0Ph5dZddlmZmZddlZddlmZmZm Z m Z m Z ddl m Z mZddlmZmZddlmZmZmZmZmZdd lmZmZmZmZdd lmZdd lm Z m!Z!d d l"m#Z#Gdde#eeZ$dS)z Sequential feature selection )IntegralRealN) BaseEstimatorMetaEstimatorMixin _fit_contextclone is_classifier) check_scoringget_scorer_names)check_cvcross_val_score)MetadataRouter MethodMapping_raise_for_params_routing_enabledprocess_routing) HasMethodsInterval RealNotInt StrOptions)get_tags)check_is_fitted validate_data) SelectorMixinc peZdZUdZedggedheedddeeddd gdee ddd ged d hgdee e e gd gdegd Z eed<ddd dddddZedddZdZdZfdZdZxZS)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_callable`) 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.ch||_||_||_||_||_||_||_dSNr')selfr(r)r*r+r,r-r.s e/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/sklearn/feature_selection/_sequential.py__init__z"SequentialFeatureSelector.__init__s:#$8!"  F)prefer_skip_nested_validationc t||d|}t||dd|jj }|jd}|jdkr|j |dz |_n|dz|_nwt|jtr'|j|krtd|j|_n6t|jtrt||jz|_|j%|jd kr|jd krtd t|j|t#|j }t'|j}t)j|t, }|jdks |jd kr|jn ||jz } t(j } |jduo |jdk} t1rt3|dfi|t5| D]0} |j|||||fi|\} }| r|| z |jkrn|} d|| <1|jdkr|}||_|j|_|S)aLearn the features to select from X. Parameters ---------- X : array-like of shape (n_samples, n_features) Training vectors, where `n_samples` is the number of samples and `n_features` is the number of predictors. y : array-like of shape (n_samples,), default=None Target values. This parameter may be ignored for unsupervised learning. **params : dict, default=None Parameters to be passed to the underlying `estimator`, `cv` and `scorer` objects. .. versionadded:: 1.6 Only available if `enable_metadata_routing=True`, which can be set by using ``sklearn.set_config(enable_metadata_routing=True)``. See :ref:`Metadata Routing User Guide ` for more details. Returns ------- self : object Returns the instance itself. rcscr) accept_sparseensure_min_featuresensure_all_finiterr Nz*n_features_to_select must be < n_features.rr$z:tol must be strictly positive when doing forward selection classifier)shapedtypeTr%)r__sklearn_tags__r input_tags allow_nanr?r)r*n_features_to_select_ isinstancer ValueErrorrintr+r r-r r(r npzerosboolinfrrrange_get_best_new_feature_scoresupport_sum)r3Xyparamstags n_featuresr-cloned_estimator current_mask n_iterations old_scoreis_auto_select_new_feature_idx new_scores r4rzSequentialFeatureSelector.fitsD &$...$$&&    !"&/";;    WQZ  $ . .x#.8!^**-71_** 18 < < U(J66 !MNNN)-)BD & & 14 8 8 U),Z$:S-S)T)TD & 8 DHqLLT^y5P5PL dgq]4>-J-J K K K 00 xj=== (F22dn 6Q6Q  & &d88  VG -U$2Kv2U    3 D% 2 26 2 2 2|$$ 1 1A)I)I !QL**Z ' '(=L$ %)]%6%6%8%8" r6c H tj|}i |D]j}|} d| |<|jdkr| } |dd| f} t || |||j|j| |<kt fd} | | fS)NTr%)r-r,r.rRc|Sr2) feature_idxscoress r4zGSequentialFeatureSelector._get_best_new_feature_score..Bs f[>Qr6)key) rH flatnonzerocopyr+rr,r.meanmax) r3r(rPrQr-rVrRcandidate_feature_indicesr`candidate_maskX_newr[ras @r4rMz5SequentialFeatureSelector._get_best_new_feature_score+s %'NL=$A$A!4  K)..00N*.N; '~++"0aaa'(E"1 {###dff ;  f*Q*Q*Q*QRRR 777r6c.t||jSr2)rrN)r3s r4_get_support_maskz+SequentialFeatureSelector._get_support_maskEs}r6ct}t|jjj|j_t|jjj|j_|Sr2)superrArr(rBrCsparse)r3rS __class__s r4rAz*SequentialFeatureSelector.__sklearn_tags__IsQww''))$,T^$<$<$G$Q!!)$.!9!9!D!K r6ct|jj}||jt dd|t |jt|jt dd|t|j|j t dd  |S) ajGet metadata routing of this object. Please check :ref:`User Guide ` on how the routing mechanism works. .. versionadded:: 1.6 Returns ------- routing : MetadataRouter A :class:`~sklearn.utils.metadata_routing.MetadataRouter` encapsulating routing information. )ownerr)callercallee)r(method_mappingr=split)splitterru)r,score)scorerru) rrp__name__addr(rr r-r r r,)r3routers r4get_metadata_routingz.SequentialFeatureSelector.get_metadata_routingOs dn&=>>> n(??..eE.JJ      dg-2O2OPPP(??..eG.LL       FFF(??..eG.LL     r6r2)rz __module__ __qualname____doc__rrrrrrsetr callabler/dict__annotations__r5rrrMrlrAr} __classcell__)rps@r4rrsCCL!j%))* Jx HZAg 6 6 6 HXq$y 9 9 9! hhtT4 BBBC j)Z!899:**SS)9)9););%<%<==xHm" $ $D   $$  &\&+bbb bH8884 r6r)%rnumbersrrnumpyrHbaserrrr r metricsr r model_selectionr rutils._metadata_requestsrrrrrutils._param_validationrrrr utils._tagsrutils.validationrr_baserrr_r6r4rs{#"""""""XXXXXXXXXXXXXX5555555577777777SRRRRRRRRRRR""""""======== NNNNN /A=NNNNNr6