U 9%e%@sdZddlZddlmZddlZddlmZddl m Z ddl m Z m Z mZddlmZdd lmZdd lmZmZdd lmZdd lmZdd lmZGddde e ZdS)z! Nearest Centroid Classification N)Real)sparse)_VALID_METRICS) BaseEstimatorClassifierMixin _fit_context)pairwise_distances_argmin) LabelEncoder)Interval StrOptions)check_classification_targets)csc_median_axis_0)check_is_fittedc@seZdZUdZeedddhZeeeddhdege e dd d d d gd Z e e d <dd dddZeddddZddZd S)NearestCentroidag 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" Metric to use for distance computation. See the documentation of `scipy.spatial.distance `_ and the metrics listed in :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric values. Note that "wminkowski", "seuclidean" and "mahalanobis" are not supported. 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. .. deprecated:: 1.3 Support for metrics other than `euclidean` and `manhattan` and for callables was deprecated in version 1.3 and will be removed in version 1.5. .. 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] Z mahalanobisZ seuclideanZ wminkowski manhattan euclidean) deprecatedrNZneither)closedmetricshrink_threshold_parameter_constraints)rcCs||_||_dS)Nr)selfrrrb/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/sklearn/neighbors/_nearest_centroid.py__init__{szNearestCentroid.__init__T)Zprefer_skip_nested_validationcCst|jtr"|jdkr"tdt|jdkrD|j||dgd\}}n|j||ddgd\}}t|}|rx|j rxt dt ||j \}}t }||}|j|_}|j} | dkrt d | tj| |ftjd |_t| } t| D]} || k} t| | | <|rt| d } |jdkrV|sBtj|| d d |j| <nt|| |j| <q|jd krltd|| jd d |j| <q|j rttj|d d d krt dtj|d d } td| d|}||j|d}|jd d }t||| }|t|7}|t |d}||}|j| |}t!|}t"||j }tj#|d d|d||9}||}| tj$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. )rrzSupport for distance metrics other than euclidean and manhattan and for callables was deprecated in version 1.3 and will be removed in version 1.5.rZcsc) accept_sparsecsrz2threshold shrinking not supported for sparse inputrz>The number of classes has to be greater than one; got %d class)Zdtyper)ZaxisrzjAveraging 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)% isinstancerstrwarningswarn FutureWarning_validate_dataspissparser ValueErrorr shaper Z fit_transformclasses_sizenpemptyZfloat64 centroids_ZzerosrangesumwhereZmedianrZmeanallZptpsqrtZreshapelensignabsZclipZnewaxis)rXyZ is_X_sparseZ n_samplesZ n_featuresleZy_indclassesZ n_classesZnkZ cur_classZ center_maskZdataset_centroid_mZvariancesmmmsZ deviationZsignsZmsdrrrfitst            zNearestCentroid.fitcCs0t||j|ddd}|jt||j|jdS)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)r)rr&r+r r/r)rr8rrrpredicts zNearestCentroid.predict)r)__name__ __module__ __qualname____doc__setrZ_valid_metricsr callabler rrdict__annotations__rrr@rBrrrrrs S   kr)rFr#numbersrnumpyr-Zscipyrr'Zsklearn.metrics.pairwiserbaserrrZmetrics.pairwiser Z preprocessingr Zutils._param_validationr r Zutils.multiclassr Zutils.sparsefuncsrZutils.validationrrrrrrs