U 9%ee,@sdZddlmZmZddlZddlmZmZm Z m Z m Z ddl m Z ddlmZmZddlmZmZmZmZdd lmZdd lmZd d lmZGd ddeeeZdS)z Sequential feature selection )IntegralRealN) BaseEstimatorMetaEstimatorMixin _fit_contextclone is_classifier)get_scorer_names)check_cvcross_val_score) HasMethodsInterval RealNotInt StrOptions) _safe_tags)check_is_fitted) SelectorMixinc @seZdZUdZedggedheeddddeeddd dgdee ddd dged d hgdee e e gd gdegd Z eed<ddd ddddddZedddddZddZddZddZdS)SequentialFeatureSelectora^Transformer that performs Sequential Feature Selection. This Sequential Feature Selector adds (forward selection) or removes (backward selection) features to form a feature subset in a greedy fashion. At each stage, this estimator chooses the best feature to add or remove based on the cross-validation score of an estimator. In the case of unsupervised learning, this Sequential Feature Selector looks only at the features (X), not the desired outputs (y). Read more in the :ref:`User Guide `. .. versionadded:: 0.24 Parameters ---------- estimator : estimator instance An unfitted estimator. n_features_to_select : "auto", int or float, default="auto" If `"auto"`, the behaviour depends on the `tol` parameter: - if `tol` is not `None`, then features are selected while the score change does not exceed `tol`. - otherwise, half of the features are selected. If integer, the parameter is the absolute number of features to select. If float between 0 and 1, it is the fraction of features to select. .. versionadded:: 1.1 The option `"auto"` was added in version 1.1. .. versionchanged:: 1.3 The default changed from `"warn"` to `"auto"` in 1.3. tol : float, default=None If the score is not incremented by at least `tol` between two consecutive feature additions or removals, stop adding or removing. `tol` can be negative when removing features using `direction="backward"`. It can be useful to reduce the number of features at the cost of a small decrease in the score. `tol` is enabled only when `n_features_to_select` is `"auto"`. .. versionadded:: 1.1 direction : {'forward', 'backward'}, default='forward' Whether to perform forward selection or backward selection. scoring : str or callable, default=None A single str (see :ref:`scoring_parameter`) or a callable (see :ref:`scoring`) to evaluate the predictions on the test set. NOTE that when using a custom scorer, it should return a single value. If None, the estimator's score method is used. cv : int, cross-validation generator or an iterable, default=None Determines the cross-validation splitting strategy. Possible inputs for cv are: - None, to use the default 5-fold cross validation, - integer, to specify the number of folds in a `(Stratified)KFold`, - :term:`CV splitter`, - An iterable yielding (train, test) splits as arrays of indices. For integer/None inputs, if the estimator is a classifier and ``y`` is either binary or multiclass, :class:`~sklearn.model_selection.StratifiedKFold` is used. In all other cases, :class:`~sklearn.model_selection.KFold` is used. These splitters are instantiated with `shuffle=False` so the splits will be the same across calls. Refer :ref:`User Guide ` for the various cross-validation strategies that can be used here. n_jobs : int, default=None Number of jobs to run in parallel. When evaluating a new feature to add or remove, the cross-validation procedure is parallel over the folds. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. Attributes ---------- n_features_in_ : int Number of features seen during :term:`fit`. Only defined if the underlying estimator exposes such an attribute when 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 n_features_to_select_ : int The number of features that were selected. support_ : ndarray of shape (n_features,), dtype=bool The mask of selected features. See Also -------- GenericUnivariateSelect : Univariate feature selector with configurable strategy. RFE : Recursive feature elimination based on importance weights. RFECV : Recursive feature elimination based on importance weights, with automatic selection of the number of features. SelectFromModel : Feature selection based on thresholds of importance weights. Examples -------- >>> from sklearn.feature_selection import SequentialFeatureSelector >>> from sklearn.neighbors import KNeighborsClassifier >>> from sklearn.datasets import load_iris >>> X, y = load_iris(return_X_y=True) >>> knn = KNeighborsClassifier(n_neighbors=3) >>> sfs = SequentialFeatureSelector(knn, n_features_to_select=3) >>> sfs.fit(X, y) SequentialFeatureSelector(estimator=KNeighborsClassifier(n_neighbors=3), n_features_to_select=3) >>> sfs.get_support() array([ True, False, True, True]) >>> sfs.transform(X).shape (150, 3) fitautorrright)closedNZneitherforwardbackwardZ cv_object estimatorn_features_to_selecttol directionscoringcvn_jobs_parameter_constraints)rrr r!r"r#cCs.||_||_||_||_||_||_||_dSNr)selfrrrr r!r"r#r(d/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/sklearn/feature_selection/_sequential.py__init__s z"SequentialFeatureSelector.__init__F)Zprefer_skip_nested_validationcCs|}|j|dd|dd d}|jd}|jdkrZ|jdk rN|d|_q|d|_nDt|jtr|j|krxt d |j|_nt|jt rt ||j|_|jdk r|jd kr|j d krt d t |j|t|jd }t|j}tj|td}|jdks |j d kr|jn||j}tj } |jdk o6|jdk} t|D]D} ||||||\} } | rv| | |jkrvq| } d|| <q@|j dkr|}||_|j|_|S)a Learn the features to select from X. Parameters ---------- X : array-like of shape (n_samples, n_features) Training vectors, where `n_samples` is the number of samples and `n_features` is the number of predictors. y : array-like of shape (n_samples,), default=None Target values. This parameter may be ignored for unsupervised learning. Returns ------- self : object Returns the instance itself. Zcscr allow_nanT)Z accept_sparseZensure_min_featuresZforce_all_finiterrNz*n_features_to_select must be < n_features.rrz1tol must be positive when doing forward selection) classifier)shapeZdtyper)Z _get_tagsZ_validate_datagetr-rrZn_features_to_select_ isinstancer ValueErrorrintr r r"r rrnpZzerosboolinfrange_get_best_new_feature_scoresupport_sum)r'XytagsZ n_featuresr"Zcloned_estimator current_maskZ n_iterationsZ old_scoreZis_auto_select_new_feature_idxZ new_scorer(r(r)rs`                zSequentialFeatureSelector.fitc st|}i|D]T}|}d||<|jdkr8|}|dd|f} t|| |||j|jd|<qtfddd} | | fS)NTr)r"r!r#cs|Sr&r() feature_idxZscoresr(r)zGSequentialFeatureSelector._get_best_new_feature_score..key) r2Z flatnonzerocopyr r r!r#Zmeanmax) r'rr9r:r"r<Zcandidate_feature_indicesr?Zcandidate_maskZX_newr>r(r@r)r6 s$  z5SequentialFeatureSelector._get_best_new_feature_scorecCst||jSr&)rr7r'r(r(r)_get_support_mask"sz+SequentialFeatureSelector._get_support_maskcCsdt|jddiS)Nr+rC)rrrGr(r(r) _more_tags&s z$SequentialFeatureSelector._more_tags)N)__name__ __module__ __qualname____doc__r rrrrrsetr callabler$dict__annotations__r*rrr6rHrIr(r(r(r)rs6     Nr)rMnumbersrrnumpyr2baserrrrr Zmetricsr Zmodel_selectionr r Zutils._param_validationr rrrZ utils._tagsrZutils.validationr_baserrr(r(r(r)s