o `^h$@sdZddlZddlmZmZddlmZddlZddl m Z m Z ddl m Z ddlmZmZmZdd lmZdd lmZdd lmZmZmZmZGd d d e edZdddZdS)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_datac@sHeZdZdZdddZeddZddZd d Zd d Z dddZ d S) 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) FcCs|}|s|St|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)selfindicesmaskr]/home/air/shanriGPT/back/venv/lib/python3.10/site-packages/sklearn/feature_selection/_base.py get_support4szSelectorMixin.get_supportcCsdS)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. Nr)rrrrrKszSelectorMixin._get_support_maskc CsJtd|dd}|dkot|}t||ddt|jj |dd}||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_XrrrrWs  zSelectorMixin.transformcCsj|}|s.tdtt|dr|jddddfStjd|j d |j ddfSt ||ddS)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 UserWarninghasattrr,remptyr!reshapeshaper )rr)rrrrr(vs  zSelectorMixin._transformcCst|r<|}|t|jdd}|}tdgt |g}t |j |j |f|j dt|df|jd}|S|}t|dd}||j dkrStd|jdkr`|dddf}tj|j d|jf|jd}||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`. r.r)r8r!Nr-z,X has a different shape than during fitting.)rtocscinverse_transformrdiffindptrr7ravel concatenatecumsumrdatarr8lenr!rr sum ValueErrorndimzerossize)rr)it col_nonzerosr=Xtsupportrrrr;s(   zSelectorMixin.inverse_transformNcCst|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_featuresrrrget_feature_names_outs  z#SelectorMixin.get_feature_names_out)F)N) __name__ __module__ __qualname____doc__rrrrr(r;rMrrrrrs   (r) metaclassr.cCst|tr,|dkr't|drtd}n!t|drtd}ntd|jjdt|}nt|s4td||}|dur>|S|dkrY|jd krNt |}|St j j |d |d }|S|d krr|jd krht |}|St |jd d }|Std)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`Nnormr.r)r0ordsquarer/zpValid values for `transform_func` are None, 'norm' and 'square'. Those two transformation are only supported now) isinstancestrr5rrD __class__rNcallablerErabslinalgrVr rC)rgettertransform_func norm_order importancesrrr_get_feature_importancess@           rc)Nr.)rQr2abcrroperatorrnumpyr scipy.sparserrbaserutilsr r r utils._set_outputr utils._tagsr utils.validationrrrrrrcrrrrs    /