`L iMddlZddlmZddlZddlmZmZddlm Z ddl m Z m Z ddl mZddlmZd d lmZmZd gZGd d eeeZy) N)Real) OutlierMixin _fit_context) check_array)Interval StrOptions) available_if)check_is_fitted)KNeighborsMixin NeighborsBaseLocalOutlierFactorc peZdZUdZiej edheedddgdgdZe e d <ejd  ddd d d dddddfd Z dZ ee ddZedddZdZeeddZddZdZeedZdZeedZdZxZS) ra Unsupervised Outlier Detection using the Local Outlier Factor (LOF). The anomaly score of each sample is called the Local Outlier Factor. It measures the local deviation of the density of a given sample with respect to its neighbors. It is local in that the anomaly score depends on how isolated the object is with respect to the surrounding neighborhood. More precisely, locality is given by k-nearest neighbors, whose distance is used to estimate the local density. By comparing the local density of a sample to the local densities of its neighbors, one can identify samples that have a substantially lower density than their neighbors. These are considered outliers. .. versionadded:: 0.19 Parameters ---------- n_neighbors : int, default=20 Number of neighbors to use by default for :meth:`kneighbors` queries. If n_neighbors is larger than the number of samples provided, all samples will be used. algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto' Algorithm used to compute the nearest neighbors: - 'ball_tree' will use :class:`BallTree` - 'kd_tree' will use :class:`KDTree` - 'brute' will use a brute-force search. - 'auto' will attempt to decide the most appropriate algorithm based on the values passed to :meth:`fit` method. Note: fitting on sparse input will override the setting of this parameter, using brute force. leaf_size : int, default=30 Leaf is size passed to :class:`BallTree` or :class:`KDTree`. This can affect the speed of the construction and query, as well as the memory required to store the tree. The optimal value depends on the nature of the problem. metric : str or callable, default='minkowski' Metric to use for distance computation. Default is "minkowski", which results in the standard Euclidean distance when p = 2. See the documentation of `scipy.spatial.distance `_ and the metrics listed in :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric values. If metric is "precomputed", X is assumed to be a distance matrix and must be square during fit. X may be a :term:`sparse graph`, in which case only "nonzero" elements may be considered neighbors. If metric is a callable function, it takes two arrays representing 1D vectors as inputs and must return one value indicating the distance between those vectors. This works for Scipy's metrics, but is less efficient than passing the metric name as a string. p : float, default=2 Parameter for the Minkowski metric from :func:`sklearn.metrics.pairwise_distances`. When p = 1, this is equivalent to using manhattan_distance (l1), and euclidean_distance (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used. metric_params : dict, default=None Additional keyword arguments for the metric function. contamination : 'auto' or float, default='auto' The amount of contamination of the data set, i.e. the proportion of outliers in the data set. When fitting this is used to define the threshold on the scores of the samples. - if 'auto', the threshold is determined as in the original paper, - if a float, the contamination should be in the range (0, 0.5]. .. versionchanged:: 0.22 The default value of ``contamination`` changed from 0.1 to ``'auto'``. novelty : bool, default=False By default, LocalOutlierFactor is only meant to be used for outlier detection (novelty=False). Set novelty to True if you want to use LocalOutlierFactor for novelty detection. In this case be aware that you should only use predict, decision_function and score_samples on new unseen data and not on the training set; and note that the results obtained this way may differ from the standard LOF results. .. versionadded:: 0.20 n_jobs : int, default=None The number of parallel jobs to run for neighbors search. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. Attributes ---------- negative_outlier_factor_ : ndarray of shape (n_samples,) The opposite LOF of the training samples. The higher, the more normal. Inliers tend to have a LOF score close to 1 (``negative_outlier_factor_`` close to -1), while outliers tend to have a larger LOF score. The local outlier factor (LOF) of a sample captures its supposed 'degree of abnormality'. It is the average of the ratio of the local reachability density of a sample and those of its k-nearest neighbors. n_neighbors_ : int The actual number of neighbors used for :meth:`kneighbors` queries. offset_ : float Offset used to obtain binary labels from the raw scores. Observations having a negative_outlier_factor smaller than `offset_` are detected as abnormal. The offset is set to -1.5 (inliers score around -1), except when a contamination parameter different than "auto" is provided. In that case, the offset is defined in such a way we obtain the expected number of outliers in training. .. versionadded:: 0.20 effective_metric_ : str The effective metric used for the distance computation. effective_metric_params_ : dict The effective additional keyword arguments for the metric function. n_features_in_ : int Number of features seen during :term:`fit`. .. versionadded:: 0.24 feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during :term:`fit`. Defined only when `X` has feature names that are all strings. .. versionadded:: 1.0 n_samples_fit_ : int It is the number of samples in the fitted data. See Also -------- sklearn.svm.OneClassSVM: Unsupervised Outlier Detection using Support Vector Machine. References ---------- .. [1] Breunig, M. M., Kriegel, H. P., Ng, R. T., & Sander, J. (2000, May). LOF: identifying density-based local outliers. In ACM sigmod record. Examples -------- >>> import numpy as np >>> from sklearn.neighbors import LocalOutlierFactor >>> X = [[-1.1], [0.2], [101.1], [0.3]] >>> clf = LocalOutlierFactor(n_neighbors=2) >>> clf.fit_predict(X) array([ 1, 1, -1, 1]) >>> clf.negative_outlier_factor_ array([ -0.9821, -1.0370, -73.3697, -0.9821]) autorg?right)closedboolean) contaminationnovelty_parameter_constraintsradius minkowskirNF) algorithm leaf_sizemetricp metric_paramsrrn_jobsc Nt |||||||| ||_||_y)N) n_neighborsrrrrrr )super__init__rr) selfr"rrrrrrrr __class__s \/mnt/ssd/data/python-lab/Trading/venv/lib/python3.12/site-packages/sklearn/neighbors/_lof.pyr$zLocalOutlierFactor.__init__s= #'  + c6|jr d}t|y)Nzmfit_predict is not available when novelty=True. Use novelty=False if you want to predict on the training set.TrAttributeErrorr%msgs r'_check_novelty_fit_predictz-LocalOutlierFactor._check_novelty_fit_predicts$ <<L !% %r(c@|j|jS)aFit the model to the training set X and return the labels. **Not available for novelty detection (when novelty is set to True).** Label is 1 for an inlier and -1 for an outlier according to the LOF score and the contamination parameter. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features), default=None The query sample or samples to compute the Local Outlier Factor w.r.t. the training samples. y : Ignored Not used, present for API consistency by convention. Returns ------- is_inlier : ndarray of shape (n_samples,) Returns -1 for anomalies/outliers and 1 for inliers. )fit_predict)r%Xys r' fit_predictzLocalOutlierFactor.fit_predicts4xx{##%%r()prefer_skip_nested_validationc|j||j}|j|kDr&tjd|jd|dt dt |j|dz |_|j|j\|_ }|jjtjk(r6|jj|jjd|_ |j|j||_|j ||j ddtj"fz }tj$|d  |_|j(d k(rd |_n2tj,|j&d |j(z|_tj |j&d kr!|j.stjd|S)aFit the local outlier factor detector from the training dataset. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) or (n_samples, n_samples) if metric='precomputed' Training data. y : Ignored Not used, present for API consistency by convention. Returns ------- self : LocalOutlierFactor The fitted local outlier factor detector. z n_neighbors (z/) is greater than the total number of samples (z=). n_neighbors will be set to (n_samples - 1) for estimation.r r"FcopyNaxisrggY@gcznDuplicate values are leading to incorrect results. Increase the number of neighbors for more accurate results.)_fitn_samples_fit_r"warningswarnmaxmin n_neighbors_ kneighbors_distances_fit_X__fit_Xdtypenpfloat32astype_local_reachability_density_lrdnewaxismeannegative_outlier_factor_roffset_ percentiler)r%r2r3 n_samples_neighbors_indices_fit_X_lrd_ratios_arrays r'r0zLocalOutlierFactor.fits* ! ''   i ' MM##Y0   3t'7'7Q#GH<@OO))=L= 9 9 ;;   *%)%;%;%B%B !!&C&D " 44  " "$=  II/ 0499Q ]3K K *,1A)J(J%    'DL==--ut7I7I/IDL 66$// 04 7 MMN   r(c6|js d}t|y)Nzpredict is not available when novelty=False, use fit_predict if you want to predict on training data. Use novelty=True if you want to use LOF for novelty detection and predict on new unseen data.Tr*r,s r'_check_novelty_predictz)LocalOutlierFactor._check_novelty_predictIs#||2  !% %r(c$|j|S)a<Predict the labels (1 inlier, -1 outlier) of X according to LOF. **Only available for novelty detection (when novelty is set to True).** This method allows to generalize prediction to *new observations* (not in the training set). Note that the result of ``clf.fit(X)`` then ``clf.predict(X)`` with ``novelty=True`` may differ from the result obtained by ``clf.fit_predict(X)`` with ``novelty=False``. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) The query sample or samples to compute the Local Outlier Factor w.r.t. the training samples. Returns ------- is_inlier : ndarray of shape (n_samples,) Returns -1 for anomalies/outliers and +1 for inliers. )r1r%r2s r'predictzLocalOutlierFactor.predictTs*}}Qr(c(t||C|j|}tj|jdt }d||dk<|Stj|j t }d||j|jk<|S)a~Predict the labels (1 inlier, -1 outlier) of X according to LOF. If X is None, returns the same as fit_predict(X_train). Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features), default=None The query sample or samples to compute the Local Outlier Factor w.r.t. the training samples. If None, makes prediction on the training data without considering them as their own neighbors. Returns ------- is_inlier : ndarray of shape (n_samples,) Returns -1 for anomalies/outliers and +1 for inliers. r)rF) r decision_functionrGonesshapeintr=rNrO)r%r2shifted_opposite_lof_scores is_inliers r'r1zLocalOutlierFactor._predictks"  =*.*@*@*C ' ; A A! DCPI9;I1A5 6  3 33?IFHId33dllB Cr(c6|js d}t|y)Na%decision_function is not available when novelty=False. Use novelty=True if you want to use LOF for novelty detection and compute decision_function for new unseen data. Note that the opposite LOF of the training samples is always available by considering the negative_outlier_factor_ attribute.Tr*r,s r' _check_novelty_decision_functionz3LocalOutlierFactor._check_novelty_decision_functions#||6 !% %r(c>|j||jz S)a%Shifted opposite of the Local Outlier Factor of X. Bigger is better, i.e. large values correspond to inliers. **Only available for novelty detection (when novelty is set to True).** The shift offset allows a zero threshold for being an outlier. The argument X is supposed to contain *new data*: if X contains a point from training, it considers the later in its own neighborhood. Also, the samples in X are not considered in the neighborhood of any point. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) The query sample or samples to compute the Local Outlier Factor w.r.t. the training samples. Returns ------- shifted_opposite_lof_scores : ndarray of shape (n_samples,) The shifted opposite of the Local Outlier Factor of each input samples. The lower, the more abnormal. Negative scores represent outliers, positive scores represent inliers. ) score_samplesrOrWs r'r[z$LocalOutlierFactor.decision_functions4!!!$t||33r(c6|js d}t|y)Nascore_samples is not available when novelty=False. The scores of the training samples are always available through the negative_outlier_factor_ attribute. Use novelty=True if you want to use LOF for novelty detection and compute score_samples for new unseen data.Tr*r,s r'_check_novelty_score_samplesz/LocalOutlierFactor._check_novelty_score_sampless$||A !% %r(ct|t|d}|j||j\}}|jt j k(r|j|jd}|j||}|j||ddt jfz }t j|d S) axOpposite of the Local Outlier Factor of X. It is the opposite as bigger is better, i.e. large values correspond to inliers. **Only available for novelty detection (when novelty is set to True).** The argument X is supposed to contain *new data*: if X contains a point from training, it considers the later in its own neighborhood. Also, the samples in X are not considered in the neighborhood of any point. Because of this, the scores obtained via ``score_samples`` may differ from the standard LOF scores. The standard LOF scores for the training data is available via the ``negative_outlier_factor_`` attribute. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) The query sample or samples to compute the Local Outlier Factor w.r.t. the training samples. Returns ------- opposite_lof_scores : ndarray of shape (n_samples,) The opposite of the Local Outlier Factor of each input samples. The lower, the more abnormal. csr) accept_sparser7Fr8Nr r:) r rrCrBrFrGrHrIrJrKrLrM)r%r2 distances_Xneighbors_indices_XX_lrdrSs r'rdz LocalOutlierFactor.score_sampless8   /+/?? 4,,,;, ( ( 77bjj %,,QWW5,AK00     99%89E!RZZ-numbersrnumpyrGbaserrutilsrutils._param_validationrr utils.metaestimatorsr utils.validationr _baser r__all__rr(r'rs>-:/.1  sA, sAr(