0Ph$dZddlZddlmZmZddlmZddlZddl m Z m Z ddl m Z ddlmZmZmZdd lmZdd lmZdd lmZmZmZmZGd d e eZddZdS)zGeneric feature selection mixinN)ABCMetaabstractmethod) attrgetter) csc_matrixissparse)TransformerMixin)_safe_indexing check_arraysafe_sqr)_get_output_config)get_tags)_check_feature_names_in _is_pandas_dfcheck_is_fitted validate_datacJeZdZdZd dZedZdZdZdZ d d Z dS) SelectorMixina Transformer mixin that performs feature selection given a support mask This mixin provides a feature selector implementation with `transform` and `inverse_transform` functionality given an implementation of `_get_support_mask`. Examples -------- >>> import numpy as np >>> from sklearn.datasets import load_iris >>> from sklearn.base import BaseEstimator >>> from sklearn.feature_selection import SelectorMixin >>> class FeatureSelector(SelectorMixin, BaseEstimator): ... def fit(self, X, y=None): ... self.n_features_in_ = X.shape[1] ... return self ... def _get_support_mask(self): ... mask = np.zeros(self.n_features_in_, dtype=bool) ... mask[:2] = True # select the first two features ... return mask >>> X, y = load_iris(return_X_y=True) >>> FeatureSelector().fit_transform(X, y).shape (150, 2) Fcf|}|s|ntj|dS)a Get a mask, or integer index, of the features selected. Parameters ---------- indices : bool, default=False If True, the return value will be an array of integers, rather than a boolean mask. Returns ------- support : array An index that selects the retained features from a feature vector. If `indices` is False, this is a boolean array of shape [# input features], in which an element is True iff its corresponding feature is selected for retention. If `indices` is True, this is an integer array of shape [# output features] whose values are indices into the input feature vector. r)_get_support_masknpwhere)selfindicesmasks _/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/sklearn/feature_selection/_base.py get_supportzSelectorMixin.get_support4s1(%%''"9ttq(99cdS)a Get the boolean mask indicating which features are selected Returns ------- support : boolean array of shape [# input features] An element is True iff its corresponding feature is selected for retention. N)rs rrzSelectorMixin._get_support_maskKsrc td|d}|dkot|}t||ddt|jj |d}||S) aBReduce X to the selected features. Parameters ---------- X : array of shape [n_samples, n_features] The input samples. Returns ------- X_r : array of shape [n_samples, n_selected_features] The input samples with only the selected features. transform) estimatordensedefaultNcsrF)dtype accept_sparseensure_all_finiteskip_check_arrayreset)r rrr input_tags allow_nan _transform)rXoutput_config_dense preserve_Xs rr"zSelectorMixin.transformWs1MMMgV(I5J-:J:J    "*4..";"EE'   q!!!rcf|}|sxtjdtt |dr|jddddfStjd|j  |j ddfSt||dS)z"Reduce X to the selected features.zYNo features were selected: either the data is too noisy or the selection test too strict.ilocNrr'axis) ranywarningswarn UserWarninghasattrr3remptyr'reshapeshaper )rr/rs rr.zSelectorMixin._transformvs!!xxzz G MC    q&!! %vaaa!e}$8AQW---55qwqz1oFF FaA....rct|r|}|tj|jdd}|}tjdgtj |g}t|j |j |f|j dt|dz f|j}|S|}t#|d}||j dkrt'd|jdkr |dddf}tj|j d|jf|j}||dd|f<|S)aReverse the transformation operation. Parameters ---------- X : array of shape [n_samples, n_selected_features] The input samples. Returns ------- X_r : array of shape [n_samples, n_original_features] `X` with columns of zeros inserted where features would have been removed by :meth:`transform`. r5r)r?r'Nr4z,X has a different shape than during fitting.)rtocscinverse_transformrdiffindptrr>ravel concatenatecumsumrdatarr?lenr'rr sum ValueErrorndimzerossize)rr/it col_nonzerosrEXtsupports rrCzSelectorMixin.inverse_transformsc A;;  A''(9(9(A(A!R(H(HIIB88::L^aS")L*A*A$BCCFF+wqz3v;;?3gB I""$$  & & & ;;==AGAJ & &KLL L 6Q;;$' A Xqwqz7<0 @ @ @111g: rNctt|t||}||S)aMask feature names according to selected features. Parameters ---------- input_features : array-like of str or None, default=None Input features. - If `input_features` is `None`, then `feature_names_in_` is used as feature names in. If `feature_names_in_` is not defined, then the following input feature names are generated: `["x0", "x1", ..., "x(n_features_in_ - 1)"]`. - If `input_features` is an array-like, then `input_features` must match `feature_names_in_` if `feature_names_in_` is defined. Returns ------- feature_names_out : ndarray of str objects Transformed feature names. )rrr)rinput_featuress rget_feature_names_outz#SelectorMixin.get_feature_names_outs8( 0~FFd..0011r)F)N) __name__ __module__ __qualname____doc__rrrr"r.rCrVr rrrrs4::::.   ^  """>/// &&&P222222rr) metaclassr5ct|trs|dkr]t|drtd}nkt|drtd}nKt d|jjdt|}nt|st d||}||S|dkrC|jd krtj |}nwtj |d | }nT|d kr?|jd krt|}n3t|d }nt d|S)a Retrieve and aggregate (ndim > 1) the feature importances from an estimator. Also optionally applies transformation. Parameters ---------- estimator : estimator A scikit-learn estimator from which we want to get the feature importances. getter : "auto", str or callable An attribute or a callable to get the feature importance. If `"auto"`, `estimator` is expected to expose `coef_` or `feature_importances`. transform_func : {"norm", "square"}, default=None The transform to apply to the feature importances. By default (`None`) no transformation is applied. norm_order : int, default=1 The norm order to apply when `transform_func="norm"`. Only applied when `importances.ndim > 1`. Returns ------- importances : ndarray of shape (n_features,) The features importances, optionally transformed. autocoef_feature_importances_z;when `importance_getter=='auto'`, the underlying estimator z should have `coef_` or `feature_importances_` attribute. Either pass a fitted estimator to feature selector or call fit before calling transform.z4`importance_getter` has to be a string or `callable`Nnormr5r)r7ordsquarer6zpValid values for `transform_func` are None, 'norm' and 'square'. Those two transformation are only supported now) isinstancestrr<rrL __class__rWcallablerMrabslinalgr`r rK)r#gettertransform_func norm_order importancess r_get_feature_importancesrms8&#Q V  y'** #G,,$:;; #$:;; 0!*!4!=000 ''FF f  QOPPP&##K 6 ! !  q &--KK)..1*.MMKK 8 # #  q ";//KK";//333;;KK 6   r)Nr5)rZr9abcrroperatorrnumpyr scipy.sparserrbaser utilsr r r utils._set_outputr utils._tagsrutils.validationrrrrrrmr rrrwsT%% ''''''''--------######9999999999222222""""""k2k2k2k2k2$k2k2k2k2\DDDDDDr