>[g2dZddlZddlmZddlZddlmZddl m Z m Z m Z ddl mZddlmZmZdd lmZdd lmZdd lmZdd lmZmZdd lmZddlmZddlm Z m!Z!Gddee e Z"y)z! Nearest Centroid Classification N)Real)sparse) BaseEstimatorClassifierMixin _fit_context)#DiscriminantAnalysisPredictionMixin)pairwise_distancespairwise_distances_argmin) LabelEncoder)get_tags) available_if)Interval StrOptions)check_classification_targets)csc_median_axis_0)check_is_fitted validate_datacNeZdZUdZeddhgeeddddgded d hgd Zee d < ddd d dZ e ddZ fdZ dZdZeeej$Zeeej&Zeeej(ZfdZxZS)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. priors : {"uniform", "empirical"} or array-like of shape (n_classes,), default="uniform" The class prior probabilities. By default, the class proportions are inferred from the training data. .. versionadded:: 1.6 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 deviations_ : ndarray of shape (n_classes, n_features) Deviations (or shrinkages) of the centroids of each class from the overall centroid. Equal to eq. (18.4) if `shrink_threshold=None`, else (18.5) p. 653 of [2]. Can be used to identify features used for classification. .. versionadded:: 1.6 within_class_std_dev_ : ndarray of shape (n_features,) Pooled or within-class standard deviation of input data. .. versionadded:: 1.6 class_prior_ : ndarray of shape (n_classes,) The class prior probabilities. .. versionadded:: 1.6 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 ---------- [1] 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. [2] Hastie, T., Tibshirani, R., Friedman, J. (2009). The Elements of Statistical Learning Data Mining, Inference, and Prediction. 2nd Edition. New York, Springer. 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] manhattan euclideanrNneither)closedz array-like empiricaluniformmetricshrink_thresholdpriors_parameter_constraints)rr c.||_||_||_y)Nr)selfrrr s ^/var/www/html/bid-api/venv/lib/python3.12/site-packages/sklearn/neighbors/_nearest_centroid.py__init__zNearestCentroid.__init__s 0 T)prefer_skip_nested_validationc |jdk(rt|||dg\}}n8t|jjrdnd}t||||ddg\}}t j |}t||j\}}t}|j|}|jx|_ } | j} | dkrtd | z|jd k(rJtj |d \} } tj"| t%t'|z |_nU|jd k(r"tj*d | z g| z|_n$tj*|j|_|j(dkj-r tdtj.|j(j1dsFt3j4dt6|j(|j(j1z |_tj8| |ftj:|_tj>| } tA| D]}||k(}tj0|| |<|rtjB|d}|jdk(rF|s(tjD||d|j<|<stG|||j<|<||jId|j<|<tjJ||j<|z ddz}tjJtjL|j1d|| z z d|_'t-|jNdk(rt3j4dd}|rTtjP|jSd|jUdz jWdk(r t||s8tjPtjX|ddk(r t||jId}tjLd| z d|z z }|jNtjD|jNz}|j[t'|d }||z}tjJ|j<|z |z d|_.|j^rtj`|j\}tjb|j\|j^z |_.tjd|j\dd|j\|xj\|zc_.||j\z}tjJ||zd|_|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_sparse allow-nanTcsr)ensure_all_finiter*rz>The number of classes has to be greater than one; got %d classr)return_inverserrzpriors must be non-negativeg?zAThe priors do not sum to 1. Normalizing such that it sums to one.dtype)axisF)copyzself.within_class_std_dev_ has at least 1 zero standard deviation.Inputs within the same classes for at least 1 feature are identical.z2All features have zero variance. Division by zero.N)out)3rrr input_tags allow_nanspissparsershaper fit_transformclasses_size ValueErrorr npuniquebincountfloatlen class_prior_asarrayanyisclosesumwarningswarn UserWarningemptyfloat64 centroids_zerosrangewheremedianrmeanarraysqrtwithin_class_std_dev_allmaxmintoarrayptpreshape deviations_rsignabsclip)r#Xyr- is_X_sparse n_samples n_featuresley_indclasses n_classes_ class_countsnk cur_class center_maskvarianceerr_msgdataset_centroid_msmmmssignsmsds r$fitzNearestCentroid.fits* ;;+ % q!E7CDAq (~88BB  !"3$en DAqkk!n $Q' ! : ^  #"$++- LL q=P  ;;+ % ii$?OA| " L 9E#a&M ID  [[I % " A M?Y+F GD  " 4;; 7D     ! & & (:; ;zz$++//137 MMS !% 1 1D4E4E4I4I4K KD ((Iz#:"**MXXi y)I9,KFF;/ByM hh{3A6 {{k)"131[>PQ1RDOOI.1B1[>1RDOOI.-.{^-@-@a-@-H ** 88A 66UCqH%'XX GGHLLaL(I ,AB C%& " t))Q. / MMW  G 266155a5=155a5=#@"I"I"Kq"PQW% %qq(9Q(>!?W% %FFFN GGS2X# /2 3  & &43M3M)N N YYs1vq ! !V88 __0 0B 6U   GGD,,-E!vvd&6&67$:O:OOD  GGD$$a43C3C D    % t'''C hh'83'>UKDO r&ct|tj|jdt |j z j rbt|jjrdnd}t|||dd}|j t||j|jSt|=|S)aPerform 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) Input data. Returns ------- y_pred : ndarray of shape (n_samples,) The predicted classes. r/r+Tr,F)r-r*resetr)rr>rFrCrBr;rVr r5r6rr rMrsuperpredict)r#r`r- __class__s r$r|zNearestCentroid.predicts  ::d''S-?)? @ D D F (~88BB  "3# A==)!T__T[[Q 7?1% %r&c t|dt||dddtj}tj|j d|j jftj}|jdk7}|dd|fxx|j|zcc<|jj}|dd|fxx|j|zcc<t|j jD]t}t|||g|jj}|d z}tj| d tj |j"|zz|dd|f<v|S) NrMTFr,)r3ryr*r1rr0rzrg@)rrr>rLrKr9r;r<rUrMr3rOr rravelsqueezelogrC)r#r` X_normalizeddiscriminant_scoremaskcentroids_normalized class_idx distancess r$_decision_functionz"NearestCentroid._decision_function8sLl+$ !$e5   XX    "DMM$6$6 7rzz ))Q.QW!;!;D!AA#335QW%)C)CD)II%t}}112I*2I;? eg  !OI/1zz S266$*;*;I*F#GGG0 q)| , 3"!r&c |jdk(S)Nrrz)r#s r$_check_euclidean_metricz'NearestCentroid._check_euclidean_metricTs{{k))r&c`t|}|jdk(|j_|S)N nan_euclidean)r{__sklearn_tags__rr5r6)r#tagsr}s r$rz NearestCentroid.__sklearn_tags__cs*w')$(KK?$B! r&)r)__name__ __module__ __qualname____doc__rrrr!dict__annotations__r%rrwr|rrrr decision_function predict_probapredict_log_probar __classcell__)r}s@r$rrseP{K89:%dAtIFM[),D!EF$D  5{6{z &D"8*> %<=+==:L!89+99M> %<=+==r&r)#rrHnumbersrnumpyr>scipyrr7baserrrdiscriminant_analysisr metrics.pairwiser r preprocessingr utilsr utils._available_ifrutils._param_validationrrutils.multiclassrutils.sparsefuncsrutils.validationrrrr&r$rsP??G).:;1=I'-Ir&