{KgdZddlmZddlZddlmZddlm Z m Z m Z ddl m Z ddlmZdd lmZmZdd lmZdd lmZdd lmZGd de e Zy)z! Nearest Centroid Classification )RealN)sparse) BaseEstimatorClassifierMixin _fit_context)pairwise_distances_argmin) LabelEncoder)Interval StrOptions)check_classification_targets)csc_median_axis_0)check_is_fittedceZdZUdZeddhgeeddddgdZee d <ddd d Z e d dZ dZ y)NearestCentroida Nearest centroid classifier. Each class is represented by its centroid, with test samples classified to the class with the nearest centroid. Read more in the :ref:`User Guide `. Parameters ---------- metric : {"euclidean", "manhattan"}, default="euclidean" Metric to use for distance computation. If `metric="euclidean"`, the centroid for the samples corresponding to each class is the arithmetic mean, which minimizes the sum of squared L1 distances. If `metric="manhattan"`, the centroid is the feature-wise median, which minimizes the sum of L1 distances. .. versionchanged:: 1.5 All metrics but `"euclidean"` and `"manhattan"` were deprecated and now raise an error. .. versionchanged:: 0.19 `metric='precomputed'` was deprecated and now raises an error shrink_threshold : float, default=None Threshold for shrinking centroids to remove features. Attributes ---------- centroids_ : array-like of shape (n_classes, n_features) Centroid of each class. classes_ : array of shape (n_classes,) The unique classes labels. 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 See Also -------- KNeighborsClassifier : Nearest neighbors classifier. Notes ----- When used for text classification with tf-idf vectors, this classifier is also known as the Rocchio classifier. References ---------- Tibshirani, R., Hastie, T., Narasimhan, B., & Chu, G. (2002). Diagnosis of multiple cancer types by shrunken centroids of gene expression. Proceedings of the National Academy of Sciences of the United States of America, 99(10), 6567-6572. The National Academy of Sciences. Examples -------- >>> from sklearn.neighbors import NearestCentroid >>> import numpy as np >>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]]) >>> y = np.array([1, 1, 1, 2, 2, 2]) >>> clf = NearestCentroid() >>> clf.fit(X, y) NearestCentroid() >>> print(clf.predict([[-0.8, -1]])) [1] For a more detailed example see: :ref:`sphx_glr_auto_examples_neighbors_plot_nearest_centroid.py` manhattan euclideanrNneither)closedmetricshrink_threshold_parameter_constraints)rc ||_||_y)Nr)selfrrs g/home/alanp/www/video.onchill/myenv/lib/python3.12/site-packages/sklearn/neighbors/_nearest_centroid.py__init__zNearestCentroid.__init__ls 0T)prefer_skip_nested_validationc|jdk(r|j||dg\}}n|j||ddg\}}tj|}|r|jr t dt ||j\}}t}|j|}|jx|_ }|j} | dkrt d| ztj| |ftj|_tj | } t#| D]} || k(} tj$| | | <|rtj&| d } |jdk(rF|s(tj(|| d |j| <st+|| |j| <|| j-d |j| <|jrrtj.tj0|d d k(r t d tj,|d } tj2d | z d |z z }||j|z dz}|j%d }tj2||| z z }|tj(|z }|j5t7|d }||z}|j| z |z }tj8|}tj:||jz }tj<|d d|||z}||z}| tj>ddf|z|_|S)a0 Fit the NearestCentroid model according to the given training data. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Training vector, where `n_samples` is the number of samples and `n_features` is the number of features. Note that centroid shrinking cannot be used with sparse matrices. y : array-like of shape (n_samples,) Target values. Returns ------- self : object Fitted estimator. rcsc) accept_sparsecsrz2threshold shrinking not supported for sparse inputrz>The number of classes has to be greater than one; got %d class)dtyper)axisz2All features have zero variance. Division by zero.g?N)out) r_validate_dataspissparser ValueErrorr shaper fit_transformclasses_sizenpemptyfloat64 centroids_zerosrangesumwheremedianrmeanallptpsqrtreshapelensignabsclipnewaxis)rXy is_X_sparse n_samples n_featuresley_indclasses n_classesnk cur_class center_maskdataset_centroid_mvariancesmmms deviationsignsmsds rfitzNearestCentroid.fitps* ;;+ %&&q!E7&CDAq&&q!E5>&JDAqkk!n 400QR R$Q' ! : ^  #"$++- LL q=P  ((Iz#:"**M XXi y)I9,KFF;/ByM hh{3A6 {{k)"131[>PQ1RDOOI.1B1[>1RDOOI.-.{^-@-@a-@-H **  vvbffQQ'1,- !UVV " 2 rcIo67ADOOE22q8H|||+HI $9:;A 1 A3q61%BaB+<<BIGGI&Ey)D,A,AAI GGIq$I 6  Iy.C/ A >DDO rct||j|dd}|jt||j|j S)a}Perform classification on an array of test vectors `X`. The predicted class `C` for each sample in `X` is returned. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Test samples. Returns ------- C : ndarray of shape (n_samples,) The predicted classes. r#F)r"reset)r)rr(r.r r3r)rrCs rpredictzNearestCentroid.predictsH    e  D}} %a M  r)r)__name__ __module__ __qualname____doc__r r rrdict__annotations__rrrXr[rrrrsjL^{K89:%dAtIFM$D 1t15T6Tl rr)r_numbersrnumpyr0scipyrr)baserrrmetrics.pairwiser preprocessingr utils._param_validationr r utils.multiclassr utils.sparsefuncsrutils.validationrrrbrrrms=??8(:;1.C o}C r