ó ‡ˆ\c@sÖdZddlZddlZddlmZddlmZddlmZddlm Z ddl m Z m Z dd l mZmZdd lmZdd lmZdd „Zd eeefd„ƒYZdS(s„ Soft Voting/Majority Rule classifier. This module contains a Soft Voting/Majority Rule classifier for classification estimators. iÿÿÿÿNi(tClassifierMixin(tTransformerMixin(tclone(t LabelEncoder(tParalleltdelayed(thas_fit_parametertcheck_is_fitted(t_BaseComposition(tBunchcCs9|dk r%|j||d|ƒn|j||ƒ|S(s7Private function used to fit an estimator within a job.t sample_weightN(tNonetfit(t estimatortXtyR ((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyt_parallel_fit_estimators tVotingClassifiercBsžeZdZddddd„Zed„ƒZdd„Zed„ƒZd„Z d„Z d„Z ed „ƒZ d „Z d „Zed „Zd „ZRS(sDSoft Voting/Majority Rule classifier for unfitted estimators. .. versionadded:: 0.17 Read more in the :ref:`User Guide `. Parameters ---------- estimators : list of (string, estimator) tuples Invoking the ``fit`` method on the ``VotingClassifier`` will fit clones of those original estimators that will be stored in the class attribute ``self.estimators_``. An estimator can be set to `None` using ``set_params``. voting : str, {'hard', 'soft'} (default='hard') If 'hard', uses predicted class labels for majority rule voting. Else if 'soft', predicts the class label based on the argmax of the sums of the predicted probabilities, which is recommended for an ensemble of well-calibrated classifiers. weights : array-like, shape = [n_classifiers], optional (default=`None`) Sequence of weights (`float` or `int`) to weight the occurrences of predicted class labels (`hard` voting) or class probabilities before averaging (`soft` voting). Uses uniform weights if `None`. n_jobs : int or None, optional (default=None) The number of jobs to run in parallel for ``fit``. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. flatten_transform : bool, optional (default=None) Affects shape of transform output only when voting='soft' If voting='soft' and flatten_transform=True, transform method returns matrix with shape (n_samples, n_classifiers * n_classes). If flatten_transform=False, it returns (n_classifiers, n_samples, n_classes). Attributes ---------- estimators_ : list of classifiers The collection of fitted sub-estimators as defined in ``estimators`` that are not `None`. named_estimators_ : Bunch object, a dictionary with attribute access Attribute to access any fitted sub-estimators by name. .. versionadded:: 0.20 classes_ : array-like, shape = [n_predictions] The classes labels. Examples -------- >>> import numpy as np >>> from sklearn.linear_model import LogisticRegression >>> from sklearn.naive_bayes import GaussianNB >>> from sklearn.ensemble import RandomForestClassifier, VotingClassifier >>> clf1 = LogisticRegression(solver='lbfgs', multi_class='multinomial', ... random_state=1) >>> clf2 = RandomForestClassifier(n_estimators=50, random_state=1) >>> clf3 = GaussianNB() >>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]]) >>> y = np.array([1, 1, 1, 2, 2, 2]) >>> eclf1 = VotingClassifier(estimators=[ ... ('lr', clf1), ('rf', clf2), ('gnb', clf3)], voting='hard') >>> eclf1 = eclf1.fit(X, y) >>> print(eclf1.predict(X)) [1 1 1 2 2 2] >>> np.array_equal(eclf1.named_estimators_.lr.predict(X), ... eclf1.named_estimators_['lr'].predict(X)) True >>> eclf2 = VotingClassifier(estimators=[ ... ('lr', clf1), ('rf', clf2), ('gnb', clf3)], ... voting='soft') >>> eclf2 = eclf2.fit(X, y) >>> print(eclf2.predict(X)) [1 1 1 2 2 2] >>> eclf3 = VotingClassifier(estimators=[ ... ('lr', clf1), ('rf', clf2), ('gnb', clf3)], ... voting='soft', weights=[2,1,1], ... flatten_transform=True) >>> eclf3 = eclf3.fit(X, y) >>> print(eclf3.predict(X)) [1 1 1 2 2 2] >>> print(eclf3.transform(X).shape) (6, 6) thardcCs1||_||_||_||_||_dS(N(t estimatorstvotingtweightstn_jobstflatten_transform(tselfRRRRR((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyt__init__~s     cCstt|jƒS(N(R tdictR(R((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pytnamed_estimators†sc sxt|tjƒrIt|jƒdkrI|jddkrItdƒ‚n|jdkrntd|jƒ‚n|jdks’t|jƒdkr¡t dƒ‚n|j dk rùt|j ƒt|jƒkrùtdt|j ƒt|jƒfƒ‚nˆdk rDx<|jD].\}}t |d ƒstd |ƒ‚qqWnt |jŒ\}}|j|ƒtjg|jD]\}} | dk^qvƒ} | t|jƒkr»td ƒ‚ntƒj|ƒ|_|jj|_g|_|jj|ƒ‰td |jƒ‡‡‡fd †|Dƒƒ|_ttƒ|_x4t |j|jƒD]\} } | |j| dÆs(RRN(t isinstancetnptndarraytlentshapetNotImplementedErrorRt ValueErrorRR tAttributeErrorRRtzipt_validate_namestsumRR tle_tclasses_t estimators_t transformRRR Rtnamed_estimators_( RRRR tnametsteptnamestclfst_Rtn_isnonetkte((RR RsAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyR Šs@:$%  1 "cCsO|jdkrdSgt|j|jƒD]"\}}|ddk r)|^q)S(s(Get the weights of not `None` estimatorsiN(RR R(R(Rtesttw((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyt_weights_not_noneÏs cs†tˆdƒˆjdkr=tjˆj|ƒddƒ}n3ˆj|ƒ}tj‡fd†ddd|ƒ}ˆjj|ƒ}|S(s* Predict class labels for X. Parameters ---------- X : {array-like, sparse matrix}, shape = [n_samples, n_features] The input samples. Returns ---------- maj : array-like, shape = [n_samples] Predicted class labels. R-Rtaxisicstjtj|dˆjƒƒS(NR(R!targmaxtbincountR:(tx(R(sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pytìstarr( RRR!R<t predict_probat_predicttapply_along_axisR+tinverse_transform(RRtmajt predictions((RsAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pytpredict×s !cCs,tjg|jD]}|j|ƒ^qƒS(s(Collect results from clf.predict calls. (R!tasarrayR-RA(RRR((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyt_collect_probasôscCs]|jdkr%td|jƒ‚nt|dƒtj|j|ƒddd|jƒ}|S(s3Predict class probabilities for X in 'soft' voting Rs-predict_proba is not available when voting=%rR-R;iR(RR'RR!taverageRIR:(RRtavg((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyt_predict_probaøs  cCs|jS(suCompute probabilities of possible outcomes for samples in X. Parameters ---------- X : {array-like, sparse matrix}, shape = [n_samples, n_features] The input samples. Returns ---------- avg : array-like, shape = [n_samples, n_classes] Weighted average probability for each class per sample. (RL(R((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyRAscCs|t|dƒ|jdkrk|j|ƒ}|jdkrNtjdtƒ|S|js[|Stj |ƒSn |j |ƒSdS(s‡Return class labels or probabilities for X for each estimator. Parameters ---------- X : {array-like, sparse matrix}, shape = [n_samples, n_features] Training vectors, where n_samples is the number of samples and n_features is the number of features. Returns ------- probabilities_or_labels If `voting='soft'` and `flatten_transform=True`: returns array-like of shape (n_classifiers, n_samples * n_classes), being class probabilities calculated by each classifier. If `voting='soft' and `flatten_transform=False`: array-like of shape (n_classifiers, n_samples, n_classes) If `voting='hard'`: array-like of shape (n_samples, n_classifiers), being class labels predicted by each classifier. R-RsŠ'flatten_transform' default value will be changed to True in 0.21. To silence this warning you may explicitly set flatten_transform=False.N( RRRIRR twarningstwarntDeprecationWarningR!thstackRB(RRtprobas((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyR.s   cKstt|ƒjd||S(s Setting the parameters for the voting classifier Valid parameter keys can be listed with get_params(). Parameters ---------- **params : keyword arguments Specific parameters using e.g. set_params(parameter_name=new_value) In addition, to setting the parameters of the ``VotingClassifier``, the individual classifiers of the ``VotingClassifier`` can also be set or replaced by setting them to None. Examples -------- # In this example, the RandomForestClassifier is removed clf1 = LogisticRegression() clf2 = RandomForestClassifier() eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2)] eclf.set_params(rf=None) R(tsuperRt _set_params(Rtparams((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyt set_params;scCstt|ƒjdd|ƒS(så Get the parameters of the VotingClassifier Parameters ---------- deep : bool Setting it to True gets the various classifiers and the parameters of the classifiers as well Rtdeep(RRRt _get_params(RRV((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyt get_paramsTs cCs/tjg|jD]}|j|ƒ^qƒjS(s(Collect results from clf.predict calls. (R!RHR-RGtT(RRR((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyRB`sN(t__name__t __module__t__doc__R RtpropertyRR R:RGRIRLRAR.RUtTrueRXRB(((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyR$sX   E    )  (R\tnumpyR!RMtbaseRRRt preprocessingRt utils._joblibRRtutils.validationRRtutils.metaestimatorsRtutilsR R RR(((sAlib/python2.7/site-packages/sklearn/ensemble/voting_classifier.pyts