and Dn-. >>> iminus, iplus = np.argmax(gaps, axis=0) >>> plt.vlines([x[iminus]], ecdfs[iminus], cdfs[iminus], color='r', ... alpha=0.5, lw=4) >>> plt.vlines([x[iplus]], cdfs[iplus], ecdfs[iplus+1], color='m', ... alpha=0.5, lw=4) >>> plt.grid(True) >>> plt.legend(framealpha=1, shadow=True) >>> plt.show()smirnovi(n, p, out=None) Inverse to `smirnov` Returns `d` such that ``smirnov(n, d) == p``, the critical value corresponding to `p`. Parameters ---------- n : int Number of samples p : float array_like Probability out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray The value(s) of smirnovi(n, p), the critical values. See Also -------- smirnov : The Survival Function (SF) for the distribution scipy.stats.ksone : Provides the functionality as a continuous distribution kolmogorov, kolmogi : Functions for the two-sided distribution scipy.stats.kstwobign : Two-sided Kolmogorov-Smirnov distribution, large n Notes ----- `smirnov` is used by `stats.kstest` in the application of the Kolmogorov-Smirnov Goodness of Fit test. For historical reasons this function is exposed in `scpy.special`, but the recommended way to achieve the most accurate CDF/SF/PDF/PPF/ISF computations is to use the `stats.ksone` distribution. Examples -------- >>> from scipy.special import smirnovi, smirnov >>> n = 24 >>> deviations = [0.1, 0.2, 0.3] Use `smirnov` to compute the complementary CDF of the Smirnov distribution for the given number of samples and deviations. >>> p = smirnov(n, deviations) >>> p array([0.58105083, 0.12826832, 0.01032231]) The inverse function ``smirnovi(n, p)`` returns ``deviations``. >>> smirnovi(n, p) array([0.1, 0.2, 0.3])spence(z, out=None) Spence's function, also known as the dilogarithm. It is defined to be .. math:: \int_1^z \frac{\log(t)}{1 - t}dt for complex :math:`z`, where the contour of integration is taken to avoid the branch cut of the logarithm. Spence's function is analytic everywhere except the negative real axis where it has a branch cut. Parameters ---------- z : array_like Points at which to evaluate Spence's function out : ndarray, optional Optional output array for the function results Returns ------- s : scalar or ndarray Computed values of Spence's function Notes ----- There is a different convention which defines Spence's function by the integral .. math:: -\int_0^z \frac{\log(1 - t)}{t}dt; this is our ``spence(1 - z)``. Examples -------- >>> import numpy as np >>> from scipy.special import spence >>> import matplotlib.pyplot as plt The function is defined for complex inputs: >>> spence([1-1j, 1.5+2j, 3j, -10-5j]) array([-0.20561676+0.91596559j, -0.86766909-1.39560134j, -0.59422064-2.49129918j, -1.14044398+6.80075924j]) For complex inputs on the branch cut, which is the negative real axis, the function returns the limit for ``z`` with positive imaginary part. For example, in the following, note the sign change of the imaginary part of the output for ``z = -2`` and ``z = -2 - 1e-8j``: >>> spence([-2 + 1e-8j, -2, -2 - 1e-8j]) array([2.32018041-3.45139229j, 2.32018042-3.4513923j , 2.32018041+3.45139229j]) The function returns ``nan`` for real inputs on the branch cut: >>> spence(-1.5) nan Verify some particular values: ``spence(0) = pi**2/6``, ``spence(1) = 0`` and ``spence(2) = -pi**2/12``. >>> spence([0, 1, 2]) array([ 1.64493407, 0. , -0.82246703]) >>> np.pi**2/6, -np.pi**2/12 (1.6449340668482264, -0.8224670334241132) Verify the identity:: spence(z) + spence(1 - z) = pi**2/6 - log(z)*log(1 - z) >>> z = 3 + 4j >>> spence(z) + spence(1 - z) (-2.6523186143876067+1.8853470951513935j) >>> np.pi**2/6 - np.log(z)*np.log(1 - z) (-2.652318614387606+1.885347095151394j) Plot the function for positive real input. >>> fig, ax = plt.subplots() >>> x = np.linspace(0, 6, 400) >>> ax.plot(x, spence(x)) >>> ax.grid() >>> ax.set_xlabel('x') >>> ax.set_title('spence(x)') >>> plt.show()stdtr(df, t, out=None) Student t distribution cumulative distribution function Returns the integral: .. math:: \frac{\Gamma((df+1)/2)}{\sqrt{\pi df} \Gamma(df/2)} \int_{-\infty}^t (1+x^2/df)^{-(df+1)/2}\, dx Parameters ---------- df : array_like Degrees of freedom t : array_like Upper bound of the integral out : ndarray, optional Optional output array for the function results Returns ------- scalar or ndarray Value of the Student t CDF at t See Also -------- stdtridf : inverse of stdtr with respect to `df` stdtrit : inverse of stdtr with respect to `t` scipy.stats.t : student t distribution Notes ----- The student t distribution is also available as `scipy.stats.t`. Calling `stdtr` directly can improve performance compared to the ``cdf`` method of `scipy.stats.t` (see last example below). Examples -------- Calculate the function for ``df=3`` at ``t=1``. >>> import numpy as np >>> from scipy.special import stdtr >>> import matplotlib.pyplot as plt >>> stdtr(3, 1) 0.8044988905221148 Plot the function for three different degrees of freedom. >>> x = np.linspace(-10, 10, 1000) >>> fig, ax = plt.subplots() >>> parameters = [(1, "solid"), (3, "dashed"), (10, "dotted")] >>> for (df, linestyle) in parameters: ... ax.plot(x, stdtr(df, x), ls=linestyle, label=f"$df={df}$") >>> ax.legend() >>> ax.set_title("Student t distribution cumulative distribution function") >>> plt.show() The function can be computed for several degrees of freedom at the same time by providing a NumPy array or list for `df`: >>> stdtr([1, 2, 3], 1) array([0.75 , 0.78867513, 0.80449889]) It is possible to calculate the function at several points for several different degrees of freedom simultaneously by providing arrays for `df` and `t` with shapes compatible for broadcasting. Compute `stdtr` at 4 points for 3 degrees of freedom resulting in an array of shape 3x4. >>> dfs = np.array([[1], [2], [3]]) >>> t = np.array([2, 4, 6, 8]) >>> dfs.shape, t.shape ((3, 1), (4,)) >>> stdtr(dfs, t) array([[0.85241638, 0.92202087, 0.94743154, 0.96041658], [0.90824829, 0.97140452, 0.98666426, 0.99236596], [0.93033702, 0.98599577, 0.99536364, 0.99796171]]) The t distribution is also available as `scipy.stats.t`. Calling `stdtr` directly can be much faster than calling the ``cdf`` method of `scipy.stats.t`. To get the same results, one must use the following parametrization: ``scipy.stats.t(df).cdf(x) = stdtr(df, x)``. >>> from scipy.stats import t >>> df, x = 3, 1 >>> stdtr_result = stdtr(df, x) # this can be faster than below >>> stats_result = t(df).cdf(x) >>> stats_result == stdtr_result # test that results are equal Truestdtridf(p, t, out=None) Inverse of `stdtr` vs df Returns the argument df such that stdtr(df, t) is equal to `p`. Parameters ---------- p : array_like Probability t : array_like Upper bound of the integral out : ndarray, optional Optional output array for the function results Returns ------- df : scalar or ndarray Value of `df` such that ``stdtr(df, t) == p`` See Also -------- stdtr : Student t CDF stdtrit : inverse of stdtr with respect to `t` scipy.stats.t : Student t distribution Examples -------- Compute the student t cumulative distribution function for one parameter set. >>> from scipy.special import stdtr, stdtridf >>> df, x = 5, 2 >>> cdf_value = stdtr(df, x) >>> cdf_value 0.9490302605850709 Verify that `stdtridf` recovers the original value for `df` given the CDF value and `x`. >>> stdtridf(cdf_value, x) 5.0stdtrit(df, p, out=None) The `p`-th quantile of the student t distribution. This function is the inverse of the student t distribution cumulative distribution function (CDF), returning `t` such that `stdtr(df, t) = p`. Returns the argument `t` such that stdtr(df, t) is equal to `p`. Parameters ---------- df : array_like Degrees of freedom p : array_like Probability out : ndarray, optional Optional output array for the function results Returns ------- t : scalar or ndarray Value of `t` such that ``stdtr(df, t) == p`` See Also -------- stdtr : Student t CDF stdtridf : inverse of stdtr with respect to `df` scipy.stats.t : Student t distribution Notes ----- The student t distribution is also available as `scipy.stats.t`. Calling `stdtrit` directly can improve performance compared to the ``ppf`` method of `scipy.stats.t` (see last example below). Examples -------- `stdtrit` represents the inverse of the student t distribution CDF which is available as `stdtr`. Here, we calculate the CDF for ``df`` at ``x=1``. `stdtrit` then returns ``1`` up to floating point errors given the same value for `df` and the computed CDF value. >>> import numpy as np >>> from scipy.special import stdtr, stdtrit >>> import matplotlib.pyplot as plt >>> df = 3 >>> x = 1 >>> cdf_value = stdtr(df, x) >>> stdtrit(df, cdf_value) 0.9999999994418539 Plot the function for three different degrees of freedom. >>> x = np.linspace(0, 1, 1000) >>> parameters = [(1, "solid"), (2, "dashed"), (5, "dotted")] >>> fig, ax = plt.subplots() >>> for (df, linestyle) in parameters: ... ax.plot(x, stdtrit(df, x), ls=linestyle, label=f"$df={df}$") >>> ax.legend() >>> ax.set_ylim(-10, 10) >>> ax.set_title("Student t distribution quantile function") >>> plt.show() The function can be computed for several degrees of freedom at the same time by providing a NumPy array or list for `df`: >>> stdtrit([1, 2, 3], 0.7) array([0.72654253, 0.6172134 , 0.58438973]) It is possible to calculate the function at several points for several different degrees of freedom simultaneously by providing arrays for `df` and `p` with shapes compatible for broadcasting. Compute `stdtrit` at 4 points for 3 degrees of freedom resulting in an array of shape 3x4. >>> dfs = np.array([[1], [2], [3]]) >>> p = np.array([0.2, 0.4, 0.7, 0.8]) >>> dfs.shape, p.shape ((3, 1), (4,)) >>> stdtrit(dfs, p) array([[-1.37638192, -0.3249197 , 0.72654253, 1.37638192], [-1.06066017, -0.28867513, 0.6172134 , 1.06066017], [-0.97847231, -0.27667066, 0.58438973, 0.97847231]]) The t distribution is also available as `scipy.stats.t`. Calling `stdtrit` directly can be much faster than calling the ``ppf`` method of `scipy.stats.t`. To get the same results, one must use the following parametrization: ``scipy.stats.t(df).ppf(x) = stdtrit(df, x)``. >>> from scipy.stats import t >>> df, x = 3, 0.5 >>> stdtrit_result = stdtrit(df, x) # this can be faster than below >>> stats_result = t(df).ppf(x) >>> stats_result == stdtrit_result # test that results are equal Truetklmbda(x, lmbda, out=None) Cumulative distribution function of the Tukey lambda distribution. Parameters ---------- x, lmbda : array_like Parameters out : ndarray, optional Optional output array for the function results Returns ------- cdf : scalar or ndarray Value of the Tukey lambda CDF See Also -------- scipy.stats.tukeylambda : Tukey lambda distribution Examples -------- >>> import numpy as np >>> import matplotlib.pyplot as plt >>> from scipy.special import tklmbda, expit Compute the cumulative distribution function (CDF) of the Tukey lambda distribution at several ``x`` values for `lmbda` = -1.5. >>> x = np.linspace(-2, 2, 9) >>> x array([-2. , -1.5, -1. , -0.5, 0. , 0.5, 1. , 1.5, 2. ]) >>> tklmbda(x, -1.5) array([0.34688734, 0.3786554 , 0.41528805, 0.45629737, 0.5 , 0.54370263, 0.58471195, 0.6213446 , 0.65311266]) When `lmbda` is 0, the function is the logistic sigmoid function, which is implemented in `scipy.special` as `expit`. >>> tklmbda(x, 0) array([0.11920292, 0.18242552, 0.26894142, 0.37754067, 0.5 , 0.62245933, 0.73105858, 0.81757448, 0.88079708]) >>> expit(x) array([0.11920292, 0.18242552, 0.26894142, 0.37754067, 0.5 , 0.62245933, 0.73105858, 0.81757448, 0.88079708]) When `lmbda` is 1, the Tukey lambda distribution is uniform on the interval [-1, 1], so the CDF increases linearly. >>> t = np.linspace(-1, 1, 9) >>> tklmbda(t, 1) array([0. , 0.125, 0.25 , 0.375, 0.5 , 0.625, 0.75 , 0.875, 1. ]) In the following, we generate plots for several values of `lmbda`. The first figure shows graphs for `lmbda` <= 0. >>> styles = ['-', '-.', '--', ':'] >>> fig, ax = plt.subplots() >>> x = np.linspace(-12, 12, 500) >>> for k, lmbda in enumerate([-1.0, -0.5, 0.0]): ... y = tklmbda(x, lmbda) ... ax.plot(x, y, styles[k], label=rf'$\lambda$ = {lmbda:-4.1f}') >>> ax.set_title(r'tklmbda(x, $\lambda$)') >>> ax.set_label('x') >>> ax.legend(framealpha=1, shadow=True) >>> ax.grid(True) The second figure shows graphs for `lmbda` > 0. The dots in the graphs show the bounds of the support of the distribution. >>> fig, ax = plt.subplots() >>> x = np.linspace(-4.2, 4.2, 500) >>> lmbdas = [0.25, 0.5, 1.0, 1.5] >>> for k, lmbda in enumerate(lmbdas): ... y = tklmbda(x, lmbda) ... ax.plot(x, y, styles[k], label=fr'$\lambda$ = {lmbda}') >>> ax.set_prop_cycle(None) >>> for lmbda in lmbdas: ... ax.plot([-1/lmbda, 1/lmbda], [0, 1], '.', ms=8) >>> ax.set_title(r'tklmbda(x, $\lambda$)') >>> ax.set_xlabel('x') >>> ax.legend(framealpha=1, shadow=True) >>> ax.grid(True) >>> plt.tight_layout() >>> plt.show() The CDF of the Tukey lambda distribution is also implemented as the ``cdf`` method of `scipy.stats.tukeylambda`. In the following, ``tukeylambda.cdf(x, -0.5)`` and ``tklmbda(x, -0.5)`` compute the same values: >>> from scipy.stats import tukeylambda >>> x = np.linspace(-2, 2, 9) >>> tukeylambda.cdf(x, -0.5) array([0.21995157, 0.27093858, 0.33541677, 0.41328161, 0.5 , 0.58671839, 0.66458323, 0.72906142, 0.78004843]) >>> tklmbda(x, -0.5) array([0.21995157, 0.27093858, 0.33541677, 0.41328161, 0.5 , 0.58671839, 0.66458323, 0.72906142, 0.78004843]) The implementation in ``tukeylambda`` also provides location and scale parameters, and other methods such as ``pdf()`` (the probability density function) and ``ppf()`` (the inverse of the CDF), so for working with the Tukey lambda distribution, ``tukeylambda`` is more generally useful. The primary advantage of ``tklmbda`` is that it is significantly faster than ``tukeylambda.cdf``.wrightomega(z, out=None) Wright Omega function. Defined as the solution to .. math:: \omega + \log(\omega) = z where :math:`\log` is the principal branch of the complex logarithm. Parameters ---------- z : array_like Points at which to evaluate the Wright Omega function out : ndarray, optional Optional output array for the function values Returns ------- omega : scalar or ndarray Values of the Wright Omega function See Also -------- lambertw : The Lambert W function Notes ----- .. versionadded:: 0.19.0 The function can also be defined as .. math:: \omega(z) = W_{K(z)}(e^z) where :math:`K(z) = \lceil (\Im(z) - \pi)/(2\pi) \rceil` is the unwinding number and :math:`W` is the Lambert W function. The implementation here is taken from [1]_. References ---------- .. [1] Lawrence, Corless, and Jeffrey, "Algorithm 917: Complex Double-Precision Evaluation of the Wright :math:`\omega` Function." ACM Transactions on Mathematical Software, 2012. :doi:`10.1145/2168773.2168779`. Examples -------- >>> import numpy as np >>> from scipy.special import wrightomega, lambertw >>> wrightomega([-2, -1, 0, 1, 2]) array([0.12002824, 0.27846454, 0.56714329, 1. , 1.5571456 ]) Complex input: >>> wrightomega(3 + 5j) (1.5804428632097158+3.8213626783287937j) Verify that ``wrightomega(z)`` satisfies ``w + log(w) = z``: >>> w = -5 + 4j >>> wrightomega(w + np.log(w)) (-5+4j) Verify the connection to ``lambertw``: >>> z = 0.5 + 3j >>> wrightomega(z) (0.0966015889280649+1.4937828458191993j) >>> lambertw(np.exp(z)) (0.09660158892806493+1.4937828458191993j) >>> z = 0.5 + 4j >>> wrightomega(z) (-0.3362123489037213+2.282986001579032j) >>> lambertw(np.exp(z), k=1) (-0.33621234890372115+2.282986001579032j)yn(n, x, out=None) Bessel function of the second kind of integer order and real argument. Parameters ---------- n : array_like Order (integer). x : array_like Argument (float). out : ndarray, optional Optional output array for the function results Returns ------- Y : scalar or ndarray Value of the Bessel function, :math:`Y_n(x)`. See Also -------- yv : For real order and real or complex argument. y0: faster implementation of this function for order 0 y1: faster implementation of this function for order 1 Notes ----- Wrapper for the Cephes [1]_ routine `yn`. The function is evaluated by forward recurrence on `n`, starting with values computed by the Cephes routines `y0` and `y1`. If ``n = 0`` or 1, the routine for `y0` or `y1` is called directly. References ---------- .. [1] Cephes Mathematical Functions Library, http://www.netlib.org/cephes/ Examples -------- Evaluate the function of order 0 at one point. >>> from scipy.special import yn >>> yn(0, 1.) 0.08825696421567697 Evaluate the function at one point for different orders. >>> yn(0, 1.), yn(1, 1.), yn(2, 1.) (0.08825696421567697, -0.7812128213002888, -1.6506826068162546) The evaluation for different orders can be carried out in one call by providing a list or NumPy array as argument for the `v` parameter: >>> yn([0, 1, 2], 1.) array([ 0.08825696, -0.78121282, -1.65068261]) Evaluate the function at several points for order 0 by providing an array for `z`. >>> import numpy as np >>> points = np.array([0.5, 3., 8.]) >>> yn(0, points) array([-0.44451873, 0.37685001, 0.22352149]) If `z` is an array, the order parameter `v` must be broadcastable to the correct shape if different orders shall be computed in one call. To calculate the orders 0 and 1 for an 1D array: >>> orders = np.array([[0], [1]]) >>> orders.shape (2, 1) >>> yn(orders, points) array([[-0.44451873, 0.37685001, 0.22352149], [-1.47147239, 0.32467442, -0.15806046]]) Plot the functions of order 0 to 3 from 0 to 10. >>> import matplotlib.pyplot as plt >>> fig, ax = plt.subplots() >>> x = np.linspace(0., 10., 1000) >>> for i in range(4): ... ax.plot(x, yn(i, x), label=f'$Y_{i!r}$') >>> ax.set_ylim(-3, 1) >>> ax.legend() >>> plt.show()_cython_3_1_6.cython_function_or_method_cython_3_1_6._common_types_metatype,,,,,0 !A 4Set how special-function errors are handled. Parameters ---------- all : {'ignore', 'warn' 'raise'}, optional Set treatment for all type of special-function errors at once. The options are: - 'ignore' Take no action when the error occurs - 'warn' Print a `SpecialFunctionWarning` when the error occurs (via the Python `warnings` module) - 'raise' Raise a `SpecialFunctionError` when the error occurs. The default is to not change the current behavior. If behaviors for additional categories of special-function errors are specified, then ``all`` is applied first, followed by the additional categories. singular : {'ignore', 'warn', 'raise'}, optional Treatment for singularities. underflow : {'ignore', 'warn', 'raise'}, optional Treatment for underflow. overflow : {'ignore', 'warn', 'raise'}, optional Treatment for overflow. slow : {'ignore', 'warn', 'raise'}, optional Treatment for slow convergence. loss : {'ignore', 'warn', 'raise'}, optional Treatment for loss of accuracy. no_result : {'ignore', 'warn', 'raise'}, optional Treatment for failing to find a result. domain : {'ignore', 'warn', 'raise'}, optional Treatment for an invalid argument to a function. arg : {'ignore', 'warn', 'raise'}, optional Treatment for an invalid parameter to a function. other : {'ignore', 'warn', 'raise'}, optional Treatment for an unknown error. Returns ------- olderr : dict Dictionary containing the old settings. See Also -------- geterr : get the current way of handling special-function errors errstate : context manager for special-function error handling numpy.seterr : similar numpy function for floating-point errors Examples -------- >>> import scipy.special as sc >>> from pytest import raises >>> sc.gammaln(0) inf >>> olderr = sc.seterr(singular='raise') >>> with raises(sc.SpecialFunctionError): ... sc.gammaln(0) ... >>> _ = sc.seterr(**olderr) We can also raise for every category except one. >>> olderr = sc.seterr(all='raise', singular='ignore') >>> sc.gammaln(0) inf >>> with raises(sc.SpecialFunctionError): ... sc.spence(-1) ... >>> _ = sc.seterr(**olderr) Get the current way of handling special-function errors. Returns ------- err : dict A dictionary with keys "singular", "underflow", "overflow", "slow", "loss", "no_result", "domain", "arg", and "other", whose values are from the strings "ignore", "warn", and "raise". The keys represent possible special-function errors, and the values define how these errors are handled. See Also -------- seterr : set how special-function errors are handled errstate : context manager for special-function error handling numpy.geterr : similar numpy function for floating-point errors Notes ----- For complete documentation of the types of special-function errors and treatment options, see `seterr`. Examples -------- By default all errors are ignored. >>> import scipy.special as sc >>> for key, value in sorted(sc.geterr().items()): ... print(f'{key}: {value}') ... arg: ignore domain: ignore loss: ignore memory: raise no_result: ignore other: ignore overflow: ignore singular: ignore slow: ignore underflow: ignore scipy/special/_ufuncs_extra_code.pxinumpy._core.umath failed to importnumpy._core.multiarray failed to importContext manager for special-function error handling. Using an instance of `errstate` as a context manager allows statements in that context to execute with a known error handling behavior. Upon entering the context the error handling is set with `seterr`, and upon exiting it is restored to what it was before. Parameters ---------- kwargs : {all, singular, underflow, overflow, slow, loss, no_result, domain, arg, other} Keyword arguments. The valid keywords are possible special-function errors. Each keyword should have a string value that defines the treatment for the particular type of error. Values must be 'ignore', 'warn', or 'other'. See `seterr` for details. See Also -------- geterr : get the current way of handling special-function errors seterr : set how special-function errors are handled numpy.errstate : similar numpy function for floating-point errors Examples -------- >>> import scipy.special as sc >>> from pytest import raises >>> sc.gammaln(0) inf >>> with sc.errstate(singular='raise'): ... with raises(sc.SpecialFunctionError): ... sc.gammaln(0) ... >>> sc.gammaln(0) inf We can also raise on every category except one. >>> with sc.errstate(all='raise', singular='ignore'): ... sc.gammaln(0) ... with raises(sc.SpecialFunctionError): ... sc.spence(-1) ... inf Set how special-function errors are handled. Parameters ---------- all : {'ignore', 'warn' 'raise'}, optional Set treatment for all type of special-function errors at once. The options are: - 'ignore' Take no action when the error occurs - 'warn' Print a `SpecialFunctionWarning` when the error occurs (via the Python `warnings` module) - 'raise' Raise a `SpecialFunctionError` when the error occurs. The default is to not change the current behavior. If behaviors for additional categories of special-function errors are specified, then ``all`` is applied first, followed by the additional categories. singular : {'ignore', 'warn', 'raise'}, optional Treatment for singularities. underflow : {'ignore', 'warn', 'raise'}, optional Treatment for underflow. overflow : {'ignore', 'warn', 'raise'}, optional Treatment for overflow. slow : {'ignore', 'warn', 'raise'}, optional Treatment for slow convergence. loss : {'ignore', 'warn', 'raise'}, optional Treatment for loss of accuracy. no_result : {'ignore', 'warn', 'raise'}, optional Treatment for failing to find a result. domain : {'ignore', 'warn', 'raise'}, optional Treatment for an invalid argument to a function. arg : {'ignore', 'warn', 'raise'}, optional Treatment for an invalid parameter to a function. other : {'ignore', 'warn', 'raise'}, optional Treatment for an unknown error. Returns ------- olderr : dict Dictionary containing the old settings. See Also -------- geterr : get the current way of handling special-function errors errstate : context manager for special-function error handling numpy.seterr : similar numpy function for floating-point errors Examples -------- >>> import scipy.special as sc >>> from pytest import raises >>> sc.gammaln(0) inf >>> olderr = sc.seterr(singular='raise') >>> with raises(sc.SpecialFunctionError): ... sc.gammaln(0) ... >>> _ = sc.seterr(**olderr) We can also raise for every category except one. >>> olderr = sc.seterr(all='raise', singular='ignore') >>> sc.gammaln(0) inf >>> with raises(sc.SpecialFunctionError): ... sc.spence(-1) ... >>> _ = sc.seterr(**olderr) Get the current way of handling special-function errors. Returns ------- err : dict A dictionary with keys "singular", "underflow", "overflow", "slow", "loss", "no_result", "domain", "arg", and "other", whose values are from the strings "ignore", "warn", and "raise". The keys represent possible special-function errors, and the values define how these errors are handled. See Also -------- seterr : set how special-function errors are handled errstate : context manager for special-function error handling numpy.geterr : similar numpy function for floating-point errors Notes ----- For complete documentation of the types of special-function errors and treatment options, see `seterr`. Examples -------- By default all errors are ignored. >>> import scipy.special as sc >>> for key, value in sorted(sc.geterr().items()): ... print(f'{key}: {value}') ... arg: ignore domain: ignore loss: ignore memory: raise no_result: ignore other: ignore overflow: ignore singular: ignore slow: ignore underflow: ignore PV1vSe1t1AAU'W,>e1 E&a QgQzvQ%Qa!! 1F!!-QfA X%\& XYl!6#/qa 1scipy.special._special_ufuncs_lanczos_sum_expg_scaled_sf_error_test_functionscipy.special._gufuncs_nbinom_kurtosis_excessscipy.special._ufuncs_struve_bessel_series_struve_asymp_large_z_struve_power_series_sf_error_action_map_nct_kurtosis_excess_ncf_kurtosis_excess_hypergeom_variance_hypergeom_skewnesscline_in_tracebackasyncio.coroutinesDeprecationWarning_stirling2_inexact_sf_error_code_maplog_wright_besseleval_sh_legendreeval_hermitenormeval_genlaguerreerrstate.__enter__V !X'vQAQ 1G'q 1_nbinom_variance_nbinom_skewnessmathieu_modsem2mathieu_modsem1mathieu_modcem2mathieu_modcem1eval_gegenbauererrstate.__init__errstate.__exit___spherical_yn_d_spherical_kn_d_spherical_jn_d_spherical_in_d_special_ufuncsseterr (line 82)_hypergeom_meangeterr (line 32)eval_sh_jacobieval_sh_chebyueval_sh_chebytRuntimeWarningwright_besselvoigt_profile_hypergeom_pmf_hypergeom_cdfeval_legendreeval_laguerre_cosine_invcdf__class_getitem___spherical_yn_spherical_kn_spherical_jn_spherical_in_skewnorm_ppf_skewnorm_isf_skewnorm_cdf_riemann_zetapseudo_huber_nct_variance_nct_skewness_ncf_variance_ncf_skewnessitmodstruve0_is_coroutine_invgauss_ppf_invgauss_isfinv_boxcox1p_initializing_hypergeom_sfgammainccinveval_hermitewrightomega_scaled_exp1pro_rad2_cvpro_rad1_cvpro_ang1_cvobl_rad2_cvobl_rad1_cvobl_ang1_cv_nbinom_meanmodfresnelpmodfresnelmmathieu_semmathieu_cemgammaincinveval_jacobieval_chebyueval_chebyteval_chebyseval_chebycbetainccinvImportError_set_actionncfdtridfnncfdtridfd_nbinom_ppf_nbinom_pmf_nbinom_isf_nbinom_cdf_landau_ppf_landau_pdf_landau_isf_landau_cdfkolmogorov_iv_ratio_cit2struve0inv_boxcox_ellip_harm_cosine_cdf_cauchy_ppf_cauchy_isfbetaincinvbesselpolyunderflowtraceback_smirnovcino_resultnewkwargsndtri_expnctdtrincnctdtridfncfdtrinc_nbinom_sfmodstruve__metaclass__mathieu_bmathieu_alog_expit_landau_sfitstruve0gammaincc_factorialexc_valueellipkincellipeincchndtrincchndtridf_binom_ppf_binom_pmf_binom_isf_binom_cdfstdtridfsph_harm_smirnovpsmirnovi_smirnovcsingular__set_name__rel_entr__qualname__pro_rad2pro_rad1pro_ang1overflowoldstateobl_rad2obl_rad1obl_ang1nrdtrisdnrdtrimn_ncx2_ppf_ncx2_pdf_ncx2_isf_ncx2_cdfnctdtrit_nct_mean_ncf_meanloggammalog_ndtr_log1mexp_lambertw_kolmogci_iv_ratio_igam_fachankel2ehankel1egammasgngammaincfdtridfdexc_typeerrstateellipkm1chndtrixboxcox1p_binom_sfbetaincc_beta_ppf_beta_pdfxlog1pytklmbdastdtritspecialsmirnov__prepare__owens_t_ncx2_sf_nct_pdf_nct_isfncfdtri_ncf_pdf_ncf_isfnbdtrinnbdtrik_log1pmx_kolmogpkolmogi_kolmogcit2j0y0it2i0k0hankel2hankel1_gufuncsgammalnfresnelerfcinvelliprjelliprgelliprfelliprdelliprcchdtrivbtdtribbtdtriabetaincA LcQstruvespenceshichiseterrrgammaradianpro_cvpdtrikolderrobl_cvnctdtr_nct_sfncfdtr_ncf_sfnbdtrinbdtrc__module__memory_lgam1pkwargskl_divkelvinitj0y0iti0k0itairyignorehyperuhyp2f1hyp1f1hyp0f1geterrgdtrixgdtribgdtriaexprelerfinvellipkellipjellipedomainchndtrchdtrichdtrcboxcoxbetalnbdtrinbdtrikactionzetacxlogyvaluetandgstdtr_sinpisindgscipyroundrangeraisepowm1pdtripdtrcothernumpyndtrinbdtrlogitlog1pitemshubergdtrcgammafdtrifdtrcexpm1expitexp10errorerfcx__enter__dawsncotdg_cospicosm1cosdgchdtrbinombdtribdtrc__all__airyeAcQ_zetawofzwarn__test____spec__slowsiciselfpochpdtrpbwapbvvpbdvndtr__name____main__lpmvlosskeyskerpkeip__init__gdtr__func__fdtrexpnexpiexp2exp1__exit__erfierfcentrcodecbrtbetaberpbeipbdtrairyA Jayvepsipopkvekeykerkeik1ek0ejveivei1ei0eerrerf__doc__berbeiargallagmyvyny1y0npkvknk1k0jvjnj1j0ivi1i0?.??lLX0:>;f? @h㈵>#B ;?@~¿п333333?-DT!-DT!?;f;f_@:0yE>0Cư>9B.@Ҽz+#-DT!@@@8@|@@T@x@@ A@^'ADAPAҶOɃ; ףp=.@Hz\/0xX>s :F^-@lz9~@wDAc;Z/@o)F@F"D@E؇.@ < @2 3¿mEN}yNtՓ @ x'1@+@ T?Q&^E?M5iPV?3?4" L)L>(V@8ҪMp @b*G?<_?Ƕ'|?)e+5?C>=kv)=>???        -DT! @-DT! \3&I)?$|=:Y;>pd·>Ƽִs+?tĔ??ޱ:I>6>73>Hg?4gG??Je=Io&F>̀4\WFT&?ꔔ?c8mۀPx>3 8M.7Nz?ʟ/п?hyp2f1psik1echyp1f1hypUitstruve0it2struve0itmodstruve0airye:exp10k0k0ek1kve:spherical_knsindgcosdgtandgcotdgComputational Errorspherical_inyve:yv(jv):digammahankel2e:hankel1:hankel1e:hankel2:jv:jv(yv):spherical_jnspherical_ynbeikerkeiberpbeipkerpkeipklvnawright_besselpbwamemory allocation errorpro_cvobl_cvn should not be negativesph_harmmathieu_modcem1mathieu_modsem1mathieu_modcem2mathieu_modsem2pbdvpbvvpro_ang1prol_ang1obl_ang1pro_ang1_cvobl_ang1_cvpro_rad1pro_rad1_cvobl_rad1obl_rad1_cvpro_rad2_cvpro_rad2obl_rad2obl_rad2_cv??w`wwvUvuuJutt?tss4srr)rqwqqplppoaoonVnmmKmll@lkk5kjj*jixiihmhhgbg gfWfeeLeddAdcc6cbb+baya a`n``_c_ _^X^]]M]\\B\[[7[ZZ,ZYzY!YXoXXWdW WVYVVUxǥfC֣i"H۠n53=ěKҚYؙW֘UԗSޖes<ϑbAԎg2Hӊ^t+A̅Wm&TGu ~:~}h}||-|{[{zz@z@z-DT! @  8)A0X"&w5BҎ7ħ*BR &ɑA`c@A?A@7AKAL漲Ax5%AЯ?K{$A@UzA!@zXATQT A?&A|LeA@g_UAd60k@`?@A0'h#A{@~?@c@^@n?@0@\?^@{t@J?8M@6?@ ????L? 1'?}"?O1?$$0a‘?Gg m?cjp?j-s`?nKP?TE1@?B0Ͳ 0?{ ?VJ?{ ?/L>fhs0>D7>J>fDY<>!>}f>]>Y>p>3V)`>P>Ev@>ZN 0>`4 >*x>-g?^r){?ɢW?[s?@⌒?3]u`M?&Y%?? gZQ~?'?'ΘH?S7C?P:?w~ ?*xnK?Ɲr?$h?zr?xG?b:?8ٯ%? ?%w?߄?8կ?8կ?߄?%w? ?8ٯ%?b:?xG?zr?$h?Ɲr?*xnK?w~ ?P:?S7C?'ΘH?'? gZQ~??&Y%?3]u`M?@⌒?[s?ɢW?^r){?-g?Ձ(u!HIᅴ>}!kg>M p7}m+Y>w@_D{fJ'/W翁ð)sTʵ俫+hMr7='Rh$Џܿy78-ٿxxտt#ѿ| ˿@qtÿLڷ]M(>؟]M(>؟?Lڷ?@qt?| ?t#?xx?y78-?Џ?'Rh$?7=?+hMr?Tʵ?ð)s?W?'/?D{fJ?>w@_?}m+Y? p7?g>M?k?>}!?HI?(u!?Ձ?W͇G?MH?O?+`?(ݼ?,i?ʁw0? }?NŒ&?oZ?"yOm?FT? ؎:?T ?_f/>o*m>:>ᄎ> *ɇe>榫ޔ8>>Mz(=o"f=~g=L >,=@N2P<`K{<9:Fe<(x%<;FbXH;M1t*;?,q#:dt:иrx:9  1@9 Eebo84FU}VRi? y~>;H"?ўRп-[?u rݝ)'?vGONxX=S?~D}Ƅ#R%>@@@@@$@(@2@$@4@>@@@ @4@        9-bؽ=y(Q˩W{K48))t>Ex$(>f>]06?9vO?%/%?cDxŻbty<# <'EѼ%XmCgb齘K:L>ͨlii!čBM&S>4.> ^<Ⳅ4hAJ@??{L?L+Hh# B~;&R>LmԀ>>q >n9>s}6?fO?%%?Js3u<^$=HMr<u,< @ 0=ᢋ#%7A%xrޤ=3ıHJsb8eE>Ka#/q&cQo>=|=>$2_V־a.5a;GU?Vۇ`?d&Q?H?\v?B?3ӻ϶?Nthԋ?-S?͢W?>ވ?Nb>Fk̶V=eP=*=C6r<};4ض\0;>3{:uB(!j9Ƞ9$8>Ij8^207l/W5?6VAS@5>@454ɮ;:3'q1Fp|0X.Z/4rEE.lƣ,i+=۾ !*5(„\FТ \<>|U} F>/z|2\Mfn> +n (4 нY6F\Gɺ=Ju>=}vYW=뛘C<6O ={Py¼|qMt:W^qqlZke?# oO9P=@4*?=@4ZJ>֫ >b |503>G> =nL0zI>{7:IX=NVNKC=EVP׽f1=TA=`̉ Xe=Q]z;UD,'\==x;dp?ȴڎ&eHI?F >3>%SC ?X9Tab>69f)>"*>l t$]oCsCN`SU:>8F)X|8t'p=rl=qxνYW"4U=`0n\9?s;_V_g`=a;9*u<{c=4;GE?Y_F.?ʷ>[1?]zq*N b=> 'o׾19 >@i2†MLu>'$;@]F=~F;SMhׇ=.(C4L<冠F?M=IkӎM:ύ^={ >LthI?z#3*Xi??nL>^|[<;=?]tqL }><3vƎj[QA=kJ0^>IxNv->^yp3PRaΧ=*ǽ<x3e=<炽wEa=R!I;](g,qŊ699H`G`s+2?'B * v$? >6̳?()>/e8þ Y‡\NPA> ;gˆ[ Z"0i>5ZA4;=bX:*+>Wpg- ڛ`b 1?Il>7[IE ` k ?L/8)w?$t*h]O]>7O5}Dl>K tP="SPwymwi> L3J}X8=p>qPw T'3=X;m˼ezqJU=!*U<{HNY=6?g4u ?ΘP85^n2?hsxB0>d&Ky}F> ->BYƱR*>c}`y4%.v\>ňNOM0>V-2Y_FbNҭ=vA:ӽwbJ}<$Rjy=4 ]bjs=D1bEp9K?aDg<0kgbmp%?ݧo ̓7F?y3>!J8Ps>0tK<pR>!;YH=9p>KPNj *Ud::ra ?703pc>ؑǾ'{P8>q9=ePӤ=w> 1 [y"eD[`0>OҺD"ܚT>k r ?ֽ?LjL=r1'EhU?lu]_Qi7+R?a並>2@E3,*裂= rX¾3qM>XMR C?U~H@Tr>cʝeH>{0HR<)}ձj/:>9F%7aZ<#{ s=YY??iD$M%?@^[$`Ara?L֏P6aZȚq"z:7?*t]q2ad?)ԇp8">jiMB >-b׾'#>T1VԲ>R · I|e>YNL*=W |/cbU>A8Q>57Ь >.J ޅ7k='ڥVp@Ji:z?^oPp͇Q¾Ma?0eX{#` dK?nMT>Y[>0gV{(?]"] UIAvty>̮-徺Ce>=!ll=NfJ >C>U0NU_%)XU>uH. +>Ҏ.;ICS|\xo>;A:U ?CI<05t?oY|>TF`L1\?-(`ű.Fv:R=T',(?OC!bwVA?L'+Q=]g40rv>VMg Ok7|M>>ZX2s>31<\I;].=> Pё?틎<>熔?G{>4HX\?'.v+Qph^? ɸ1$X۠1B?M>a"~?͠ VWsy>bWTӾ N(>+=Eݑ^Sh>YgUiTYĒo"A>\?4Td?F^I|^C?䢔x2׾S8?e:(l{2v?W?`>,]:\e5U? 0_O>H'齡E/?7ΠH>Ś}Zr=1&UU־=I>+CڶjnBލ,>=8'~mb>xP_h[ċ+?GB)oItz+?<÷Dc8/?лo>x{ ?,Ci{w$Ӕ$\PCZ?j=SM :?.8j1=k0DE|?bědE;@uSޫ>=moƾNt$>ɢUYKQ?,~8A&ž.co?~3 S?>ȩU%=iv;jzզW>H.k+.?g!9Ds ?Ce(?Fpſ鵱C?>B_'M>kxT?M:~x6߽QX?kp9+QюwJ7?NfEl=0m2Bc?] ?7GbT ={vP>?wս?|Fv uoD~@ٺ1W2 1X)tW?aj޺ ?@&T}пfXI?YNnf@٘?4y=m{3z?,=Ő|YjMQ?J7C-:=$Y?\|C B>y>*@B%%-غŃW3|w"@aJ$"n1M @oh#A//_@ Jf{gbz??uѿ4z3?Ķ >_+@?JTk)|x=֐"[?y,(R41O7?*'n2̽>?M1"`u[VGB@훵-&JQq@@-iOd?)c4W4@FMf$5VɖN@a 7fM?5\'s>VL&ܿvE?ϱJwA1?e)՗,M(rFw?I </~^rS?ߥ9`1xR@ LA,c`@t ?@ȋَ^X|ߞFb@heTgߛ[AbD@!kC>z!11@_ Ha>ʕ"w@JwA~=<`C5=c.?1QT!MܿgG?w-PyŎZ1ջ(v?|g=uV>o2d|ha?Kcj@Ru97*@ʹ}dEن@?#6"~gDuݬbt@X>`K~uQk*Hv~e@t=-ef"?y}TRD#BP@zrj@AM09@ڂ܅Fk@۶mc}:Q?Hn}@_fFX@cq=HÒ@m;[Ť?*@I3AkATp@]USŻ@$~K@Ҁ9 Z4AF#LA=wEgEZ3A˟=~X@"v4dja8@v1IA/1IESSXiA#e@E#RiA } [@:B]Z^t៤7Faďf|n>ƥRR/>qMX)?fFig#?,@ឌϥqX<&rͨA. TTioY>Tpt?A>B BY?O-iN@?¿rqGk~X X¿@9SsMԿ:(,a(5 F[t/!T ~z7o??98c?Hxi?d?_cJ6?Z> @Hn-@*S@Ҁ9}@v1@RmUamրVX>na>+A>Rx?I墌k? b?4!\T}b3<r넱^<"P '&&KF5=bLa$ӛ/=jz0 K5dMv;p>"c쑾$>'doҾY(X?>ZY&+|t(?RBuZ?I ^qa?!N-Ί>?-4pKw?Wӿ*5N?UUUUUU?llfJ?88C#+K?}<ٰj_AAz?SˆB8?:gG,2D*@%%cN4"@Jᦉ %AWBm3dҶAoFE%@y7TBz{ uoBSŮR9B.? * ?,|l @yD@:5/?@@R2B@96SC@wz*E@r4dF@OOfq]@Ob^@+NT_@ݭC#`@~{`@kbba@YSȐa@n b@1Ib@5ca c@c@ͦ3 d@\>d@nz e@s9Je@FGGʪ f@yyuf@IJC g@Y&g@oFh@·h@aQL i@ai@ F~x*j@&Pj@7k@!+k@VFl@ l@tVm@pZNm@k9ihn@HQOUn@a,~|o@b4nʼnp@+e Ip@cp@)Vp@*q@6Gaq@q@>m#FJq@FK.5r@b)C|r@Wrr@V] s@rRs@GIqs@ >6qs@jB*t@ A=rt@fIw|t@d'-u@X+{ Mu@# u@ZGDu@;#(v@b%rv@?ʿ?98c?ٿ?Hxirq?̄?d@x5?i&!@ffff?_cJ6<cVʷ(U@r^VlzDE@;:y?Z>j@BM09@؂܅Fk@۶mc}:Q?Hn}@_fFX@cq=HÒ@m;[Ť?*@I3AkASp@\USŻ@$~K@Ҁ9 Z4AF#LA=wEgEZ3A˟=~X@#v4dja8@v1IA11IESSXiA#e@E"RiA } [@P-X/gA=kbx&Az'E40E~AchFxBVwjA7Ww)\AA~ VtWN:@$XHA^@u.UgBKQv I8#B3'V=B >sE8>.?)+Z9?'.T5?U$2?h0?1o"-?ywg)?-'?[$?M eG"?tN:!??s??0W?@0?ߞeS?Fd?9߼? q?I.LJc?2j?7auXa@Lz@6kqKR3A&jzJCTW'HA:\b)"dq@^Lxoܱ(>'K > ^=>3P> MS|>{>`N>c3>fRU&>_[>N2&>t+>#p>->>]4>I>DY>~[>FXbt>?> nLB?f[=?$DQ2?&6}#?Gv,?{srh{> w=e[$|U 鴹 ӡj/W ȷ5ޓ\>O >/!&>7>@>I ]>.>^p>2I!H?[oL?=G(c53 '6 '(7W/)_6=HG3b_z1M-.9о(=R$wN9 )q>i_ ;\I^=}讶X?⾨GR>o8>QN'kh>nu>!r>PUe>Ҧ>j ~?2c]\cAmM ^7H-V/?IvO?B?V?7RX?-eW?WU?V;%A{R??YcM?\%F?9L??/} Q 4?ͤTM%?H?Ki 7z+^!G(!ۃ.'.61@6=|253}%~3 eL ho3+3 ꡗ2 t1[p'1|j(z?Μ? 4?I3g?%d(.0a*}wvywn=wЀ/@^lc|z ]qtf Pl.m`MH*t2?,6"+R?nT\?t˻a? -d?yzge?2Ze?(e?~[IPe?p.d?lb?Ka?Vz? `?R]?\U)Z?"9HW?߼xV4r%B6Nfj2eH%?F7`*0?_l[n1?| ˮ(1?w M0?3Ҁ.?,嵙[,?VO*?j(?R޾&?L7W%? H{b#?_?ڃj"?B!?DD5 ?eVӃ?Qgp? o 4?MJ?>Zo?#@l!Ƈcgb˔g`b"bpX4Ip2 _dbv ӌ~.J !RC/ p{QdJ U3_es`an_u{2"~nqkm쾬_W*,a| 49Pհ67$ w$U>}!?De%?ϻO&?Q$?@!?\ W?Nu?Hv ?cƫ?7f6?R?$K#N>y%uwB>S]F>i>IE">U-U>[+ZCƾ˛Ծ?{7ܾu{#dF=t㾩ACdɭ yCR羧SJc()龚l 8?bԉ*?3"^1F/D&O`4N֭4ؚMH2;V-8/~A&VDJt "@ B\iDLNnC^>ɑ`yC>vN?^A?X ?mIb ?Wn:)?tZ?jC=? =?l8w?lCd-?|_ ?Xn; ?90 ?e ?L%?`ٶFL_-qG?$T?#pZ?S>^?5ښc_?(9_? %]?:d[?>iY? V?bh"S?JP?Ւ&L?lvG?ZgB?'Q j@BM09@؂܅Fk@۶mc}:Q?Hn}@_fFX@cq=HÒ@m;[Ť?*@I3AkASp@\USŻ@$~K@Ҁ9 Z4AF#LA=wEgEZ3A˟=~X@#v4dja8@v1IA11IESSXiA#e@E"RiA } [@P-X/gA=kbx&Az'E40E~AchFxBVwjA7Ww)\AA~ VtWN:@$XHA^@u.UgBKQv I8#B3'V=B >sE8>.WFҲtrl <??98c?Hxi?d?_cJ6?Z> @Hn-@*S@Ҁ9}@v1@P-@$XHAW;Ay0y1jvzetakv:erferfcellpeellpkellikellpjlambertwiteration failed to converge: %g + %gjL}`ywzvvuGammalgamigamlbetaincbetincbigammainccgammaincInput parameter p is out of rangeInput parameter a is out of rangeInput parameter x is out of rangeIndeterminate result for (x, p) == (0, 0).Computational Error, (%.17g, %.17g, %.17g)`scipy.special.sph_harm` is deprecated as of SciPy 1.15.0 and will be removed in SciPy 1.17.0. Please use `scipy.special.sph_harm_y` instead.m should not be greater than ngammaincinvgammainccinvikv_temmeiv(iv_asymptotic)ikv_temme(CF1_ik)ikv_temme(temme_ik_series)ikv_temme(CF2_ik)ikv_asymptotic_uniformJvive:ive(kv):iv:iv(kv):loggammajve:jve(yve):yvyv:struvemathieu_amathieu_bairy:mathieu_semmathieu_cem?ox?-jCp^? #Q?@񚥿1>H(?`R}?I,SNO6,ڌ ?G<_P>lmf~D:>F{5>KLKv=EϠ =r} :BnHa=>017QxD\8<ؗҜ<fY?ӸS?\?gH>%?;ܩ?.vF?\v?SQO?h_ ?A]"j?"?(?\y-? C2Q?K/n+f?[m?saNh?Zy_W?Low?(s)?C?ș?Kݗ"V?AӔ?RfB?=LH?!?[LГ?D~?'ΧMs?c`?.2?xP?> ʑ? |"?,?a8??lq1?#L?+sV?Z U?N?)a?>?R0?VΓW?/x?i?? x.?F5r?)+Z9?'.T5?U$2?h0?1o"-?ywg)?-'?[$?M eG"?tN:!??s??0W?@0?ߞeS?Fd?9߼? q?I.LJc?2j?Q63E?' ?UUUUUU?aa?eM6d?0303п?^^^^^^O|K@-r%~F0@ D#*m5ATqz@HAc( -DT! @mBwE?wۆaR3?V :q?1-L?nG3_ 2mI?Yqٱ;$cV?1H_]8?}gcj?:p¿ ?IaʿH*2Q?ײ[դٿSbQ?G}g)@\AL(@+D@@\AL,@?JXT@-DT!?-DT!-DT!?-DT! @;f;f;f?;f??QK@?ͿŤ?dja8?u¿?h @??%?;@u<7u<7m0_?m0_?-DT!@@`D@n(N@Lv;@(UbAJVAِ OBY7=!B@@??@@@@?u<7~u<7~0.++0.++UUUUUU?UUUUUUe:;4V>l܍Ol\xO~>O[<;DgEZ> .!>LYɮº mF=t(:|t9=.o]0:3j=ke93*=keء9J0pRr%K*@{xD\W@@4:@s*_"@9˚?+Z?:r?;v?ҢR>R>޻%5?7d?4 : ? ?i~?x !A:?CP/w?`v2?NWi=O>u>@k+"@3@5ܧ~!/@y+N@?d"?kp?a?$E>z}x=ԉ=5>]}?~=_???3 /?@G1x?Y].?$>`(x-@1$%mB@ =w?@cQk%@z!?P$?5Z:Hv?c|Y?}MejZ>.$Z>[_5v\d?I~!JV? n ?n ? K#?PlTl?*$$*>?1z>lP> #@$G5@,%P1@@'Iqj?{Jx?+Ks? ?N> F^E_>~dȝ48>Q@X7%-?g(@ S@<@e@[4c@OLOOQ@M*\ ,@1Mb)?,34-@QM U@0-*f@ad@_ӑQ@ 1,@>LM?+gܭ}-@$T@əee@d+c@FA~Q@@j+@Ոҗc?~2\&@Q@2c@3 &c@/6+Q@y5N!+@mBP ҿ:  @Qg5п#rph?)υg2?x'*?X@ 95%@p @ڦ?ͺ-Vo?Ɇ3?{7? Qp?_ q?o)"D:>?<@ĬȎ?\?ffffff-@<@Mb? ףp= ?' ?Bп"@>@2@UUUUUU?NU/A@'K!ƄoZ__@'K!Ƅ@55@oZ__S?(@UUUUUU?r(?r(?=n=e?!3|@98c?ӜG@?ʿ?@@Q63E?-DT!??LXz뿪LXz?UUUUUU?@? C;fA\BzU@>Jz?Ȁ?3Ey?m0_促m0_?lV}?A@o8@_i>AC9@g66A4.4AID BF.r~BHB.{~AA\Cb4C9@'k;0J?]4? hN!?V z@@i~!@%6@7΀JN?TT?r?bG@!!@:Be9@J88BGt2:;? ,ύ3@mZ/MW@ 5f@-9zbb@UI@%wH@;s*@1/@ݡX3@T (/@n@Q63E?7t@2kAL(x?A+{lB- KC?esCėB+*C9)pvwC,A+]-@2r`H@elL,H?H?֖?j:r@/] @/@i=DB?HYݟ?P?QK@eݹ @ٴbG@@pk'?֏mƵ@gϚR@ Gyv@Pno6@ꫂ@ TL vj@wP`0R@o_ˁ@iz@р(@= =@b@!3|@M49@Yju@ŶbA!eX-bBT B7j@BM@09@؂܅@Fk@۶mc}:@Q?Hn}@_fF@X@c@q=HÒ@m;[@Ť?98c?¿rqGk~X X¿@9SsMԿ:(,a(5 Hxi?d?_cJ6?Z> @@< *I:.,i>&?A}|?tCrc? {u?6g?u<7~dg?ؗҜ<& .>A@y@@@Py@@O@@`~@@x@@P@@@A`@M@=@kym?{lj??Kap?%TӢ?++MJA?x/?QTE?5@CV4?d?V`V?͎T?n%`??=$|o?BC?wm]"(ȉ?_B??>īQ7?*TU?.@m%kW4?"߄#; 8? Hs9?:MIQ?bkϏ3?1?80@ v*9GqNo?yj?rh|/@=zhq>tR#>pȫSU?=zhqܾA@ᰟ4x>ZDph?Rh?i4?ڊe9@=hTH*D/X?j1Q?ʡ8@>Y[g2A?B@D@fF~byy??HLg?)]2?/$6B@^=e_hdF.?cW `?yS A@I@[Pܗ\O?'Ak`i?| g?hH@3sYX ? [u?ec]H@fA>&4a?U&?7̒@jMZ[@nh5V+b?Q?QKL@a>%ŽP?7{5?z&@tF_@ 5b`?|tް?~8gDS@D%H>@E9?*bmV?/r@`TR'Fa@Aҗ1?-T'?LX@&@Kϕ @->Ky?)N?\(a@Ahz$k?/(? ^@Ed\l>N_g?9v?mV}he@]应>C~&s$?-nb?s.Ue?Pn/d@ox2}j9B.?^^^^^^?eTUUUU?ox?)@u<7ffffffֿ+=x&1?Mb`?חAK͉ ?~, ?_6.>9d?t ?CQB' @U_SOxx%>4HBgɶT>I0 `{2"]>Rv o>H@3xsP@꺂5&?rY@ ! @@^@!<#pb@rqe@Vx?>qˤ[{@)n>R1xh!su> >V"Y?Eh &#@FDŽC.NϘ"AE!jMx?]75#@NV@5p@r5 .@4!R T@Vek@]Qs@fH> k@ - 4@DfD0N@R x<`^r!`^r!?So^ $?Vd?%ʁ?O H?u"?qyY?g?m4E[? ?q\?f+s1?l)OP?]"z?P̞J?5u+#Κ?97&$?VU%ߥ?.??H?m #"?z b?T?O0?^(|? [ϥYy?a?$5r֗?[?|8 ?o0>²龼M?''Ux?s?){?{מ?{"#??/??9B.?ư./Mѫ*=A29=ʳ !>ʸ^O~>ʌ>llV?UUUUUU??KNt3* Zbty@,@F@V@6@J@:@HzG?]tE]deM6ds?[e?O"_:?DgE>rqqqq|?llf?4V'?\@aa?j??<قnQ:Bp@A? ;p<]{IkY=#du= bR>t>UuWG?j/(9G?+]5cÉQ>²`G?fa?:Lf V>DiMNH?dgm??<㮸f\^=pS=竢CT>0^e>ssaH?`zT$t?J<`Mj`= j=K9U>^ >UTDUI?J I8{?xR22,<(=>R`=XA=k_V>5n7k>*(I?Vf0{π?*@vw U<Ga=yC˛=^W>W>lJ? e?Tc(<"b=eJ =HSK?zX>9s>J?|j?1@k=<߸6c=;~jE=3U-yY>a>LqpK?Fӊ?3@T H<ΔMd= =x=*G؃Z>`_y>z/L?ʙqO?5@hRY>0> tsguM?1’?HI% <ۥ`h=&û== U]>*4>: N?9罞?;@/tg" j>N?hj=?̢bnR)>q޿O?mx??@.7 h<2%m=$o=1`>>;>!P?}/|{C>BAȪP?m? T<qNp=D_TI=@yb>B Q>.UP?d$?B@EK_<.|(Bq=hN1o=qIc>TG |>[|OQ?]?C@;3^i>0⸻Q? w#v?D@6tG˰8b`>4H+R?_V?E@ s.b4<{-x{t=2~=-zh@e>qb>qʞR?D _?F@h<3u=@Hf&T=V:f>Fy#p>kS?uE?G@%fw_<^ Bv=Dtz3=|h><> \S?q?*,vX>T?DJ<[?I@W"ZB =y=Q=!VJj>Y>QT?|?J@z*=o^{=r,$=;?k> 22> "U?:=?K@:j%=r.m}=g>=cCl>g=>KU?UE?L@.%@ M==~=d=di=-Ek,n> c>`EV?qEn?M@k=E*Q= V=2Мo>n@>b[@V?|C2?N@P؀=EO=Xд=7ΐp>Vw5qi>.}W? n0?R87=\`d^=^N@)4[=REj^q>,ik4>*EPf&X?1?@P@+Ͱ=Zb}=7==ػ6r>2o >_i\X?pC?P@fIA = ,=_s=g=jX}xs>GkQ>wg:Y?A#1 ?@Q@Hms =i=t=9Uq t>M J:>1۩BZ?۲?Q@0ݭ =7ɏ]M=j>G" u>>pP %[?K?@R@\=~d=-y [>%v> zp>;:a[?-?R@$tIH= C=_Y>08w>*%>Cs3\? nm?@S@Ycr=H =:h>G!4fx>iJ>>>I}]?zqHV?S@ڤ=Hgʚ= 7/&>"|y>6ox(>1+b^?+E?&=?&0o=E>޾z>d>\aEP_?)(S]|>7d*>_[#E$`?G:?@U@z1q=Ylj=T2T>1^U}>C\>44`?U;)A?U@=q3ђ=XW/ >th>`(Q>>k},a?!qO?@V@w[=|F =,ΘF >VSg>z> a?`p-f?V@F=S\6=FI' >{f1'h>!L>bLb?s ?@W@l!x=i=$>'V>/L>칊b?F,?W@ƽW}=hI"=ln3>]R>G.Iݧ>Ӎpc?d?@X@P\v( =]Ia=-9)>Lvi]> q>_a.d??ÛԐ?X@[>!=϶ =DU/>>x>"l>aVd?JKT5?D*""=k=E>E4ͣ>Bu>iԕe?:?Y@1C2#=&8:W=^yk>d <>hN>, 'Uf?Yx?@Z@-]P$==P6L>MB1>'>vg?DD?Z@|^}%=ʘ=>k,>SF>Z0'g?v:}?@[@~&n&=*=)bBO>t >[1>Ԅh?Ⱥq?[@*=w(=L%Qm>'u">kS-3ii?Pr?@\@)x\)=z*]="%uP>0 I>T#>jj?V^?\@HVV0*=,G=#>=s>W\D1=?s(k?C7?@]@A-A,=Q7g=6ͼ\>!&!t>M?OjJl?9?]@Õ/-=TZ<=34NC >艄p>3L?[1m??~Ch/=ѫ= &=!>#k|>?On?írǶ?^@)܊0=iKγ.=;ј>\a@?ҕ"p?L(?@_@o'9nj1=D!Ƭ= ]#>c+ŕ>0!f?T:p?;?_@_mR2=6r=z8$> >5Y?҃V> %?`- r?y,@#?``@rU?4=+ =1Q '>ɮ>d?l8Mr?Q|I?`@gf$TC5=?=g(>Yhle8>1E ?! ts?.>>?`@P6=U4]={) )>[kYʜ>b+ ?\t?{? a@ t+g7=t=px-a+>''t>$aF ?yVw6u?xv(?`a@S8=[Q8=4鞈?,>z>H؍qp ?;Lv?n1?a@h[$&9=k e={nfP.>#, >F?z;w?]?a@y)y:=QjO=3;?0>.V> 6 eQ?hYX x?t? b@Ҫ<=6*=YXT11>NW>n_'/?' 2y?hJg?`b@Gɇ$Xb==$C=EE x12>qb->j[?2z?O^%4?b@w>=OP=5h?3> 'sX>` p?akBm]\{?Q-:X ?b@2@=4$=/m[4>Pn>ģ?Ƴ̕|?qS? c@V3@=|=j Au5>A(>pod2?*,-}?3?`c@o/'@eA=Ӈ#=cs$6>J:F>Y?Zz<?H?c@[Si+}B=", =|" 8># >R(/?BCU?"q?c@|R+B=!=aH6h9>򂒝H>C"?XΪ?>C9? d@lZ*C=X?zL=H:>R:7ot>T$$8??jC?`d@=8;XD=̷߫=JޒU<>$T~>+?8gK?>nf?d@eE==G=t<4=>٧ɺ>b00?>?D#B?d@ԾE=*=N?>A|̝>Wg?K])?Wy? e@<F=k L+4=Qb@>P>8mA ?a>Z?cj?`e@#~G=3K=(A>$2ų>6U'!?J%?Z ?e@3ŽMH=P==B> N>f"?l??e@Tm7I= _=C>>TM#?2ڈ?:? f@\U?I=gzA=.'2D>S0V>m6mT.$?q?\a?`f@5 J=LSNW}=#.E>}>M%?`?(Fa >@T~&?y??f@wLqL=`t=G>uO>xH'?[170?tڧ? g@ZGM=Y0!7= 2I>=5]s >do)? hc?.'V?`g@ÿN=+M=US}J>/ܦ>Co|x*?yЩ?X]Is?g@N=+x=MK>2؜,>2^h+?{n?+?g@dO=A\=v^t>M>鯂>㢬6-?.i?@w"0? h@'KP=y˵=[%wCN>>\oGr%/?^bd[?QH8^?`h@LP=$ζ=0EP>y|>c{p0?Jg[? ?h@gr/,Q=[Ɠ=1Jf3{P>}>NZ1?sj?D?h@yրQ=P S=~=( VQ>ƣ>ӉQ2?!@i?Qϣ0uI?ׇA@@33333:ffffffp{Gzt?{Gzt+?ykt?mBP ?p@Z3}+:=킙=AK >mo]}>XtA>(Wg?@9g?[ߺ>=JďB=lۄ>jjs>\ d> 5١g??d%B=hd=)i`>nw'g>}<>A\:`Uh?]1?\IE=K=T }2>= aM'>4kl>sh?30?`bcI=ĆfUİ=^J>"a>A|N>nYWli? N@?JID<#O=k=4$>2u'> o"C> j?huCנ?]<2R=*v?=xN >5>. jK>1فj?.Rb!?݊h j߶>d>Bj>IЅGk?4? HAxW<\=ҥ]8|q=mdʇ2#>],>#q>ܲ k?§?/>=lI'b=L=ie^%>[߼>SZ>Al?tg%~?0 =\F%g=Ј=,V)>t -Wm>ꊌywm?SsN? {=ݣucn=Yܒ=q%->j|O>g >?;In?ZZC?|zH=Ts=6Ү= 0>NKO>>}%5(o?zoٴ?WXhk#=(Vz=͍"[=o3>QD>v>Xh p?Ӷ?ߖPWX_/= Tp9=t\UZ=p}7>1H>@q?AGip?rܸ?Z6/a;=5b=2,=(<>e[:>l5?֍q?f?7Y!D=d|J=S5i=5=? A>4uy*>hWl(?LUQq?GV"?=D|h9X=K=z=w6F>R->_2W?wpFr?<a?jz]=8b=tp`=ق)M>4>H$?V}r?Q\S??At)=@s'=)`=ꌍ> N^S>2. >e?cOos?I^ s?AyG@8=JrlM]r=@ >v/%gˀ[>qm`j>/ ޖ ?#) t?_ Q? f'5=O&Hl,,=e6 >Sp==b>>߰?mu?e9r?5qt37=dd_̽NEG=9ne>0b>Kw.?c=`f>`>"+?"~prw?ro?\;%F=6nn$A=C9OHB=>}~t`>n>«!H?kTsx?L]=?)(C=@XeHĄ=Ղy=yJ)>?>s>RG7܋?C%yz?0~F?Vw3=[} = y=#6e0>6Tc\>.y>^؈S?YV|?;~G?5H=%d9=q=1z\ڎD1>q>RZ>µ ?JV~?c+?G% g7=98~֏=&FP=ն#->%|>?-4,>Ac!?aA?q ?J>{u?=H~u=!׏=gq2$>";& >$.>TMrR"?iXf? ? A==+!]L=_ =Po>̖s<>(TRbQ>1"?ݮ+?6gq6?TVVB'5=l@>)vEJo=v}]:>h8g>j&~Og>C ?»X?I0h?"QdR%=l.& =cFw >d>LIl>>"ׂ?y_?3Ϊ? Yn= Q=X9[c(>'~>:i>$*ϔb?`{?n)?%=7/Ä=-,ǽ=ϣa@->Xs[v>>6 ?TI?/H Y?O+(3"=o=c|=ԗK.>x{i>$f>OH>0gu?kֽ?\$=|0x=Y=CD,>DM>O]>eZ> ?M/I8&??"=Bl= Pe=5)>U]R>H=8>)T vt?z-hT?̗?J='(~eV=w5=UnZ$>펚Ng>8>QH?{DGʼԅ?rF?=h.1=wȶ=h'>>ob>hq>B>i4?!( ?_zm F?2' = ݔV=ztW=%>8*!Qu>I͹.'>;zׂ"?Px?=?<ܵ<.Zwc`=J_=9>=L5Fw>m(+>~%?mi*u?b?;--7c=S]u_==ai.x>6s>F(?}&q I?vL7?GPc=opq3@=( t=f^>Ìx>zqJF>?3g+?xR?4ƙw?a=q=K*7>qbIw> >;,?ӊp{?7Ty?γxI_=iD$h=]'M>q+u>=">Qmo7-?;[H&x?)R{U?gY=~ݠ=Q`؎ >ls> gn>DC.?j)A]t?]?jxT= wiŠ=to >*Fgq>lIb> .?t Up?MS?aaO=|BRUb=鲃>Sm>G@/lW>D .).?vB`i? \2?E|F=a=Q'>Lζ`ei>T> &-?8Fa?[]?fQi%==9=5g >r}Yd>DD83>$-?#RT?9{z?i40=X]=5{} >}_>%ʳ9>rap,?^!W :??"=z=0> a X>q:>ݱ*?/pR=WP>Kȿ>3JH)??z)T?ϐ%y?{$b4=Н=4a>YQX;E> p>Hu''?=\F6`?C_?tB ="0o5\= OJ=b5>.$B>tʆM'&?x^ue? p9?bI$={?^M=Ri(= />1*:^u>~$? |f>[wW"?ȸ2p?B)?d6'=CS=jO5=b6>%M">gD!?(]r?&?نvb'=r̽=z+Ѷ=6Y;@>|=ɲ>Q\?pa lt?3HZ9?.K&=h&<=x5zY= C>.!>6%H?Iv?lS+?Xz߹$=1eË=8k==KF>pkJ>DQ?ϟSw?GSt?P1"=Ĺl=~e=NH>s>|?֦ty?e$?pj =Oq=ѹaә=WNpI>/x߻>igZ?XD*Fz?0 ?C%=.=f=!fnJ>Y'.=>KPC?o{?`sN?3=g\Uy= _)@ Xp=bJ> >>T ?٣|?0?u K=:t=K^=`cjYkJ>Q>O ?h1q}?V?h1yZ=}MSo=Gxo<=Dr}I>tnH>:G*?A~?i)?;Da=KNh=\$:=*0I>'JzX=S?A,t?O\Ȁ?PC3t =Փa=A=JğGH>؆L#>EVt>?6%U?h=`$X=E.=3;>G>#>r >?@p?B8.<=]\ N=r٬>= e-F>*ήw>l >Pk\"?6?gL<ia9>=s;{=AD>-gL0 ǫ>O{5>%M:?o?`<fHK6w<>e-u>kI?z 0?H:<ˏ+?F(8?&=4B>}SFئ>śLр>L'M?j?7w<Ԯ:nwٜ=ɵ&'MA>Xߛ>">MI?cQF?o@C=4w=R@>W7>>l>0wO>? Ӵ?3g;G=^50 d=w7=>뤶#ד>>sX+?|?v%2J=*}=d;>k>AAͩ>X ??"g,L=sPq>qF?a; ,`?`YM=&DV =иLʜ7>8 $>Q*`>+_Ǣ?Y)?a2M=>`1=725>.O>L> 1S?$?]M=v8B=^R3>0Yg{> C >ݚ^~?4?:㴼M= =;2>\xަ>S>Y~?ٍ?(f$L=͞w\=gt0>?, K>+gXs>$<~?P>z^>}?a'E?@EJ=)&Dz=Е{Z+>K>JwOY> 2hsg}?(-?PI=)kaR=XP)>܈JD~>X>bc|?kXslZ?ތKH=&w=+:K&>4x>1>J|??z?P%F=ĺ=1Mȍ$> `ks>E9K>&P |?;?Q &E=m玄w=y">Hm>vL>p̙%{??pnLD=*\=)+  >/Ed>.3>D {? 3f8X>{Bc>\ Jz?w::Q?0>XpA=#f{&=ï>\YOE>]Y ~>R{-z?W?c j~@=s=7o>,Ɍ!>%>Cسy?;h;ư?4>=Q=s_>S~ K>d$x>G-M9y?E.? zg<=:x>RX=NF>"W>(0 %\>!sD`>nl1>FQ< Gx?Pwd\5d>[>w?>֗? >?A?ykt?Fׇkﴑ[?@s{B@|J?]ɭ1?f^?|=@@cAhW!?|a2U0?ۊe?&@333333@?Mb@?f^?UUUUUU?-C6?-C6>?@7y!C?N@V@?333333?A?+?0.++@Y[X?B9"@WR'@#}?x`? @?\0q@0yyu} @}<ٰj_SˆBAAz?#+K?88CJ?llfdg?wE?mBj@Hz>@vIh%<=E@m0_?W &?8,6V?iW @UUUUUUտ?WU?́R?-^OMX@VL@;+@t ҕE?@ԁ 5U@_6V.l@Si@ٷaT@cu/@~?Ϳ?' @ێ<8@yՒm?@BהL@N F@>F^-@lz9~@wD?Ac?;Z/@o)F@F"D@E؇.@ < @2 3?mEN?lL?}yN?tՓ @ x'1@+@ T?Q&^E?M5iPV?3?4" L)L>(V@8ҪMp @b*G?<_?Ƕ'|?)e+5?C>=kv)=>~ 9Ҥ?= ףp=?E<#E<@<;f@?>Ri?a@

lHE?|\pctx?zrd??En1???eAN]׽+h>'`v>&>-P?6)p+?o7=k6#h> g>(?Ҍ[?ef\r$>'`s??2E%?#q=jh{/Z*>)/ث>,b4?P, ?z @"f@qt?y`?c~{?u4?wvT @ml;@׹f?v!r?-x;|?G?%@5[k>Eڸkk>[/]2L?yVj?)fk?VS')?1rv?f;%? Q=> M?jAuMR?-#ʽP?wL~y?0zU&?t.ʢ>FF@>&ZMVF@>/]&-?HNj?0?yŇ?& }6?̲d> bR/a>^B/=r[?F*?[ ?o㫨7?2{> f1FHa>@.=z.=Q;=ʆ2P?uٖt%? ׮?"Yb"\?hK?=K>΢;wF>d]=7M?y8?^W%?^qHy-_?9"Y1Q?>oq<&>|X=cEI<Js3uA%?y?F]?*a ?ʬi?. V7?z ?Q63EtE X1@H տKR/@u/io@@apM@r3@o]s@zƴõ@K@u.=@X)@67Q& aB! FwMBͶ&B\C;3Aƃ]AA^nA wG""A$`u@Wk޺VBaX(BgKvA4Asf"qAwK!Aj&S@`DwQ:i@çh@oV`A7W AI:.LBDy^B˦BBZ@2C'CIF{5 vC@DMbqCj†{<^Ac"A7F z"B"Q[BU9uBvBMUF1C?22CTu`iC/+tCD^f8OC b?4ھcD}?h\Qa!?dn&?j[!&@'4z#@#+wa @rF?! #ך??4B?)m?N @oR7c!@#+wa @DTȥ?[a34@v{@<\%m@ /6@yPDs@yPDsqy O @D?yP>-u?4Yt}'@Izky@Jy@QEU@w^@ e7?@9v?4!\TT`ឌϥqX^>>s=cu.T?JUk?=!?f!?0@@;fq= ףp?-C6@ļB9RFߑ?=!>O~>ټ>G]lV?QUUUUU?=)Z>H}V>߿*??HUUUUU?f@U>Gase@r-YrI?|'k.?O&e?Řql?YUUUU?C4a@& .S!9$?S?W?#c?1}ܩ?97?zHs%)A?JP@r?[1?g?yW?‡B?Q:cCa>U >>q#??M;?cv߿t?Mt+n?Òekt?"mS?Of@FFg<AHP?ag>[54@剐s=AQ۔1A E:A u@W׉{ @Lt ACqb1AL/URCA^Tg *AJjK>A%m]LWaf3'PJ?C逵C?^ J?lf?KUUUUU?@0BH@?ffffff?G@R@}@w@P@{@@@@ffffff@{Gz?i@E@^ 9^;.ACd~QJ _B?ffffff?< ==MbP?ٿ?0.+_GaSe@?@ @St$?)@r@Q@(\?@wm0_???Vcb?)γ٢@õem_,С%A$FAz`A{4$Br2q@ڜB@и/SAQA"dBW$ςRBBs;aBb, jtb>B$E?YjV?7N?jh=uIt>Qǀ>2*>?qL?t0`? @#ё?^0[?}{嘇?p6?w5r>NHg`>I =YW5H=䩏-ZYR3H>a3=kl0=R#]< 6;Aa; c$?tg:?2T7?;HyjF?w%>`Mbz> =ˉf s=d=(tq|>AA:A&FA[@@A @@!A&@P@"@@@@A@@#A&A@r@@b@@Ь%AO`A (qAnIAۍPAA@@q@F[A@{AlA` kAjJAY1At@@p9AjAУAyAkA 5$A@A`-VA,AU@@xUA=yAAAӊAInAЬNA:@8DAhAWAHJA IAAAAd!A$@@@`@@tA@@@p4@:@@0vA@8I"AF*(At A@@jA`+%AϱXA=3jA@KZA&AAм@MDA`fA]AvAzAwA2t%AKA@ @` A AAA|ZAAlsAbA@MAqA`ǣA4A~ B'TAPuAA jAŅAro`A@9Ah2AUB TGB!GB1CB,{ЪA[AA@@z@|@PA@ @@@׎AYAS5AI>A*Ad@*@`GAtZAA@fqAphAzA7MA8i)A@`GlA@3'A)bA~AhAaAPJB|{oB`:!)B5eB,mPBP.2BGBA[Aq@px@Z@`An@@@h@A@@AA@@PAl8A|{`AQiA[ZAx.A@پAcAqAI-AOA`A0MAAA QA`yAƢA"FNAwAP QA4=A@5A%A0AkAA?A:wCAbUAP#ApAD%ALЯAAQ5B˪YcB*-xB#?OvBHVBXWW:BpD Bd"A`#At@A@zA"{ufBG&B$BX\B=N}BlB#zBV3B0B@AA03BB*0/qB(€B8PCqiiCPI- C@(MB@Uob1B]B@HB"ˠ)B@D(B@`@B]VBKdBХ@CO\_C>$|aCXͬC&Y3kk]ICc΁8ChC2FB_B,ADc}BE5B;`B`ե6%C{*5\C.ϐqElCp:FMCqoW^C&.iDC!.2C C"a/B+B "xqBx@rRBp_uB4Bp,s Hh0Cؠ)DdYCdC*M+uCv⬽ yCɞrCqWC@ZL&FCRb"CVYB7fB϶IBPmBB4Bі8^CXM 1CۿSUCϊ qCbCbWC: RIC5߳)Cxt C8GBgB!iBwr`Bx^Q@B CP42>C:K2]CwmxC oCPXCవSCoa2@$ ?s@_QPC?b@2Xf@@e@9B.@vH7B?"@'Ǹ?B?LXz?!3|2@88?O懅?E>D!@Y?@=:B@b{sh@20@KiZk@&'@Z/n'Ao);f]_A\o9A4͜A Bf0VJB FrB+HBGAIb/(BY7=!B.j?_"@_D@Hl@m(N@1s`-@Lv;@Wx+A?@B?Gbff6@= WY @~jL@($?1.?SbQ?6R?<? @c]@@@1 ?KH9h@' ?' ?@?E@mBP ?<~?<~ֿ L@fffff`@̬V@@T㥛 ?_vOn?0.;+:RFߑ?jﴑ[?333333@Ww'&l7}Ô%ITN~h}Ô%I&y3qh?둤 ??"??scipy.special/%s: (%s) %sscipy.special/%s: %sscipy.specialSpecialFunctionWarningSpecialFunctionErrorfloating point underflowfloating point overflowfloating point invalid valueno errorsingularitytoo slow convergenceloss of precisionno result obtaineddomain errorother errormemory allocation failedfloating point division by zero,c!fv:w1?[=Eb?DJ9?g|N?w N?#'8T?Pݜ?ޓ ?h%?PSz?F;QC?Ꞵu?@)>j?c23r?|{홐?MV.?ox?hj Vq?!Tk?˾$H?w@L]? 8%[kJOoK?0C`HԟJ?lfSUUUUU?0C?lf?O{\h?lv |y?{@?*Vy?ROCG@d.Z@P4@VB@uXdj!@fz|!#@}O@΋}O@ջ&nJ?.2C?9ӊJ?lf??UUUUU?R8ah|6?t3U?.`?q#z%?xn?/ ۈrh?vh?Vޥ ?Z^W ?ͨ'@ÔE@`9c@F`"5u@>|@^"Yr@)@t@S@N]Yq@j@jX/@~@%i"Yr@p@{,<:@΄j^5@FFߡ@oBP ?Ts׉W@ˉcg@FjD:X@ےk02@jBP ?F6?HŎа?@޲/4G@D d@U~ɀ@qy®@ȭRw @̾@;By8@;f@X_fA?ED6@5,!@ilm@d m`W@Ik@b)@'U@a>}@Õ-@]0@| @`ObS@o@[9@a_[9@t%w?B+?PT?SfN?Uh?zp=Ė?9,>?ONJW?}}Bn?m>ѺG!?bî0s?Fg\K?EÖo?h_d>s?T4?/?7Nt?T̝n? U8ήA?>'Cue?9KKS@s?ŭ?!-P?@Î?7`Ay?k?u?J_?|?;cJ?C?jHҟJ?ھlf?h}ɐ?Nz'@Ff)?*M?H?ʕUC?ԥS9?^?,耀E?uY?P 8*?zx?f9 @(u@-Q@? ͞u??qtJ?0u.#?̓ ? cs?$7}?R.R?Q?؍y?@?n}ɐ?(\ؿ= ףp=? ףp= ǿ ףp= ?`p?!_?|(Zxny?e ?OUUUUU?UE?l'eb?Q?Q?zG?Uk@Mb0?t^cj?I{sgC1 hA?6?`s+2?:9H`G?oŊ6?w#3thI?{ >L?][1?ʷ>?S_F.?4;GE?OC ?P>%?F >HI?δڎ&e?;dp?ZJ=@4>=@4*?% oO9P?Zke?qql?k:W^?R7U¾X?B'n'?,V7?t/R?k:W?ffffff v$?B *?> 1?I{sgC?vnL>??Wi?*>w#3?19 >$'o>N b=>q*>]?*>">'9f)> 9Tab>X>/0zI>犺 =n>D>w503>b >>֫ >ZJ>/z|2|U} F> \<>dFТ> AK֫>Ɣ">R7U> @+<+دQC?(/a?a>m??;f?kﴑ[?nQo~?*?^Ǚy@*]?IiU ?"[nr@Nnt c@.n9>ѝ@ J*@>Z> ּ)if@r3 `<@+<Q? _"#}?dyED<Jz5333333?P6?,VZΚ"@@nFFRV@NNK@`<@?Jz5?|=@0@@.1@3@@(@@@S@@X@x@@?:0yE>BT2?K~T-@^ r1?׳]9 A%tF$?4!K0WqĜ9>@@__5h!?_ SeB׳?ׁsF? @s IpĜ?Y\3&<_ .! C>9 @C:pΈ?@<FLXzK>7G.eB5<;?ý.@5?cܥL@+eG?std::bad_array_new_lengthSt20bad_array_new_length;dhv.cw.mxP/*z/z0.|1u|2~D33ـ3 4x555̈́\HrI Latud%54EUe,T$8L`4tT4 4\ t2T?$2Ah24A|2DP4F4I,54J6TK 6dMP6Np64N6N6tO7DQP7Qh7$R|7R7$S7dU 8dVX8$X8X8tY8Z9D[9\49\H9D]`9T^9_9_9`9`9b:cH:d`:ex:g:k ;k8;n\;r;Ts;s;Tt;u<uH<tw<x<x<yL=z=}>4T>Ā>T> ?td???$0@t@D@@ԇ ADA`AABTBdBԟBBB$C,C$pCCCtCDDDDhDDԷDĹDE,EPEd|EtEEEFh?$@BЏEdG(4I\dI$LԐdPtPXPlTYؑt[8i$xȒ4xDxtxTxįԯT<d|tDЗ0tXt44̙L4|ܚT4T$T Ȟ4(T%$*/</̠24ȡ5T=(D LdM $N,STXDZ$\4^x`4xTD,ḐD(tȨԥȪ0Ԧ`DĩHDxĮ0԰pԭ4Юd$@Txt|dD$X̳<d#\)$***|D++,.P00(01ؼd2t22x346 D78,8d;=?<$ATCE|THtJL0O$RTSatTDbDUbUhcbcdct4ddDdT epedfLf4.fDfpgDg4hT(h4JhNPiTfidyijk,kĊLk|kđktk4ldHll,m|mmtm nT nJGAE Hl Dq K K E @l( BAG L DBD ` AEJ ` DBJ xBBE B(D0D8Dc 8G0A(B BBBF ] 8D0A(B BBBF Q 8I0A(B BBBM H@uIBEB B(A0A8GPk8D0A(B BBBHJBEE E(A0D8E@w8D0A(B BBB8 L7BEA A(K0(A ABB8M0BLE A(A0(A BBBDPMBHE A(D08I@T8A0P(D BBBx|'BBB E(A0A8D@_ 8A0A(B BBBF _ 8A0A(B BBBG _ 8F0A(B BBBB \0BBD A(G@ (A ABBI g (G ABBE h (A ABBJ Ht`BGF A(I0N (A ABBC I(J FBB(hMBBD BBN\AZDQNBEE E(A0A8DP8C0A(B BBBP$DP,h,ADp, EJ N AI  D0r J fHBGF A(I0N (A ABBC I(J FBBHBGF A(I0N (A ABBC I(J FBB0dPBGF Ip  EBBF [L0N4{jD a`t5BBB B(D0D8G` 8A0A(B BBBF  8C0A(B BBBH HTPBEE B(A0D8Gp 8A0A(B BBBA `BEB B(A0E8Dpz 8A0A(B BBBG | 8F0A(B BBBA `fD ]0 L0`H !%HPd "P|"d#Py(# AD  AN f AI $P h%e|h%dh 8&Do E C E @&L`0\($AG  AG L AK NA)P \*P $$+ D@G E P H | -BBB B(A0A8I 8A0A(B BBBH L 8A0A(B BBBJ F 8A0A(B BBBH hl0SDN 0A^P AM 4P3AAG`9 EAH L AAJ (7DM G 7xD~ F o7xD~ F o(8\8ADD d AAA (d8ADD d AAA @d9BAG L DBD ` AEJ ` DBJ :D~ F o I L`;BGF A(D@X (L ABBK L (A ABBF LD;BGF A(D@X (L ABBK L (A ABBF L`<BGF A(D@X (L ABBK L (A ABBF p BPF A(E0M 0A(A BBBD  0A(A GBBO _ 0A(A BBBA  0A(A BBBG <PT]DKK C(A0s (E BBBA XQt BMF A(C0DV 0A(A BBBA  0C(A BBBE 4lQpAH@ EK R AM K A\ QLQ0QBFA D`  AABK Q$RR|E,R$@R?D J Y G a O ,hRD y C Q G  E  J $RAa4 AE RRD  K RDF }@S<BEA Gm  AABH G  IABA pLSBBA A(D`) (F ABBB h (A AGGA N (A ABBE D (F FBBA (S4D0] G  E m K ,SjH k E a G H H + M `TH< tBA G  ABBa  KBBAH  ABBP <T$ JA A(DF (A ABBJ LTxAD JBK JBBP ABK `UEA DpC AABAPpXpM  AABE LtU& BFB B(D0D8J 8D0A(B BBBG U"U[[ U"6r Tb I V#!n @ J ~b x0V$Z F H tPV%,dVZ xVQ2VRVSc| bLVTAS AH ` AG  AS  IJ  AK Wj WjP0@ H v B (@WmP@s E t D  H lWtPPx H | D W(z>Di@WBBA Di  EBBE   EBBA DWKPP\ IH ` IO p AG xPP IE <Q^TPHW A Y,tKPPi AK  PP BHK M ] C J(ȅ6ALGPI AAA @AID` AAL  IAZ L AAR @8LAAD` AAK  IAb L AAR @|AAD` AAK  IAb L AAR @ AAD` EAD d AAJ  IA^ 4ABFA Dm  AABB D<BLB A(D0I 0F(A BBBB D@HBLB A(D0I 0F(A BBBB ḊBFA Di  AABF L  AAFD 4_BFA D  AABE $LHR0A E L L eS0LtBBA A(D (A ABBA l (A AFBJ LĈfBFB B(A0A8D 8A0A(B BBBH $pH@s A  D  J 0<HR0b L i G L L H0PTpAA DHS  AABA L  AABH DȉlxBFA D  AABI L  AAFD POAF H  AABE L  KABN a  AABK ddp7BFB B(A0A8D 8A0A(B BBBK  8A0A(F BBBF L̊jBBD A(D (A AFBK ^ (A ABBA Xm8BEB A(A0Dp 0A(A FBBG D 0I(A BBBA |xo BKB B(A0A8Gk 8A0A(B BBBA  8K0J(B BBBE  8J0F(G BBBE D T$D TL(BFE E(A0A8G 8A0A(B BBBG ,xHPfXF`VXIPP E c E c(lH`hhFpdhA`T A g I ,Ԍ\PXXF`VXIPP G c E c(\`ZhFpdhA`P G g A ,0AJPkXF`VXIP\ AH ,`AJ`mhFpdhA`\ AH ,4\PXXF`VXIPP G c E c(\`ZhFpdhA`P G g A LHBIE D(D0GplxFuxAp 0A(A BBBG 8<ȜOG0T AE a AF  AGH0<xAH a AM T AC } Ab L AC 8\OG0T AE a AF  AGH0$H@s A  D  J L~BFD D(DpT (A ABBB  (A ABBD PlxOAF H  AABE L  KABN a  AABK TD BIC G  AABH O  AABE /  AABE 4\*AO AQ  AC O AH 4PTA^ EI T AK O AH 4#*AO AQ  AC O AH <15OG@O EF H EC a AN H@,3iAO AH O AH ,0BiAO AH O AH 4`TPA^ ED Y AF O AH (|*P E a A c E a0đ_?Hs G a E ^ I a A I0 `3Hq E a A Z E a A M|,HBJB B(D0D8Gp. 8A0A(B BBBI z 8A0A(B BBBD  8A0A(B BBBE H`BEE D(Gp (A BBBK D(A BBB,a| 8BJB B(D0D8Gp& 8A0A(B BBBA z 8A0A(B BBBD  8A0A(B BBBE `<45OG@O EF H EC a AN H@4d`AH0n AH E AZ M AB $V@u E L L eK@,@alAN0  AD V AI ,ptpV0Z H e C L L A0<bAL0/ AK  AD L AK T AC 0t,R0b D l D a G H H dE0(dBAH n AH U AJ @@DKG0E ED u AJ D IC LEGH0,e\AN0 AH N AA HLAGP@ ABI qEBHHPL EBE (f"AD0[ AO  AA P,(e BBA A(G (A ABBK  (A ABBU <D BFA C(D (A ABBJ ,.NNZ- ABA L VBBB B(A0A8G 8A0A(B BFBI L@fW`0` H a G Y0 E h E  E 8 E L E Pt BBA A(G (A ABBF ! (E ABBM < BFA C(Dz (A ABBH ,$p&0NNi/ ABI LTPVXBBB B(A0A8G 8A0A(B BBBA Dl`@` H a G Y@ E C E  E L E X]BJE D(D0Gh 0A(A BBBH c 0A(A BBBA HHqBIE D(G0] (A BBBA D(A BBBDpeALJ] AAJ  AAF # AAA 0ܙqbBHG J ABJ vABHiU BJB B(A0D8J` 8A0A(B BBBG \xq2EJ I YD|rALG@9 AAA  AAF X AAA 0ĚPqbBHG J ABJ vAB`wBJA D(G (A ABBE  (A ABBD [ (A ABBA \(q2EJ I YL|x}z BNH B(A0A8G ` 8A0A(B BBBA (̛pADG@i AAI L|BFB B(A0A8In 8D0A(B BBBA LH|qBFA A(DPa (E ABBG L (A AFBJ LLsBFA A(DPa (E ABBG L (A AFBJ p< BJB D(D0G 0A(A BBBE  0A(A BBBJ t 0A(A BBBD \t ptL0BBB B(A0C8F- 8F0A(B BBBB HԝPtBGG F(A0t (E JBBB R(A BBBH tBGG A(D0j (E JBBF T(A BBBllBMD D(G0T`[ 0A(A BBBK o 0A(A BBBA  0A(A BBBA `ܞhBIB E(D0F8Fpl 8A0A(B BBBA V 8C0A(B BBBA L@dBFA D(G@ (A ABBH S (A ABBG LBFA D(G@ (A ABBG j (A ABBH ssd\`BEE H(D0D8OP 8A0A(B BBBK  8A0A(B BBBI LpT#BBB B(A0A8GY 8D0A(B BBBA 4s0AHG0y AAE |8]@P8A04s0ADG0 AAE t8]@P8A040t+AHG0y AAE 8I@\8A04hu+ADG0 AAE w8I@\8A0DTAEDp@ EAH   AAE  EAM T>BFA Dm  FABA #  AAFA c  FABA @DPu G + U dD@C I  Y LL BNB E(D0D8G 8A0A(B BBBE HآuBED A(D@e (D ABBE r(A ABBL$`\ BNI B(D0D8G\ 8A0A(B BBBH HtuBED A(D@e (D ABBE r(A ABBL$hBFB B(A0A8J 8D0A(B BBBF HD$BKD H(E0E8J` 8A0A(B BBBA zPLRxs P$G/BBJ E(A0A8I 8D0A(B BBBA @Ф4uBBB A(A0GP 0A(A BBBC @wqBBB A(A0GP 0A(A BBBC (XyADG  AAD (@{ADG  AAD L" BBB E(D0D8N3 8D0A(B BBBA H- BIB B(D0A8J 8A0A(B BBBC LL6 BEB E(A0A8N 8D0A(B BBBA LD{6-BGB B(A0A8G` 8A0A(B BBBI (zPLRx%q `0- ,L},BGB B(A0D8GP 8A0A(B BBBD (zPLRxp P0 L,Ll0<,BKB B(A0A8G`  8A0A(B BBBA ,Q +Lh+BKB B(A0D8GP 8A0A(B BBBD +L@BFB B(A0A8GK 8D0A(B BBBA dPUBFF E(D0C8Gp  8A0A(B BBBD  8A0A(B BBBJ |L[ BJB E(D0D8G 8A0A(B BBBD = 8A0A(B BBBA  8A0A(B BBBG 4tg g*AC BJ. A X,>*BGB B(A0D8G` 8A0A(B BBBD h\pOhA`x%)\ l)BBB B(A0A8GpxWTxApS 8A0A(B BBBA (zPLRx9m p0k)HxqBBB B(D0H8Gp3 8A0A(B BBBA Hhs BHE I(I0D8Dp 8D0A(B BBBA 4\P~(AC Pc I ..\(BEE E(I0A8Gp 8D0A(B BBBH TxWZxApLLBFB A(A0G`hHpmhA`z 0A(A BBBK 4ȆAHG0 AAD G8I@_8A0Ԭ$X'ACG YAA`AYH0dBGE E(D0A8J 8A0A(B BBBE |G0|ADD ^ AAG UMF̭G(AAG\ AAI ,,(@$5TPDPlUGI,D T4}[ H ԮH,AG0 AA x AA PDpVAAG  AAC  AAA i AAA g AAA |D00WD0 AA @0`,b0B0D@ \ 4 1BEHP EBJ z FBQ 8XH@AF@X`@JEAq,D  M  Q L T l T ذy i4 a( xL H D B F H H H$8 D   H  I [ `ARS KG LBMB B(A0F8GW 8A0A(B BBBA (Ա 'AKD` EAM ,$AR0 AH A AN ,0 AV FI o AA L`$hAD@ AK u AJ k AL  AK c AL DD ACD` AAH  AAC  LAN 4nAIP AM a EJ  AE 80 BJD/ ABF V EBK (lh#D@\ H % C X H P(BLKi ABK U DBE X ABE  ABG @%H@ A  A&@V(BL@ I dHC}0[D`dD BMA G  AABC   AABD 4BMF B(D0A8G 8D0A(B BBBF D~BMB D(A0G 0D(A BBBC L̺NBMB B(D0A8G 8D0A(B BBBB LBMF B(D0A8G 8D0A(B BBBF li lK C(hBS  EE a BE <BMH A(G* (D ABBF (BO  EE a BE $P0y@@cBJJ Gt  DABH d  AABH @FBJJ Gt  DABH d  AABH LȼBMI B(A0A8G 8D0A(B BBBE (|xBG E BH ]B(DBG L BI ]B(p$BG L BI ]BxJBG ~B[ tA <ؽL6BMH A(G (D ABBK <LBMH A(G! (D ABBG X^a@`@z F @|BJK G  DABA m  AABA @T BJF G'  DABI k  AABA  '@< $ BMD A(GE (D ABBG P`?BJJ G  DABE   AABA d  AABD DBMF D(A0G# 0D(A BBBA HD(! AADp AAD <" ADp AB `.DP G |3D@g E \4 ADpX AB ?DP G EDxHs AMP EAJ E AAI K EAG d4TZgHE AK  MN pxx MS PHpP(b PP d  K x H hD e O | D d ikDE IC  MP x@s F_ PPxP(P4wDP a  G | L |}m AAG AAJ LWAT^thNSAdGGGFAMBGGGGQM ACD eIA`BRAzPpNtdBBhNdA]kBw X PPbDHm G E sGGGFBNBGGGGOmYBNBLV} F FVvh]TBZ`AQA]`AQAnV_jAwIANPbmAWA\WAX_ArhVTkBqLbtpD`pWhB`HP` hDpGhA`G D D L KpIhA`CpOhA`pKhI`hpYxAM`QpfhB`,lvDDD D(D0IR A s E DH G G cGGGFBNBGGGGO} H `YBNBLVCXvh]TBZ`AQA]`AQAnVjAwIANPbmAWA\_A`WAjhVDkBqLbtD`pZhB`HP`hDpGhA`H H D D FhDpOhA`~pOhA`pKhI`hpYxAM`YpfhB`\)p )<)X)t)))Ȥ))$)8L`$t  (<Pdxܤؤ0ԤDФX̤lȤĤ  4H\p:Ĥ $ 8DQPĤ dS R[ a O Z ,S R[ i G bgM m F XT U G ('AG  AF JAJ,( @$ T DQl( $V TV b N Z V TV j F b gN q A Z\V [ G (\PAG  AK ZA49H \ pDDD I8Dd H J F L N0PD J J L0PD8$Dd H J F L N0TD F J L0TD(D T@V x A _ J J0H D T0M8D@S E A f H N0|.AG0K8D@I  AA `A/;,/H=t/=(3<GP$Gd`HxZZ4@LXdp|,@Th|̱ر0"D"X5lH5t3DKZDIܲZ(DI +.`-`:.`-`/+`.`) `' `)`# `) `.`6.`(+`' ``# `# `# `x# `H% ` +`' `f,`) `8% `' `@`' ``,`-`-`- `(% `% `x" ```p```h" `+`%`X" `H" `$ `+ `p- `Z,`*`*`)`)`h# `X# ```8" `H# `8# `$ `@` `) `@`' `) `*`!`!`*`x)`(# `# `$ `h) ` `' `X) `*` ` `*`$ `$ `' `x' `h' `X' `H' `H) `i-`T,`$ `$ `$ `.`8' `(' `N,`( # ' `(" `*`' `" `& `" `*`& `H,`& `@)`d-`_-`Z-`U-`B,`<,`*`P-`2.`6,`0) `& `! `*`& `! `& `! `  `..`& `*`0,`*,`& `*` `$,`! `,`@````% K-`# `x& `*`@ ` ` `*`F-`,`h& `,` ` ` `A-`()`X& `x$ `H& `8& `8- ` )`0`*`(& ` ` `x ``h ``X `` ,`& `)``*````,`(- `)`h$ `X$ `+``-`-``! `)`+`.`.`.`.`*.`-`+` X=P=@= ==<<@<<;@;::h<pXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX<6FVfvƀր&6FVfvƁց&6FVfvƂւ&6FVfvƃփ&6FVfvƄք&6FVfvƅօ&6FVfvƆֆ&6FVfvƇև&6FVfvƈֈ&6FVfvƉ։&6FVfvƊ֊&6FVfvƋ֋&6FVfvƌ֌&6FVfvƍ֍&6FVfvMG4BH2XGJ3@@HHHI`I6Xe @0(% P. P6@H@@HIV0`0ivHH@LIL  H`OMo" +@??     / A T a m  GCC: (GNU) 10.2.1 20210130 (Red Hat 10.2.1-11)(P0*0,-b    x6 H  "@"X"`">@`G O Q<p`tb@b"?!Y@UzJ|p~-b0:@rp0L`fp`V` .@b0:pn Ffn& \   @p  *<   b  b{ ` S    M4 5x @=   G Z P1 9 BR    f\,BF H @HDH(:H%E VOPqHI)o{`G JIJcKpLpLE0N1NbPPtpRG0V&WAXTXr1w@wveC^7j0ř\']Pa!]BZy\v՛ac eJebef0gi[5`i{mipjjj5  m( nMofPp0qq%Bssptu .vpxpz${1|v`} p]PSVpxx )pE0_Џp@o=P{09jPp8O)hТp@ `  l9 e P @ q `}.!`!!`!0!/"c""""/#pd#P#@# $0 3$@f$@$P$P$P3%`h%p%$% %P&@@&M Y&&&&.x& ' %+' U''", '+$"'x(pR(Gk("P|( (`L (G (]( ( 5 ) ) ;) . H) P) X) *h) - v) ~)ح)Э)ȭ9*x***6+v+++4,t,x,p,h1-`r-X-P-H6.@z.8.0/(F/ //0W00011s11ج1Ь;2Ȭ{222=3}333?4~44x4p?5h5`5X 6PY6H6@6870]7(7 78]888-9s999ث7:Ы:ȫ::;;y;;;4<w<<<x9=pw=h=` >XH>P>H>@?8>?0{?(? @B@@@A@AAAAت:BЪyBȪBB6CyCCC@DDDExpupPp p-q`jqq  q@"r_r r rr4s0vs` ss@9tИpt t tup Hu |uuu v@ Ov`v vv ,wgwwPw xPx`x  xx)y@_yy y#zdz0z` z{@={Еs{ { {|pG| z|||}@ W}`} }~ @~{~~P~ !X`  @1g Ӏ @0w` @ Mؒ 1ВvP : s` #  \@х  E @0& \p0ɇ 8p@0 ۈ pI ljFɊ Op`ҋXX@8ٌ0P]  0Nh Ў 0FPy 0ݏp BЍu@ ې `B tۑPD w`  J@ %^0Δ` <@s Њٕ  @ tpߖ@ H} ` N P`M  @M ` M0@ ЇQ  p$Z@ Ɲ 3`j ԞІ ?  t @ ݟ`@E y @ ` J @`  @P@   !@T` 0@ LЂ  PP(&`(_ PϦ((@Ȁy@P((!Z`P (ɨ(;~x~P@~(~(,}Ph@}(}(}!|Y||̫}|B|||{4 |Pk{(|(ܭ {Pz(O{(zŮ@zPz(8z(sy`yP y(#y(_yxPհ@x(x(L(xwP±`w(x(90wuvP`v(w(,Hvj0vv0̳uu /u _uu´pu@u %uX u`ut t!tSut Pt`t%t[ t st@t s Qsss`s 0sO@sss rrO sr prrrP@r  r0r`rq@Kr q q q `q Mp q@p ppLp`p 0p@p%p]p oϿo pBo tooopo?@o0m oo n n4nhon Pn `nBnz n nn @n?m rm0mm@m0:pmnm  ml0l;lnl `l @l l>0lsl k lkDpk xk kkk F@k y`k kj jOkj j `j,jdPj  j j@j>i uii iiB`i w@ii0ii Ph ihph*h ^hh@h  h,`h_hg gh4gkg `gg Pg@ g tg@gff Hf|ff`f @fGfy0ff e fAete0epe e=@e o`e ee d :elddPdd 3df`d d @d dCc}c cccR`c cPc@cb Ob@ c b @b@b Jb | b a0aaIa ~@a0paa aS`@p`` ` @` Q ````_ _R`__ `_%_ZP_ _ _@_+_`h^^ ^@ ^ A ^0oP^] ^ MhG)@H@BH[`ItL LP .   , " @ W w  . + . . - |. , x.  . , ,* +9 +H t.T .a p.m .z H$  . (  (  p* (  "  8$  + ,! & 3 % E % W % i ( z + (  h* `* ($  $  - , +  + X*) +8 % J % \ ( m @   - , $  (  , , ,  , h.& +5 # H +W % i +x + %  (  P* H* @* 8* 0* ,  - b.! -. (*> ,L -Y +h ^.t , (     "  "  "  " , D ] ! r  "         `) x( : % L - Y -f ,t - - , , - + x%  - , , h(  *" - / ~,= X( N h% ` ! u "  * H(  - x, + + |+ u+ p * ( *8 8( I )Y (( j r,x n+ g+ `+  `  !  `3 Y+B .M Z.Y .d V.p (  R+ -  x! #  h!  X! H! 8! )) )9 # L K+[ l,i D+x =+ (!  X%  . (  #  R. . . .  . N.! ., J.8 .C F.O B.[ -h 6+w >. - :. - /+ . )  '  ) #  )  ." 6.. (+= ' N n #  #  #  x#  H%  + '  f, )  8%  ' - @G ' X `,f -s - -  (%  %  x"    p  `% h" 9 +H %Z X" n H"  $  +  p-  Z, * * ) ) h#  X# " `A 8" U H# h 8# { $  @  )  @ '  )  * !. !C *R x)b (# u #  $  h)   '  X)  *     */ $ A $ S ' d x' u h'  X'  H'  H)  i- T, $  $  $  . 8' % (' 6 N,D (m # '  ("  * '  "  &  "  *# & 4 H,B & S @)c d-p _-} Z- U- B, <, * P- 2. 6, 0)  &  !  *- & > ! R & c ! w   .. &  * 0, *, &  *   $, ! + ,9 @X ~  `% K- #  x&  * @ 8 R q * F- , h&  ,    A- () X& ' x$ 9 H& J 8& [ 8- h )x 0 * (&    x   h  3 X H _ ,m & ~ )  *     , (- ( )8 h$ J X$ \ +j  - -  !  ) + . . . . *. -' +5`O CM0Y @w   0R4pRG|kVo0X0l:XqYm`Z[#Q0\a ygq k v  `ul ( }C ~^ @Hu p p  @yPx  pX* @qXL oi r q d` : Oh `Oh NhO `Nh `P   L"? ` G @G FH `Eh Dh' EI @:4m<h L J @K I  `=3  `tP  sm  p   `d  A  @C  @9  `>Y x      P"  X=B  P=b  @=  =  =  <(  <0  @<8"  <@B  ;Hb  @;P  :X  :` 0" ?@ P  P    O+ X"R ^ @"}    0  `00V"(0/,: A01HpUq\byh`mrp'` @hp  n P  *%  ,&%P-,`.:@/ H`9Q OCEbuOz  D @$p `e C @ 7+h<H`Sp xx}/@'?pV/ p;!-p;`I _*@`i "P!/P 2,< JE~Si}I jUF hP`  P# )Fu2 lvp }"u, H0hVbnl 0 `PAy``F@  %EQ, `O0@ P0I` й>b3% X  Y x Jh\xDQhXpe6 ?z6ФpUFЭP;*SV5G d^`3fI)^0Jvp "UvX1?@X W aC @;  ?`I`>)*6@ LVep {@h@`0Ф3+; .'pP h_@  k(3@ep`0 ,ZC0L^X|j@|@Lx  Pm- 7@'-6@)A[Vp)a k 8  3" 6` > 8M+BV! ya R ?s @:О@JRp0B6{H| *d`n z pPgPP09`"P4W 0n.  N D  W j ` =    = 0  % X!p! 9!! D!@HL! r! B|!pr!4!@ !Љ ,!p~"E"PF%"1")>"L"JZ"o"@z"P"`"0j"`"p"p|C"p"Ц"0 )#NE# ] f#p%M}##P#p  # #w# # #$X$p=$` pi$Abv$v$$ 2$$$z$ $Q)$0 %G%G%%O/%cA%pO z l%Ю%pa%0 ! %PB2%m% % &0& R)-&;&0T&0 ~& &P"&j' 'P)' ' .' R'gg''4''`'pQ1'=(` (%(Х-(0B(,I(s(p ((*(PR(н(p](M(0(F)  )x*.) PW)e)С)o) N})))`yg)")+)Pg)X)j6)P)m* *e*); +*K* ]g*0q**s*P*y_*P'*p*@*Ah++*%+pH)1+;+I+@W+pb+`m+ a+P 5+0+@+0 +`{+O < , +,n52,u H,0 x_,Vi,,`c,8 ,`,,9,0 Q -0-` hM-P x-A -f -@O-u & .!.+:6.~ Z.0 ..]g.Bb.0. ).L6. ./R/{)/Ы 5/!L/\/ym g/qq/S/H /j/mn/ / 0@0@ !D0pN00Z0g0 0B0<0" 0O0:0z0 1@J01Pw1(1P 51 N1`LZX1 =c19)o1<(11n 1P{s11111 =1p2 d>2 DH2c?_2H 2p 2P2/2H212N3p3p3?+3h>3pp X3d3`q3P _30~_33p303`d3Z 334  )4 \ T4У]4 $4@ '4\4p`O444<4 5H'5)25k5550$25 # 555x5 646p!G60eo6p}6G6Pi6r6660Z6z6 V!7p+7Za:7; \7y|j727N7@D7`757PV7p; 70w8, p807&8`-868V8`Gl80~8@8p8W8@d a8Z80 >8xe8в99iQ9P`9p%$l99949 _9Z : @: a:p ::O: : p:Z:N::H):0:pp ;@ .3; G; R`;`t;;@c;` ;l?;Шg; Sq;;pa;6;`d< `<< ,_<pM jv<+,<^<+<p,<P <i<M=f s4=>=Z=E e=@=Ѐ =-= ?m=P=  >0>,>0{ g>cQz>0: U >@>p>@>`>U > ?n?{h'?p0?9?pxE? d?05s?p ??p,l?P]?m ?2?@ #@)%@0z4@ >@L@7X@`c@P7y@`!@} H@0@ @@PG@ G#AR XA AcAjA` aA}OApn B1 8BHBUB'cBZBpx(B0b,B)BЏ e Bpm BB% $ Ca -C TC*CpI C@WCC C<C VD b'D GDZQDN`cD@"~Dp DD _Dq DD &EREЫ`E yE`c E06EP[EPE` E`E 0FL+F$$Fur2F@F`|FxF0s;F eF`F1\F)F@WFа G08GBG5 eGoGxGG}G@GC2G@CG:)G*G -H8H dHH H  H H I i(I AI 0N,LIpK0VI w~I I5I IPIиIH)I0I*IKJp3%J.;JHJ@ 2\JPRqJ. 8JhJpjKp+ K"K, LKQ1aKм?oK \ KKKKKKKKLL0LBLSLhL{L[LZLLL[LLLLM M7MFMOZMmMxMMMMM MMNN(N9NHN"dNqNNNNNNN1ZO(O;OJO]OlOOOOOOOOMRP!P;PKP_PvPZPPPPPPP QQ-Q>QKQlQ^SQQQVQQQQRR+R6RLR^RlYqRRRqSRRy]VRRRR SS6SIS]SpSSSSSSSS TT)T.0@0H`G`7  O?a 0?/8? `  X9]$$.o(($8 PP80@00TGNUmd8(IZ%>  5   | V D;V ] t   g j  u   p x   F"6G    + UUt    h y  $  [ 8 t  d@Lq k 8K   @j? &-  % q v mo e    d 1 j   "  - ^ d          }       Ct- ~ 6 P  W   |  Q   ow  l Q  F      e p *  `4  T1  j   W  F < w     !"      b  $) bU , E d  ;  6  XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX;? N X f p @"X"o(0P T @b-5 o0,oo*o__gmon_start___ITM_deregisterTMCloneTable_ITM_registerTMCloneTable__cxa_finalize_Py_NoneStructPyDict_NewPyUnicode_FromStringmallocscipy_dstevr_freePyExc_TypeErrorPyErr_FormatPyExc_SystemErrorPyErr_SetStringPyDict_SizePyObject_VectorcallPyUnicode_InternFromStringPyUnicode_FromFormatPyList_New_Py_DeallocPyObject_GetAttrPyExc_AttributeErrorPyErr_ExceptionMatchesPyExc_ImportErrorPyErr_ClearPyModule_GetNamePyUnicode_ConcatPyImport_GetModulePyExc_DeprecationWarningPyErr_WarnFormatPyTuple_NewPyDict_SetDefaultPyBytes_FromStringAndSizePyBytes_AsStringPyUnstable_Code_NewWithPosOnlyArgsPyObject_GetAttrStringPyDict_SetItemStringPyThreadState_GetPyInterpreterState_GetIDPyModule_NewObjectPyModule_GetDict__isnanlog1pexpm1__isinf_Py_FalseStructPyObject_RichCompareBoolPyLong_AsUnsignedLongPyExc_OverflowErrorPyLong_TypePyErr_OccurredPyMethod_NewPyTuple_GetSlicePyTuple_GetItemPyMem_MallocPyDict_NextPyMem_FreePyErr_NoMemorystrrchrPyImport_AddModulePyDict_GetItemWithErrorPyType_FromMetaclass_PyObject_GC_NewPyObject_GC_TrackPyDict_GetItemStringPyCapsule_IsValidPyCapsule_GetNamePyCapsule_GetPointerPyExc_ValueErrorPyList_TypePyTuple_TypePyLong_FromSsize_tPyObject_GetItemPyNumber_IndexPyLong_AsSsize_tPyErr_GivenExceptionMatchesPyExc_IndexErrorPyGILState_EnsurePyErr_WarnExPyGILState_ReleasePyObject_CallPyErr_SetObjectPyException_GetTracebackmemcmpPyObject_HashPyUnicode_TypePyDict_SetItemPyBaseObject_TypePyExc_RuntimeWarningPyCFunction_TypePyObject_VectorcallDictPy_EnterRecursiveCallPy_LeaveRecursiveCallPyImport_ImportModuleLevelObject_Py_TrueStructPyObject_GC_UnTrackPyObject_ClearWeakRefsPyObject_GC_Del_PyThreadState_UncheckedGetPyErr_PrintExPyErr_WriteUnraisablePyException_SetTracebackPyExc_ZeroDivisionError__finitePyIter_NextPyExc_RuntimeErrorPyObject_GetIterPyExc_StopIterationPyMethodDescr_TypePyType_IsSubtypePyCMethod_NewPyFrame_NewPyTraceBack_HerePyCode_NewEmptymemmovePyMem_ReallocPyObject_SetAttrPyArg_ValidateKeywordArgumentsPyDict_Update_PyDict_PopPyDict_ContainsPyObject_GenericGetAttr_PyObject_GenericGetAttrWithDictPyExc_NameError_PyDict_GetItem_KnownHashPyDict_TypePyLong_FromLongPyObject_VectorcallMethodPyDict_Copy_PyStack_AsDictPyMethod_TypePySequence_ContainsPyObject_SetAttrStringPy_VersionPyOS_snprintfPyUnicode_FromStringAndSizePyUnicode_DecodePyType_TypePyTuple_PackPyImport_GetModuleDictPyImport_ImportModulePyExc_ModuleNotFoundErrorPyCapsule_TypePyExc_ExceptionPyObject_IsTrue_PyDict_NewPresizedPyObject_SetItem_PyDict_SetItem_KnownHashPyInit__ufuncsPyModuleDef_Initcbrtsincoscabs__muldc3fmaclog__divdc3csqrtcexpfmaxccoshcsinhatancsinfmin_ZSt7nothrow_ZnamRKSt9nothrow_t_ZdaPvfrexpldexpacoslog10fmodasinhasinccosroundatan2log1pflog1plmemset_Unwind_Resume__gxx_personality_v0__tls_get_addrPyOS_vsnprintfcpowfacosfasinfatanfatanhfcpowatanhcpowlacoslasinlatanlatanhlcabsfatan2fcexpfclogfcsqrtfccosfcsinfctanfccoshfcsinhfctanhfctanctanhcabslatan2lcexplcloglcsqrtlccoslcsinlctanlccoshlcsinhlctanhllog2hypotlog2fhypotfmodfflog2lhypotlmodflexpm1fexp2ffmodfexp2expm1lexp2lfmodl__popcountdi2__cxa_allocate_exception__cxa_throw_ZNSt9bad_allocD2Ev_ZdlPv_ZTVN10__cxxabiv120__si_class_type_infoE_ZTISt9bad_alloclibscipy_openblas.solibstdc++.so.6libm.so.6libgcc_s.so.1libc.so.6ld-linux-x86-64.so.2GLIBC_2.3GLIBC_2.2.5GCC_3.0GCC_3.4GCC_4.0.0CXXABI_1.3GLIBCXX_3.4/opt/_internal/cpython-3.12.11/lib/python3.12/site-packages/scipy_openblas32/liblibscipy_openblas-b75cc656.so$ORIGIN/../../scipy.libs