{Kg=-dZddlmZmZddlZddlmZmZm Z m Z m Z ddl m Z ddlmZmZddlmZmZmZmZdd lmZdd lmZdd lmZd d lmZGddeeeeZy)z Sequential feature selection )IntegralRealN) BaseEstimatorMetaEstimatorMixin _fit_contextclone is_classifier)get_scorer_names)check_cvcross_val_score) HasMethodsInterval RealNotInt StrOptions) _safe_tags)_RoutingNotSupportedMixin)check_is_fitted) SelectorMixinc eZdZUdZedggedheedddeeddd gdee ddd ged d hgdee e e gd gdegd Z eed<ddd dddddZedddZdZdZdZy)SequentialFeatureSelectoraTransformer 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"`. `tol` is required to be strictly positive when doing forward selection. 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)closedNneitherforwardbackward cv_object estimatorn_features_to_selecttol directionscoringcvn_jobs_parameter_constraints)r#r$r%r&r'r(cf||_||_||_||_||_||_||_yNr!)selfr"r#r$r%r&r'r(s i/home/alanp/www/video.onchill/myenv/lib/python3.12/site-packages/sklearn/feature_selection/_sequential.py__init__z"SequentialFeatureSelector.__init__s6#$8!"  F)prefer_skip_nested_validationc |j}|j|dd|jdd }|jd}|jdk(r"|j |dz |_n|dz|_n}t|jtr,|j|k\r td |j|_n7t|jtrt||jz|_|j )|j d kr|jd k(r td t|j|t|j  }t#|j }t%j&|t(}|jdk(s|jd k(r |j n||j z }t$j* } |j duxr|jdk(} t-|D]7} |j/|||||\} } | r| | z |j krn | } d|| <9|jdk(r|}||_|j0j3|_|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. cscr allow_nanT) accept_sparseensure_min_featuresforce_all_finiterrNz*n_features_to_select must be < n_features.rrz:tol must be strictly positive when doing forward selection) classifier)shapedtyper) _get_tags_validate_datagetr9r#r$n_features_to_select_ isinstancer ValueErrorrintr%r r'r r"r npzerosboolinfrange_get_best_new_feature_scoresupport_sum)r-Xytags n_featuresr'cloned_estimator current_mask n_iterations old_scoreis_auto_select_new_feature_idx new_scores r.rzSequentialFeatureSelector.fits=,~~     !!%+t!<<   WWQZ  $ $ .xx#.8!^*-71_* 118 <((J6 !MNN)-)B)BD & 114 8),Z$:S:S-S)TD & 88 DHHqLT^^y5PL dggq]4>>-J K 0 xxj= ((F2dnn 6Q  & &d888  VVG -U$2K2Kv2U|$A)-)I)I !QL* &OYI $9TXX#E!I,0L )% >>Z '(=L$ %)]]%6%6%8" r0c < tj|}i |D]h}|j}d||<|jdk(r|}|dd|f} t || |||j |j j |<jt fd} | | fS)NTr)r'r&r(c|Sr,) feature_idxscoress r.zGSequentialFeatureSelector._get_best_new_feature_score..&s f[>Qr0key) rB flatnonzerocopyr%r r&r(meanmax) r-r"rJrKr'rOcandidate_feature_indicesrYcandidate_maskX_newrTrZs @r.rGz5SequentialFeatureSelector._get_best_new_feature_scores %'NNL=$A!4K)..0N*.N; '~~+"0a'(E"1 {{ #df ;  5f*QR 777r0c0t||jSr,)rrHr-s r._get_support_maskz+SequentialFeatureSelector._get_support_mask)s}}r0c4dt|jdiS)Nr4r\)rr"rfs r. _more_tagsz$SequentialFeatureSelector._more_tags-s DNN D  r0r,)__name__ __module__ __qualname____doc__rrrrrrsetr callabler)dict__annotations__r/rrrGrgrirXr0r.rrsCL!%)* x ZAg 6 Xq$y 9! htT4 BC )Z!89:*S)9);%<=xHm" $D $$  &&+N N`82 r0r)rmnumbersrrnumpyrBbaserrrr r metricsr model_selectionr r utils._param_validationrrrr utils._tagsrutils.metadata_routingrutils.validationr_baserrrXr0r.r|sF#XX&7RR$>. ] }.@-] r0