o tBhj @sdZddlZddlZddlmZddlmZm Z ddl m Z ddl m Z ddlmZdd lmZdd lmZGd d d e eZdS) z! Nearest Centroid Classification N)sparse) BaseEstimatorClassifierMixin)pairwise_distances) LabelEncoder)check_is_fitted)csc_median_axis_0)check_classification_targetsc@s0eZdZdZd ddddZddZd d ZdS) 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 : str or callable, default="euclidean" The metric to use when calculating distance between instances in a feature array. If metric is a string or callable, it must be one of the options allowed by :func:`~sklearn.metrics.pairwise_distances` for its metric parameter. The centroids for the samples corresponding to each class is the point from which the sum of the distances (according to the metric) of all samples that belong to that particular class are minimized. If the `"manhattan"` metric is provided, this centroid is the median and for all other metrics, the centroid is now set to be the mean. .. 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] euclideanN)shrink_thresholdcCs||_||_dS)N)metricr )selfrr rz/var/www/html/riverr-enterprise-integrations-main/venv/lib/python3.10/site-packages/sklearn/neighbors/_nearest_centroid.py__init__as zNearestCentroid.__init__cCst|jdkr td|jdkr|j||dgd\}}n |j||ddgd\}}t|}|r4|jr4tdt||j\}}t}| |}|j |_ }|j } | dkrXtd | t j | |ft jd |_t | } t| D]I} || k} t | | | <|rt | d } |jdkr|st j|| d d |j| <qlt|| |j| <ql|jd krtd|| jd d |j| <ql|jr8t t j|d d d krtdt j|d d } t d| d|}||j|d}|jd d }t ||| }|t |7}|t|d}||}|j| |}t |}t ||j}t j |d d|d||9}||}| t j!ddf||_|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. precomputedzPrecomputed is not supported. manhattancsc) accept_sparsecsrz2threshold shrinking not supported for sparse inputrz>The number of classes has to be greater than one; got %d class)dtyperaxisr zjAveraging for metrics other than euclidean and manhattan not supported. The average is set to be the mean.z2All features have zero variance. Division by zero.g?N)out)"r ValueError_validate_dataspissparser r shaper fit_transformclasses_sizenpemptyfloat64 centroids_zerosrangesumwheremedianr warningswarnmeanallptpsqrtreshapelensignabsclipnewaxis)rXy is_X_sparse n_samples n_featuresley_indclasses n_classesnk cur_class center_maskdataset_centroid_mvariancesmmms deviationsignsmsdrrrfitesn             zNearestCentroid.fitcCs8t||j|ddd}|jt||j|jdjddS)aKPerform 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. Notes ----- If the metric constructor parameter is `"precomputed"`, `X` is assumed to be the distance matrix between the data to be predicted and `self.centroids_`. rF)rreset)rrr)rrr#rr(rargmin)rr:rrrpredicts zNearestCentroid.predict)r )__name__ __module__ __qualname____doc__rrOrRrrrrr s J _r )rVr.numpyr%scipyrrbaserrmetrics.pairwiser preprocessingrutils.validationrutils.sparsefuncsr utils.multiclassr r rrrrs