ó ‡ˆ\c@s6dZddlZddlmZmZddlmZddlmZddl m Z ddl m Z dd l m Z dd l mZdd l mZdd lmZmZmZdd lmZddlmZddlmZddl mZd„Zde e efd„ƒYZdee fd„ƒYZdS(s1Recursive feature elimination for feature rankingiÿÿÿÿNi(t check_X_ytsafe_sqr(tif_delegate_has_method(t _safe_split(tcheck_is_fitted(t BaseEstimator(tMetaEstimatorMixin(tclone(t is_classifier(tParalleltdelayedteffective_n_jobs(tcheck_cv(t_score(t check_scoringi(t SelectorMixinc s^t||||ƒ\}}t|||||ƒ\‰‰|j||‡‡‡fd†ƒjS(s5 Return the score for a fit across one fold. cs#t|ˆdd…|fˆˆƒS(N(R (t estimatortfeatures(tX_testtscorerty_test(s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyt s(Rt_fittscores_( trfeRtXtyttrainttestRtX_trainty_train((RRRs<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyt_rfe_single_fitstRFEcBsÅeZdZdddd„Zed„ƒZd„Zdd„Ze ddƒd „ƒZ e ddƒd „ƒZ d „Z e ddƒd „ƒZ e ddƒd „ƒZe ddƒd„ƒZRS(sZ Feature ranking with recursive feature elimination. Given an external estimator that assigns weights to features (e.g., the coefficients of a linear model), the goal of recursive feature elimination (RFE) is to select features by recursively considering smaller and smaller sets of features. First, the estimator is trained on the initial set of features and the importance of each feature is obtained either through a ``coef_`` attribute or through a ``feature_importances_`` attribute. Then, the least important features are pruned from current set of features. That procedure is recursively repeated on the pruned set until the desired number of features to select is eventually reached. Read more in the :ref:`User Guide `. Parameters ---------- estimator : object A supervised learning estimator with a ``fit`` method that provides information about feature importance either through a ``coef_`` attribute or through a ``feature_importances_`` attribute. n_features_to_select : int or None (default=None) The number of features to select. If `None`, half of the features are selected. step : int or float, optional (default=1) If greater than or equal to 1, then ``step`` corresponds to the (integer) number of features to remove at each iteration. If within (0.0, 1.0), then ``step`` corresponds to the percentage (rounded down) of features to remove at each iteration. verbose : int, (default=0) Controls verbosity of output. Attributes ---------- n_features_ : int The number of selected features. support_ : array of shape [n_features] The mask of selected features. ranking_ : array of shape [n_features] The feature ranking, such that ``ranking_[i]`` corresponds to the ranking position of the i-th feature. Selected (i.e., estimated best) features are assigned rank 1. estimator_ : object The external estimator fit on the reduced dataset. Examples -------- The following example shows how to retrieve the 5 right informative features in the Friedman #1 dataset. >>> from sklearn.datasets import make_friedman1 >>> from sklearn.feature_selection import RFE >>> from sklearn.svm import SVR >>> X, y = make_friedman1(n_samples=50, n_features=10, random_state=0) >>> estimator = SVR(kernel="linear") >>> selector = RFE(estimator, 5, step=1) >>> selector = selector.fit(X, y) >>> selector.support_ # doctest: +NORMALIZE_WHITESPACE array([ True, True, True, True, True, False, False, False, False, False]) >>> selector.ranking_ array([1, 1, 1, 1, 1, 6, 4, 3, 2, 5]) See also -------- RFECV : Recursive feature elimination with built-in cross-validated selection of the best number of features References ---------- .. [1] Guyon, I., Weston, J., Barnhill, S., & Vapnik, V., "Gene selection for cancer classification using support vector machines", Mach. Learn., 46(1-3), 389--422, 2002. iicCs(||_||_||_||_dS(N(Rtn_features_to_selecttsteptverbose(tselfRR!R"R#((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyt__init__us   cCs |jjS(N(Rt_estimator_type(R$((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyR&|scCs|j||ƒS(sEFit the RFE model and then the underlying estimator on the selected features. Parameters ---------- X : {array-like, sparse matrix}, shape = [n_samples, n_features] The training input samples. y : array-like, shape = [n_samples] The target values. (R(R$RR((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pytfit€s cCst||dƒ\}}|jd}|jdkrA|d}n |j}d|jkoddknrˆttd|j|ƒƒ}nt|jƒ}|dkr²tdƒ‚ntj |dtj ƒ}tj |dtjƒ}|rôg|_ nx‡tj |ƒ|kr}tj |ƒ|} t|jƒ} |jdkrRd tj |ƒGHn| j|dd…| f|ƒt| d ƒr| j} nt| d dƒ} | dkrºtd ƒ‚n| jdkrítjt| ƒj d dƒƒ} ntjt| ƒƒ} tj| ƒ} t|tj |ƒ|ƒ} |rO|j j|| | ƒƒnt|| | | <|tj|ƒcd70tdtypes#Fitting estimator with %d features.tcoef_tfeature_importances_sKThe classifier does not expose "coef_" or "feature_importances_" attributestaxis("RtshapeR!tNoneR"tinttmaxt ValueErrortnptonestboolRtsumtarangeRRR#R'thasattrR*tgetattrt RuntimeErrortndimtargsortRtraveltmintappendtFalset logical_nott estimator_t n_features_tsupport_tranking_(R$RRt step_scoret n_featuresR!R"RCRDRRtcoefstrankst threshold((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyRŽsV        $#  tdelegateRcCs&t|dƒ|jj|j|ƒƒS(sPReduce X to the selected features and then predict using the underlying estimator. Parameters ---------- X : array of shape [n_samples, n_features] The input samples. Returns ------- y : array of shape [n_samples] The predicted target values. RA(RRAtpredictt transform(R$R((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyRKás cCs)t|dƒ|jj|j|ƒ|ƒS(s,Reduce X to the selected features and then return the score of the underlying estimator. Parameters ---------- X : array of shape [n_samples, n_features] The input samples. y : array of shape [n_samples] The target values. RA(RRAtscoreRL(R$RR((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyRMós cCst|dƒ|jS(NRC(RRC(R$((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyt_get_support_masks cCs&t|dƒ|jj|j|ƒƒS(s§Compute the decision function of ``X``. Parameters ---------- X : array-like or sparse matrix, shape = [n_samples, n_features] The input samples. Internally, it will be converted to ``dtype=np.float32`` and if a sparse matrix is provided to a sparse ``csr_matrix``. Returns ------- score : array, shape = [n_samples, n_classes] or [n_samples] The decision function of the input samples. The order of the classes corresponds to that in the attribute `classes_`. Regression and binary classification produce an array of shape [n_samples]. RA(RRAtdecision_functionRL(R$R((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyROs cCs&t|dƒ|jj|j|ƒƒS(s/Predict class probabilities for X. Parameters ---------- X : array-like or sparse matrix, shape = [n_samples, n_features] The input samples. Internally, it will be converted to ``dtype=np.float32`` and if a sparse matrix is provided to a sparse ``csr_matrix``. Returns ------- p : array of shape = [n_samples, n_classes] The class probabilities of the input samples. The order of the classes corresponds to that in the attribute `classes_`. RA(RRAt predict_probaRL(R$R((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyRPs cCs&t|dƒ|jj|j|ƒƒS(s‘Predict class log-probabilities for X. Parameters ---------- X : array of shape [n_samples, n_features] The input samples. Returns ------- p : array of shape = [n_samples, n_classes] The class log-probabilities of the input samples. The order of the classes corresponds to that in the attribute `classes_`. RA(RRAtpredict_log_probaRL(R$R((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyRQ1s N(t__name__t __module__t__doc__R.R%tpropertyR&R'RRRKRMRNRORPRQ(((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyR $sP   S tRFECVcBs5eZdZddddddd„Zdd„ZRS(sTFeature ranking with recursive feature elimination and cross-validated selection of the best number of features. See glossary entry for :term:`cross-validation estimator`. Read more in the :ref:`User Guide `. Parameters ---------- estimator : object A supervised learning estimator with a ``fit`` method that provides information about feature importance either through a ``coef_`` attribute or through a ``feature_importances_`` attribute. step : int or float, optional (default=1) If greater than or equal to 1, then ``step`` corresponds to the (integer) number of features to remove at each iteration. If within (0.0, 1.0), then ``step`` corresponds to the percentage (rounded down) of features to remove at each iteration. Note that the last iteration may remove fewer than ``step`` features in order to reach ``min_features_to_select``. min_features_to_select : int, (default=1) The minimum number of features to be selected. This number of features will always be scored, even if the difference between the original feature count and ``min_features_to_select`` isn't divisible by ``step``. cv : int, cross-validation generator or an iterable, optional Determines the cross-validation splitting strategy. Possible inputs for cv are: - None, to use the default 3-fold cross-validation, - integer, to specify the number of folds. - :term:`CV splitter`, - An iterable yielding (train, test) splits as arrays of indices. For integer/None inputs, if ``y`` is binary or multiclass, :class:`sklearn.model_selection.StratifiedKFold` is used. If the estimator is a classifier or if ``y`` is neither binary nor multiclass, :class:`sklearn.model_selection.KFold` is used. Refer :ref:`User Guide ` for the various cross-validation strategies that can be used here. .. versionchanged:: 0.20 ``cv`` default value of None will change from 3-fold to 5-fold in v0.22. scoring : string, callable or None, optional, (default=None) A string (see model evaluation documentation) or a scorer callable object / function with signature ``scorer(estimator, X, y)``. verbose : int, (default=0) Controls verbosity of output. n_jobs : int or None, optional (default=None) Number of cores to run in parallel while fitting across 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_ : int The number of selected features with cross-validation. support_ : array of shape [n_features] The mask of selected features. ranking_ : array of shape [n_features] The feature ranking, such that `ranking_[i]` corresponds to the ranking position of the i-th feature. Selected (i.e., estimated best) features are assigned rank 1. grid_scores_ : array of shape [n_subsets_of_features] The cross-validation scores such that ``grid_scores_[i]`` corresponds to the CV score of the i-th subset of features. estimator_ : object The external estimator fit on the reduced dataset. Notes ----- The size of ``grid_scores_`` is equal to ``ceil((n_features - min_features_to_select) / step) + 1``, where step is the number of features removed at each iteration. Examples -------- The following example shows how to retrieve the a-priori not known 5 informative features in the Friedman #1 dataset. >>> from sklearn.datasets import make_friedman1 >>> from sklearn.feature_selection import RFECV >>> from sklearn.svm import SVR >>> X, y = make_friedman1(n_samples=50, n_features=10, random_state=0) >>> estimator = SVR(kernel="linear") >>> selector = RFECV(estimator, step=1, cv=5) >>> selector = selector.fit(X, y) >>> selector.support_ # doctest: +NORMALIZE_WHITESPACE array([ True, True, True, True, True, False, False, False, False, False]) >>> selector.ranking_ array([1, 1, 1, 1, 1, 6, 4, 3, 2, 5]) See also -------- RFE : Recursive feature elimination References ---------- .. [1] Guyon, I., Weston, J., Barnhill, S., & Vapnik, V., "Gene selection for cancer classification using support vector machines", Mach. Learn., 46(1-3), 389--422, 2002. itwarnicCsC||_||_||_||_||_||_||_dS(N(RR"tcvtscoringR#tn_jobstmin_features_to_select(R$RR"R[RXRYR#RZ((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyR%¾s      c s…tˆˆdƒ\‰‰tˆjˆtˆjƒƒ}tˆjdˆjƒ‰ˆjd}dˆjkoudknr™t t dˆj|ƒƒ}nt ˆjƒ}|dkrÃt dƒ‚nt dˆjd ˆj d ˆjd ˆjƒ‰tˆjƒdkrtt}‰ntd ˆjƒ}ttƒ‰|‡‡‡‡‡‡fd †|jˆˆ|ƒDƒƒ}tj|ddƒ}|ddd…} t|ƒtj| ƒd} t || |ˆj ƒ} t dˆjd | d ˆjd ˆjƒ‰ˆjˆˆƒˆjˆ_ˆjˆ_ˆjˆ_tˆjƒˆ_ˆjjˆj ˆƒˆƒ|ddd…|j!ˆˆ|ƒˆ_"ˆS(s‰Fit the RFE model and automatically tune the number of selected features. Parameters ---------- X : {array-like, sparse matrix}, shape = [n_samples, n_features] Training vector, where `n_samples` is the number of samples and `n_features` is the total number of features. y : array-like, shape = [n_samples] Target values (integers for classification, real numbers for regression). groups : array-like, shape = [n_samples], optional Group labels for the samples used while splitting the dataset into train/test set. tcsrRYiggð?isStep must be >0RR!R"R#RZc 3s6|],\}}ˆˆˆjˆˆ||ˆƒVqdS(N(R(t.0RR(RtfuncRRR$R(s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pys sR,Niÿÿÿÿ(#RR RXRRRRYR-R"R/R0R1R R[R#R RZtlistRR R tsplitR2R5tlentargmaxR'RCRBRDRRARLt get_n_splitst grid_scores_( R$RRtgroupsRXRFR"tparalleltscorest scores_revt argmax_idxR!((RR^RRR$Rs<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyR'ÈsH          )N(RRRSRTR.R%R'(((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyRVDsy  (RTtnumpyR2tutilsRRtutils.metaestimatorsRRtutils.validationRtbaseRRRRt utils._joblibR R R tmodel_selectionR tmodel_selection._validationR tmetrics.scorerRRRR RV(((s<lib/python2.7/site-packages/sklearn/feature_selection/rfe.pyts$  ÿ!