\c@ sdZddlmZddlmZmZmZddlZddlm Z m Z ddl Z ddl mZddl mZdd lmZmZdd lmZmZdd lmZdd lmZdd lmZddlmZmZm Z m!Z!ddl"m#Z#m$Z$ddl%m&Z&m'Z'm(Z(ddl)m*Z*m+Z+ddlm,Z,m-Z-ddl.m/Z/m0Z0ddl1m2Z2ddl3m4Z4dddddgZ5e j6e j7j8Z9dZ:dZ;de<dZ=d ej>e e,fd!YZ?d"Z@d#ej>e e?efd$YZAd%ej>e e?efd&YZBdeAfd'YZCdeBfd(YZDdeAfd)YZEdeBfd*YZFde?fd+YZGdS(,s1Forest of trees-based ensemble methods Those methods include random forests and extremely randomized trees. The module structure is the following: - The ``BaseForest`` base class implements a common ``fit`` method for all the estimators in the module. The ``fit`` method of the base ``Forest`` class calls the ``fit`` method of each sub-estimator on random samples (with replacement, a.k.a. bootstrap) of the training set. The init of the sub-estimator is further delegated to the ``BaseEnsemble`` constructor. - The ``ForestClassifier`` and ``ForestRegressor`` base classes further implement the prediction logic by computing an average of the predicted outcomes of the sub-estimators. - The ``RandomForestClassifier`` and ``RandomForestRegressor`` derived classes provide the user with concrete implementations of the forest ensemble method using classical, deterministic ``DecisionTreeClassifier`` and ``DecisionTreeRegressor`` as sub-estimator implementations. - The ``ExtraTreesClassifier`` and ``ExtraTreesRegressor`` derived classes provide the user with concrete implementations of the forest ensemble method using the extremely randomized trees ``ExtraTreeClassifier`` and ``ExtraTreeRegressor`` as sub-estimator implementations. Single and multi-output problems are both handled. i(tdivision(tcatch_warningst simplefiltertwarnN(tABCMetatabstractmethod(tissparse(thstacki(tClassifierMixintRegressorMixin(tParalleltdelayed(tsix(tr2_score(t OneHotEncoder(tDecisionTreeClassifiertDecisionTreeRegressortExtraTreeClassifiertExtraTreeRegressor(tDTYPEtDOUBLE(tcheck_random_statet check_arraytcompute_sample_weight(tDataConversionWarningtNotFittedErrori(t BaseEnsemblet_partition_estimators(tparallel_helpert_joblib_parallel_args(tcheck_classification_targets(tcheck_is_fittedtRandomForestClassifiertRandomForestRegressortExtraTreesClassifiertExtraTreesRegressortRandomTreesEmbeddingcC s%t|}|jd||}|S(s8Private function used to _parallel_build_trees function.i(Rtrandint(t random_statet n_samplestrandom_instancetsample_indices((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyt_generate_sample_indicesLs cC sMt||}tj|d|}|dk}tj|}||}|S(s8Private function used to forest._set_oob_score function.t minlengthi(R*tnptbincounttarange(R&R'R)t sample_countstunsampled_maskt indices_rangetunsampled_indices((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyt_generate_unsampled_indicesTs   ic C sE|dkr"d|d|fGHn|jr%|jd} |d krbtj| fdtj} n |j} t|j| } tj | d| } | | 9} |dkrt (t dt | t d|| 9} Wd QXn%|d kr| t d || 9} n|j||d | d tn|j||d |d t|S(s7Private function used to fit a single tree in parallel.isbuilding tree %d of %ditdtypeR+t subsampletignoretautoNtbalanced_subsampletbalancedt sample_weightt check_input(t bootstraptshapetNoneR,tonestfloat64tcopyR*R&R-RRtDeprecationWarningRtfittFalse( ttreetforesttXtyR:ttree_idxtn_treestverboset class_weightR'tcurr_sample_weighttindicesR/((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyt_parallel_build_trees_s&          t BaseForestc B seZdZedeeed d ded d ZdZdZ d dZ edZ dZ d Z ed ZRS( s|Base class for forests of trees. Warning: This class should not be used directly. Use derived classes instead. idic C shtt|jd|d|d|||_||_||_||_||_| |_| |_ dS(Ntbase_estimatort n_estimatorstestimator_params( tsuperRPt__init__R<t oob_scoretn_jobsR&RKt warm_startRL( tselfRQRRRSR<RVRWR&RKRXRL((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRUs       c s_|jtd|jd|jtddfd|jD}tj|jS(sXApply trees in the forest to X, return leaf indices. Parameters ---------- X : array-like or sparse matrix, shape = [n_samples, n_features] The input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csr_matrix``. Returns ------- X_leaves : array_like, shape = [n_samples, n_estimators] For each datapoint x in X and for each tree in the forest, return the index of the leaf x ends up in. RWRKtprefertthreadsc3 s-|]#}tt|ddtVqdS(tapplyR;N(R RRD(t.0RE(RG(s6lib/python2.7/site-packages/sklearn/ensemble/forest.pys s( t_validate_X_predictR RWRKRt estimators_R,tarraytT(RYRGtresults((RGs6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR\s  c s|jtd|jd|jtddfd|jD}dg}|jg|D]}|jd^qetj |j }t |j |fS(s1Return the decision path in the forest .. versionadded:: 0.18 Parameters ---------- X : array-like or sparse matrix, shape = [n_samples, n_features] The input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csr_matrix``. Returns ------- indicator : sparse csr array, shape = [n_samples, n_nodes] Return a node indicator matrix where non zero elements indicates that the samples goes through the nodes. n_nodes_ptr : array of size (n_estimators + 1, ) The columns from indicator[n_nodes_ptr[i]:n_nodes_ptr[i+1]] gives the indicator value for the i-th estimator. RWRKRZR[c3 s-|]#}tt|ddtVqdS(t decision_pathR;N(R RRD(R]RE(RG(s6lib/python2.7/site-packages/sklearn/ensemble/forest.pys sii( R^R RWRKRR_textendR=R,R`tcumsumt sparse_hstackttocsr(RYRGt indicatorstn_nodestit n_nodes_ptr((RGs6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRcs  'c  sjdkr(tdtd_ntdddttdddtdddk rtdtntrjnj d_ t j j d krj ddkrtd td d nj dkrt jdnj d_j\}tddtks]jj rut jdtn|dk rdk r|q|njj rjrtd ntj}j std rg_njt j}|dkrKtdjt jfn|dkrdtdnjrt jdkr|j!t"dt jngx9t#|D]+}j$dtd|}j%|qWt&dj'dj(t)ddfdt*Djj+jr^j,ntdrjdkrj-d_-j.d_.nS(s0Build a forest of trees from the training set (X, y). Parameters ---------- X : array-like or sparse matrix of shape = [n_samples, n_features] The training input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csc_matrix``. y : array-like, shape = [n_samples] or [n_samples, n_outputs] The target values (class labels in classification, real numbers in regression). sample_weight : array-like, shape = [n_samples] or None Sample weights. If None, then samples are equally weighted. Splits that would create child nodes with net zero or negative weight are ignored while searching for a split in each node. In the case of classification, splits are also ignored if they would result in any single class carrying a negative weight in either child node. Returns ------- self : object RsUThe default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.i t accept_sparsetcscR4t ensure_2diisA column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().t stacklevelis6Out of bag estimation only available if bootstrap=TrueR_isTn_estimators=%d must be larger or equal to len(estimators_)=%d when warm_start==TruesJWarm-start fitting without increasing n_estimators does not fit new trees.tsizetappendR&RWRKRZR[c 3 sQ|]G\}}tt||tdjdjVqdS(RKRLN(R ROtlenRKRL(R]Rjtt(RGR:RYttreesRH(s6lib/python2.7/site-packages/sklearn/ensemble/forest.pys Jstclasses_N(ii(/RRRt FutureWarningRRRDR>Rt sort_indicesR=t n_features_R,t atleast_1dtndimRtreshapet n_outputs_t_validate_y_class_weighttgetattrRtflagst contiguoustascontiguousarrayt_validate_estimatorR<RVt ValueErrorRR&RXthasattrR_RrR%tMAX_INTtranget_make_estimatorRqR RWRKRt enumerateRdt_set_oob_scoret n_classes_Ru( RYRGRHR:texpanded_class_weightR&tn_more_estimatorsRjRE((RGR:RYRtRHs6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRCsn    "%           cC sdS(s+Calculate out of bag predictions and score.N((RYRGRH((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR\scC s |dfS(N(R>(RYRH((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR}`scC sM|jdks$t|jdkr3tdn|jdj|dtS(s>Validate X whenever one tries to predict, apply, predict_probais=Estimator not fitted, call `fit` before exploiting the model.R;N(R_R>RrRR^tTrue(RYRG((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR^ds$cC sUt|dtd|jtddd|jD}t|t|jS(sReturn the feature importances (the higher, the more important the feature). Returns ------- feature_importances_ : array, shape = [n_features] R_RWRZR[cs s$|]}tt|dVqdS(tfeature_importances_N(R R~(R]RE((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pys ys(RR RWRR_tsumRr(RYtall_importances((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRls  N(t__name__t __module__t__doc__RttupleRDR>RUR\RcRCRR}R^tpropertyR(((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRP~s$  $   c C sy||dt}|[t|dkr>|dc|7td|jn|jrWtdqWn|jdksp|j r|jdkrd}n |j}t||}qn||fS( NR4treturn_inverseiR9R8sWValid presets for class_weight include "balanced" and "balanced_subsample". Given "%s".sclass_weight presets "balanced" or "balanced_subsample" are not recommended for warm_start if the fitted data differs from the full dataset. In order to use "balanced" weights, use compute_class_weight("balanced", classes, y). In place of y you can use a large enough sample of the full training set target to properly estimate the class frequency distributions. Pass the resulting weights as the class_weight parameter.(R9R8(RR,RAR>RLRuRRR=tintRR|tuniqueRRqt isinstanceR t string_typesRRXRR<R( RYRHRt y_originalty_store_unique_indicesRt classes_kt valid_presetsRL((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR}s:   ;     cC s|j|}|jdkrC|jjtj|ddddS|djd}tj||jf}xVt|jD]E}|j|jtj||dddd|dd|f 1. The class probabilities of the input samples. The order of the classes corresponds to that in the attribute `classes_`. R_iR4RWRKtrequiret sharedmemc3 s-|]#}tt|jVqdS(N(R RR(R]te(RGt all_probaR(s6lib/python2.7/site-packages/sklearn/ensemble/forest.pys RsiN(RR^RRRRWR,RyRRR=R@t threadingtLockR RKRR_Rr(RYRGRWt_tjR((RGRRs6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR/s A  cC sd|j|}|jdkr+tj|Sx.t|jD]}tj|||| 1. The class probabilities of the input samples. The order of the classes corresponds to that in the attribute `classes_`. iN(RR|R,tlogR(RYRGRR((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pytpredict_log_proba^s  N( RRRRRRDR>RURR}RRR(((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRs  - 0 $ /tForestRegressorc B sJeZdZedeeedddedZdZdZ RS(sBase class for forest of trees-based regressors. Warning: This class should not be used directly. Use derived classes instead. idic C sJtt|j|d|d|d|d|d|d|d|d| dS( NRRRSR<RVRWR&RKRX(RTRRU( RYRQRRRSR<RVRWR&RKRX((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRUs c st|d|jt|j|j\}}}|jdkrttjjd|jfdtj ntjjddtj t j t d|d|j tddfd |jDt|jS( sPredict regression target for X. The predicted regression target of an input sample is computed as the mean predicted regression targets of the trees in the forest. Parameters ---------- X : array-like or sparse matrix of shape = [n_samples, n_features] The input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csr_matrix``. Returns ------- y : array of shape = [n_samples] or [n_samples, n_outputs] The predicted values. R_iiR4RWRKRRc3 s0|]&}tt|jgVqdS(N(R RR(R]R(RGRty_hat(s6lib/python2.7/site-packages/sklearn/ensemble/forest.pys s(RR^RRRRWR|R,RR=R@RRR RKRR_Rr(RYRGRWR((RGRRs6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRs + c C st|dtdd}|jd}tj||jf}tj||jf}x|jD]}t|j|}|j ||ddfdt }|jdkr|ddtj f}n||ddfc|7<||ddfcd7} |jt|dd| f|dd| f7_qW|j|j_dS( sCompute out-of-bag scoresR4RlRiNR;isvSome inputs do not have OOB scores. This probably means too few trees were used to compute any reliable oob estimates.g(RRR=R,RR|R_R3R&RRDRRRtoob_prediction_R{RRR ( RYRGRHR'Rt n_predictionsRR2RR((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRs2      N( RRRRRRDR>RURR(((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRs *cB sJeZdZddd ddddd dd eed d ded dZRS( sx*A random forest classifier. A random forest is a meta estimator that fits a number of decision tree classifiers on various sub-samples of the dataset and uses averaging to improve the predictive accuracy and control over-fitting. The sub-sample size is always the same as the original input sample size but the samples are drawn with replacement if `bootstrap=True` (default). Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) The number of trees in the forest. .. versionchanged:: 0.20 The default value of ``n_estimators`` will change from 10 in version 0.20 to 100 in version 0.22. criterion : string, optional (default="gini") The function to measure the quality of a split. Supported criteria are "gini" for the Gini impurity and "entropy" for the information gain. Note: this parameter is tree-specific. max_depth : integer or None, optional (default=None) The maximum depth of the tree. If None, then nodes are expanded until all leaves are pure or until all leaves contain less than min_samples_split samples. min_samples_split : int, float, optional (default=2) The minimum number of samples required to split an internal node: - If int, then consider `min_samples_split` as the minimum number. - If float, then `min_samples_split` is a fraction and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for fractions. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node. A split point at any depth will only be considered if it leaves at least ``min_samples_leaf`` training samples in each of the left and right branches. This may have the effect of smoothing the model, especially in regression. - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a fraction and `ceil(min_samples_leaf * n_samples)` are the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for fractions. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node. Samples have equal weight when sample_weight is not provided. max_features : int, float, string or None, optional (default="auto") The number of features to consider when looking for the best split: - If int, then consider `max_features` features at each split. - If float, then `max_features` is a fraction and `int(max_features * n_features)` features are considered at each split. - If "auto", then `max_features=sqrt(n_features)`. - If "sqrt", then `max_features=sqrt(n_features)` (same as "auto"). - If "log2", then `max_features=log2(n_features)`. - If None, then `max_features=n_features`. Note: the search for a split does not stop until at least one valid partition of the node samples is found, even if it requires to effectively inspect more than ``max_features`` features. max_leaf_nodes : int or None, optional (default=None) Grow trees with ``max_leaf_nodes`` in best-first fashion. Best nodes are defined as relative reduction in impurity. If None then unlimited number of leaf nodes. min_impurity_decrease : float, optional (default=0.) A node will be split if this split induces a decrease of the impurity greater than or equal to this value. The weighted impurity decrease equation is the following:: N_t / N * (impurity - N_t_R / N_t * right_impurity - N_t_L / N_t * left_impurity) where ``N`` is the total number of samples, ``N_t`` is the number of samples at the current node, ``N_t_L`` is the number of samples in the left child, and ``N_t_R`` is the number of samples in the right child. ``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum, if ``sample_weight`` is passed. .. versionadded:: 0.19 min_impurity_split : float, (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. deprecated:: 0.19 ``min_impurity_split`` has been deprecated in favor of ``min_impurity_decrease`` in 0.19. The default value of ``min_impurity_split`` will change from 1e-7 to 0 in 0.23 and it will be removed in 0.25. Use ``min_impurity_decrease`` instead. bootstrap : boolean, optional (default=True) Whether bootstrap samples are used when building trees. If False, the whole datset is used to build each tree. oob_score : bool (default=False) Whether to use out-of-bag samples to estimate the generalization accuracy. n_jobs : int or None, optional (default=None) The number of jobs to run in parallel for both `fit` and `predict`. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity when fitting and predicting. warm_start : bool, optional (default=False) When set to ``True``, reuse the solution of the previous call to fit and add more estimators to the ensemble, otherwise, just fit a whole new forest. See :term:`the Glossary `. class_weight : dict, list of dicts, "balanced", "balanced_subsample" or None, optional (default=None) Weights associated with classes in the form ``{class_label: weight}``. If not given, all classes are supposed to have weight one. For multi-output problems, a list of dicts can be provided in the same order as the columns of y. Note that for multioutput (including multilabel) weights should be defined for each class of every column in its own dict. For example, for four-class multilabel classification weights should be [{0: 1, 1: 1}, {0: 1, 1: 5}, {0: 1, 1: 1}, {0: 1, 1: 1}] instead of [{1:1}, {2:5}, {3:1}, {4:1}]. The "balanced" mode uses the values of y to automatically adjust weights inversely proportional to class frequencies in the input data as ``n_samples / (n_classes * np.bincount(y))`` The "balanced_subsample" mode is the same as "balanced" except that weights are computed based on the bootstrap sample for every tree grown. For multi-output, the weights of each column of y will be multiplied. Note that these weights will be multiplied with sample_weight (passed through the fit method) if sample_weight is specified. Attributes ---------- estimators_ : list of DecisionTreeClassifier The collection of fitted sub-estimators. classes_ : array of shape = [n_classes] or a list of such arrays The classes labels (single output problem), or a list of arrays of class labels (multi-output problem). n_classes_ : int or list The number of classes (single output problem), or a list containing the number of classes for each output (multi-output problem). n_features_ : int The number of features when ``fit`` is performed. n_outputs_ : int The number of outputs when ``fit`` is performed. feature_importances_ : array of shape = [n_features] The feature importances (the higher, the more important the feature). oob_score_ : float Score of the training dataset obtained using an out-of-bag estimate. oob_decision_function_ : array of shape = [n_samples, n_classes] Decision function computed with out-of-bag estimate on the training set. If n_estimators is small it might be possible that a data point was never left out during the bootstrap. In this case, `oob_decision_function_` might contain NaN. Examples -------- >>> from sklearn.ensemble import RandomForestClassifier >>> from sklearn.datasets import make_classification >>> X, y = make_classification(n_samples=1000, n_features=4, ... n_informative=2, n_redundant=0, ... random_state=0, shuffle=False) >>> clf = RandomForestClassifier(n_estimators=100, max_depth=2, ... random_state=0) >>> clf.fit(X, y) RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini', max_depth=2, max_features='auto', max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=0, verbose=0, warm_start=False) >>> print(clf.feature_importances_) [0.14205973 0.76664038 0.0282433 0.06305659] >>> print(clf.predict([[0, 0, 0, 0]])) [1] Notes ----- The default values for the parameters controlling the size of the trees (e.g. ``max_depth``, ``min_samples_leaf``, etc.) lead to fully grown and unpruned trees which can potentially be very large on some data sets. To reduce memory consumption, the complexity and size of the trees should be controlled by setting those parameter values. The features are always randomly permuted at each split. Therefore, the best found split may vary, even with the same training data, ``max_features=n_features`` and ``bootstrap=False``, if the improvement of the criterion is identical for several splits enumerated during the search of the best split. To obtain a deterministic behaviour during fitting, ``random_state`` has to be fixed. References ---------- .. [1] L. Breiman, "Random Forests", Machine Learning, 45(1), 5-32, 2001. See also -------- DecisionTreeClassifier, ExtraTreesClassifier RtginiiigR7icC stt|jdtd|ddd| d| d| d |d|d|d| ||_||_||_||_||_||_ ||_ | |_ | |_ dS(NRQRRRSt criteriont max_depthtmin_samples_splittmin_samples_leaftmin_weight_fraction_leaft max_featurestmax_leaf_nodestmin_impurity_decreasetmin_impurity_splitR&R<RVRWRKRXRL( RRRRRRRRRR&( RTR RURRRRRRRRRR(RYRRRRRRRRRRRR<RVRWR&RKRXRL((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRUs0         N(RRRR>RRDRU(((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR s$cB sGeZdZddd ddddd dd eed d dedZRS( s$A random forest regressor. A random forest is a meta estimator that fits a number of classifying decision trees on various sub-samples of the dataset and uses averaging to improve the predictive accuracy and control over-fitting. The sub-sample size is always the same as the original input sample size but the samples are drawn with replacement if `bootstrap=True` (default). Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) The number of trees in the forest. .. versionchanged:: 0.20 The default value of ``n_estimators`` will change from 10 in version 0.20 to 100 in version 0.22. criterion : string, optional (default="mse") The function to measure the quality of a split. Supported criteria are "mse" for the mean squared error, which is equal to variance reduction as feature selection criterion, and "mae" for the mean absolute error. .. versionadded:: 0.18 Mean Absolute Error (MAE) criterion. max_depth : integer or None, optional (default=None) The maximum depth of the tree. If None, then nodes are expanded until all leaves are pure or until all leaves contain less than min_samples_split samples. min_samples_split : int, float, optional (default=2) The minimum number of samples required to split an internal node: - If int, then consider `min_samples_split` as the minimum number. - If float, then `min_samples_split` is a fraction and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for fractions. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node. A split point at any depth will only be considered if it leaves at least ``min_samples_leaf`` training samples in each of the left and right branches. This may have the effect of smoothing the model, especially in regression. - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a fraction and `ceil(min_samples_leaf * n_samples)` are the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for fractions. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node. Samples have equal weight when sample_weight is not provided. max_features : int, float, string or None, optional (default="auto") The number of features to consider when looking for the best split: - If int, then consider `max_features` features at each split. - If float, then `max_features` is a fraction and `int(max_features * n_features)` features are considered at each split. - If "auto", then `max_features=n_features`. - If "sqrt", then `max_features=sqrt(n_features)`. - If "log2", then `max_features=log2(n_features)`. - If None, then `max_features=n_features`. Note: the search for a split does not stop until at least one valid partition of the node samples is found, even if it requires to effectively inspect more than ``max_features`` features. max_leaf_nodes : int or None, optional (default=None) Grow trees with ``max_leaf_nodes`` in best-first fashion. Best nodes are defined as relative reduction in impurity. If None then unlimited number of leaf nodes. min_impurity_decrease : float, optional (default=0.) A node will be split if this split induces a decrease of the impurity greater than or equal to this value. The weighted impurity decrease equation is the following:: N_t / N * (impurity - N_t_R / N_t * right_impurity - N_t_L / N_t * left_impurity) where ``N`` is the total number of samples, ``N_t`` is the number of samples at the current node, ``N_t_L`` is the number of samples in the left child, and ``N_t_R`` is the number of samples in the right child. ``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum, if ``sample_weight`` is passed. .. versionadded:: 0.19 min_impurity_split : float, (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. deprecated:: 0.19 ``min_impurity_split`` has been deprecated in favor of ``min_impurity_decrease`` in 0.19. The default value of ``min_impurity_split`` will change from 1e-7 to 0 in 0.23 and it will be removed in 0.25. Use ``min_impurity_decrease`` instead. bootstrap : boolean, optional (default=True) Whether bootstrap samples are used when building trees. If False, the whole datset is used to build each tree. oob_score : bool, optional (default=False) whether to use out-of-bag samples to estimate the R^2 on unseen data. n_jobs : int or None, optional (default=None) The number of jobs to run in parallel for both `fit` and `predict`. `None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity when fitting and predicting. warm_start : bool, optional (default=False) When set to ``True``, reuse the solution of the previous call to fit and add more estimators to the ensemble, otherwise, just fit a whole new forest. See :term:`the Glossary `. Attributes ---------- estimators_ : list of DecisionTreeRegressor The collection of fitted sub-estimators. feature_importances_ : array of shape = [n_features] The feature importances (the higher, the more important the feature). n_features_ : int The number of features when ``fit`` is performed. n_outputs_ : int The number of outputs when ``fit`` is performed. oob_score_ : float Score of the training dataset obtained using an out-of-bag estimate. oob_prediction_ : array of shape = [n_samples] Prediction computed with out-of-bag estimate on the training set. Examples -------- >>> from sklearn.ensemble import RandomForestRegressor >>> from sklearn.datasets import make_regression >>> X, y = make_regression(n_features=4, n_informative=2, ... random_state=0, shuffle=False) >>> regr = RandomForestRegressor(max_depth=2, random_state=0, ... n_estimators=100) >>> regr.fit(X, y) RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=2, max_features='auto', max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=0, verbose=0, warm_start=False) >>> print(regr.feature_importances_) [0.18146984 0.81473937 0.00145312 0.00233767] >>> print(regr.predict([[0, 0, 0, 0]])) [-8.32987858] Notes ----- The default values for the parameters controlling the size of the trees (e.g. ``max_depth``, ``min_samples_leaf``, etc.) lead to fully grown and unpruned trees which can potentially be very large on some data sets. To reduce memory consumption, the complexity and size of the trees should be controlled by setting those parameter values. The features are always randomly permuted at each split. Therefore, the best found split may vary, even with the same training data, ``max_features=n_features`` and ``bootstrap=False``, if the improvement of the criterion is identical for several splits enumerated during the search of the best split. To obtain a deterministic behaviour during fitting, ``random_state`` has to be fixed. The default value ``max_features="auto"`` uses ``n_features`` rather than ``n_features / 3``. The latter was originally suggested in [1], whereas the former was more recently justified empirically in [2]. References ---------- .. [1] L. Breiman, "Random Forests", Machine Learning, 45(1), 5-32, 2001. .. [2] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees", Machine Learning, 63(1), 3-42, 2006. See also -------- DecisionTreeRegressor, ExtraTreesRegressor RtmseiigR7icC stt|jdtd|ddd| d| d| d |d|d| ||_||_||_||_||_||_ ||_ | |_ | |_ dS(NRQRRRSRRRRRRRRRR&R<RVRWRKRX( RRRRRRRRRR&( RTR!RURRRRRRRRRR(RYRRRRRRRRRRRR<RVRWR&RKRX((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRUs.         N(RRRR>RRDRU(((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR!s"cB sJeZdZddd ddddd dd eed d ded dZRS( s$An extra-trees classifier. This class implements a meta estimator that fits a number of randomized decision trees (a.k.a. extra-trees) on various sub-samples of the dataset and uses averaging to improve the predictive accuracy and control over-fitting. Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) The number of trees in the forest. .. versionchanged:: 0.20 The default value of ``n_estimators`` will change from 10 in version 0.20 to 100 in version 0.22. criterion : string, optional (default="gini") The function to measure the quality of a split. Supported criteria are "gini" for the Gini impurity and "entropy" for the information gain. max_depth : integer or None, optional (default=None) The maximum depth of the tree. If None, then nodes are expanded until all leaves are pure or until all leaves contain less than min_samples_split samples. min_samples_split : int, float, optional (default=2) The minimum number of samples required to split an internal node: - If int, then consider `min_samples_split` as the minimum number. - If float, then `min_samples_split` is a fraction and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for fractions. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node. A split point at any depth will only be considered if it leaves at least ``min_samples_leaf`` training samples in each of the left and right branches. This may have the effect of smoothing the model, especially in regression. - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a fraction and `ceil(min_samples_leaf * n_samples)` are the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for fractions. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node. Samples have equal weight when sample_weight is not provided. max_features : int, float, string or None, optional (default="auto") The number of features to consider when looking for the best split: - If int, then consider `max_features` features at each split. - If float, then `max_features` is a fraction and `int(max_features * n_features)` features are considered at each split. - If "auto", then `max_features=sqrt(n_features)`. - If "sqrt", then `max_features=sqrt(n_features)`. - If "log2", then `max_features=log2(n_features)`. - If None, then `max_features=n_features`. Note: the search for a split does not stop until at least one valid partition of the node samples is found, even if it requires to effectively inspect more than ``max_features`` features. max_leaf_nodes : int or None, optional (default=None) Grow trees with ``max_leaf_nodes`` in best-first fashion. Best nodes are defined as relative reduction in impurity. If None then unlimited number of leaf nodes. min_impurity_decrease : float, optional (default=0.) A node will be split if this split induces a decrease of the impurity greater than or equal to this value. The weighted impurity decrease equation is the following:: N_t / N * (impurity - N_t_R / N_t * right_impurity - N_t_L / N_t * left_impurity) where ``N`` is the total number of samples, ``N_t`` is the number of samples at the current node, ``N_t_L`` is the number of samples in the left child, and ``N_t_R`` is the number of samples in the right child. ``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum, if ``sample_weight`` is passed. .. versionadded:: 0.19 min_impurity_split : float, (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. deprecated:: 0.19 ``min_impurity_split`` has been deprecated in favor of ``min_impurity_decrease`` in 0.19. The default value of ``min_impurity_split`` will change from 1e-7 to 0 in 0.23 and it will be removed in 0.25. Use ``min_impurity_decrease`` instead. bootstrap : boolean, optional (default=False) Whether bootstrap samples are used when building trees. If False, the whole datset is used to build each tree. oob_score : bool, optional (default=False) Whether to use out-of-bag samples to estimate the generalization accuracy. n_jobs : int or None, optional (default=None) The number of jobs to run in parallel for both `fit` and `predict`. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity when fitting and predicting. warm_start : bool, optional (default=False) When set to ``True``, reuse the solution of the previous call to fit and add more estimators to the ensemble, otherwise, just fit a whole new forest. See :term:`the Glossary `. class_weight : dict, list of dicts, "balanced", "balanced_subsample" or None, optional (default=None) Weights associated with classes in the form ``{class_label: weight}``. If not given, all classes are supposed to have weight one. For multi-output problems, a list of dicts can be provided in the same order as the columns of y. Note that for multioutput (including multilabel) weights should be defined for each class of every column in its own dict. For example, for four-class multilabel classification weights should be [{0: 1, 1: 1}, {0: 1, 1: 5}, {0: 1, 1: 1}, {0: 1, 1: 1}] instead of [{1:1}, {2:5}, {3:1}, {4:1}]. The "balanced" mode uses the values of y to automatically adjust weights inversely proportional to class frequencies in the input data as ``n_samples / (n_classes * np.bincount(y))`` The "balanced_subsample" mode is the same as "balanced" except that weights are computed based on the bootstrap sample for every tree grown. For multi-output, the weights of each column of y will be multiplied. Note that these weights will be multiplied with sample_weight (passed through the fit method) if sample_weight is specified. Attributes ---------- estimators_ : list of DecisionTreeClassifier The collection of fitted sub-estimators. classes_ : array of shape = [n_classes] or a list of such arrays The classes labels (single output problem), or a list of arrays of class labels (multi-output problem). n_classes_ : int or list The number of classes (single output problem), or a list containing the number of classes for each output (multi-output problem). feature_importances_ : array of shape = [n_features] The feature importances (the higher, the more important the feature). n_features_ : int The number of features when ``fit`` is performed. n_outputs_ : int The number of outputs when ``fit`` is performed. oob_score_ : float Score of the training dataset obtained using an out-of-bag estimate. oob_decision_function_ : array of shape = [n_samples, n_classes] Decision function computed with out-of-bag estimate on the training set. If n_estimators is small it might be possible that a data point was never left out during the bootstrap. In this case, `oob_decision_function_` might contain NaN. Notes ----- The default values for the parameters controlling the size of the trees (e.g. ``max_depth``, ``min_samples_leaf``, etc.) lead to fully grown and unpruned trees which can potentially be very large on some data sets. To reduce memory consumption, the complexity and size of the trees should be controlled by setting those parameter values. References ---------- .. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees", Machine Learning, 63(1), 3-42, 2006. See also -------- sklearn.tree.ExtraTreeClassifier : Base classifier for this ensemble. RandomForestClassifier : Ensemble Classifier based on trees with optimal splits. RRiigR7icC stt|jdtd|ddd| d| d| d |d|d|d| ||_||_||_||_||_||_ ||_ | |_ | |_ dS(NRQRRRSRRRRRRRRRR&R<RVRWRKRXRL( RRRRRRRRRR&( RTR"RURRRRRRRRRR(RYRRRRRRRRRRRR<RVRWR&RKRXRL((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRUs0         N(RRRR>RDRU(((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR"s$cB sGeZdZddd ddddd dd eed d dedZRS( sAn extra-trees regressor. This class implements a meta estimator that fits a number of randomized decision trees (a.k.a. extra-trees) on various sub-samples of the dataset and uses averaging to improve the predictive accuracy and control over-fitting. Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) The number of trees in the forest. .. versionchanged:: 0.20 The default value of ``n_estimators`` will change from 10 in version 0.20 to 100 in version 0.22. criterion : string, optional (default="mse") The function to measure the quality of a split. Supported criteria are "mse" for the mean squared error, which is equal to variance reduction as feature selection criterion, and "mae" for the mean absolute error. .. versionadded:: 0.18 Mean Absolute Error (MAE) criterion. max_depth : integer or None, optional (default=None) The maximum depth of the tree. If None, then nodes are expanded until all leaves are pure or until all leaves contain less than min_samples_split samples. min_samples_split : int, float, optional (default=2) The minimum number of samples required to split an internal node: - If int, then consider `min_samples_split` as the minimum number. - If float, then `min_samples_split` is a fraction and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for fractions. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node. A split point at any depth will only be considered if it leaves at least ``min_samples_leaf`` training samples in each of the left and right branches. This may have the effect of smoothing the model, especially in regression. - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a fraction and `ceil(min_samples_leaf * n_samples)` are the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for fractions. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node. Samples have equal weight when sample_weight is not provided. max_features : int, float, string or None, optional (default="auto") The number of features to consider when looking for the best split: - If int, then consider `max_features` features at each split. - If float, then `max_features` is a fraction and `int(max_features * n_features)` features are considered at each split. - If "auto", then `max_features=n_features`. - If "sqrt", then `max_features=sqrt(n_features)`. - If "log2", then `max_features=log2(n_features)`. - If None, then `max_features=n_features`. Note: the search for a split does not stop until at least one valid partition of the node samples is found, even if it requires to effectively inspect more than ``max_features`` features. max_leaf_nodes : int or None, optional (default=None) Grow trees with ``max_leaf_nodes`` in best-first fashion. Best nodes are defined as relative reduction in impurity. If None then unlimited number of leaf nodes. min_impurity_decrease : float, optional (default=0.) A node will be split if this split induces a decrease of the impurity greater than or equal to this value. The weighted impurity decrease equation is the following:: N_t / N * (impurity - N_t_R / N_t * right_impurity - N_t_L / N_t * left_impurity) where ``N`` is the total number of samples, ``N_t`` is the number of samples at the current node, ``N_t_L`` is the number of samples in the left child, and ``N_t_R`` is the number of samples in the right child. ``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum, if ``sample_weight`` is passed. .. versionadded:: 0.19 min_impurity_split : float, (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. deprecated:: 0.19 ``min_impurity_split`` has been deprecated in favor of ``min_impurity_decrease`` in 0.19. The default value of ``min_impurity_split`` will change from 1e-7 to 0 in 0.23 and it will be removed in 0.25. Use ``min_impurity_decrease`` instead. bootstrap : boolean, optional (default=False) Whether bootstrap samples are used when building trees. If False, the whole datset is used to build each tree. oob_score : bool, optional (default=False) Whether to use out-of-bag samples to estimate the R^2 on unseen data. n_jobs : int or None, optional (default=None) The number of jobs to run in parallel for both `fit` and `predict`. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity when fitting and predicting. warm_start : bool, optional (default=False) When set to ``True``, reuse the solution of the previous call to fit and add more estimators to the ensemble, otherwise, just fit a whole new forest. See :term:`the Glossary `. Attributes ---------- estimators_ : list of DecisionTreeRegressor The collection of fitted sub-estimators. feature_importances_ : array of shape = [n_features] The feature importances (the higher, the more important the feature). n_features_ : int The number of features. n_outputs_ : int The number of outputs. oob_score_ : float Score of the training dataset obtained using an out-of-bag estimate. oob_prediction_ : array of shape = [n_samples] Prediction computed with out-of-bag estimate on the training set. Notes ----- The default values for the parameters controlling the size of the trees (e.g. ``max_depth``, ``min_samples_leaf``, etc.) lead to fully grown and unpruned trees which can potentially be very large on some data sets. To reduce memory consumption, the complexity and size of the trees should be controlled by setting those parameter values. References ---------- .. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees", Machine Learning, 63(1), 3-42, 2006. See also -------- sklearn.tree.ExtraTreeRegressor: Base estimator for this ensemble. RandomForestRegressor: Ensemble regressor using trees with optimal splits. RRiigR7icC stt|jdtd|ddd| d| d| d |d|d| ||_||_||_||_||_||_ ||_ | |_ | |_ dS(NRQRRRSRRRRRRRRRR&R<RVRWRKRX( RRRRRRRRRR&( RTR#RURRRRRRRRRR(RYRRRRRRRRRRRR<RVRWR&RKRX((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRUs.         N(RRRR>RDRU(((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR#s"cB sneZdZdddddd dd ed d ded ZdZd d d Zd d d Z d Z RS( s]An ensemble of totally random trees. An unsupervised transformation of a dataset to a high-dimensional sparse representation. A datapoint is coded according to which leaf of each tree it is sorted into. Using a one-hot encoding of the leaves, this leads to a binary coding with as many ones as there are trees in the forest. The dimensionality of the resulting representation is ``n_out <= n_estimators * max_leaf_nodes``. If ``max_leaf_nodes == None``, the number of leaf nodes is at most ``n_estimators * 2 ** max_depth``. Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) Number of trees in the forest. .. versionchanged:: 0.20 The default value of ``n_estimators`` will change from 10 in version 0.20 to 100 in version 0.22. max_depth : integer, optional (default=5) The maximum depth of each tree. If None, then nodes are expanded until all leaves are pure or until all leaves contain less than min_samples_split samples. min_samples_split : int, float, optional (default=2) The minimum number of samples required to split an internal node: - If int, then consider `min_samples_split` as the minimum number. - If float, then `min_samples_split` is a fraction and `ceil(min_samples_split * n_samples)` is the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for fractions. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node. A split point at any depth will only be considered if it leaves at least ``min_samples_leaf`` training samples in each of the left and right branches. This may have the effect of smoothing the model, especially in regression. - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a fraction and `ceil(min_samples_leaf * n_samples)` is the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for fractions. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node. Samples have equal weight when sample_weight is not provided. max_leaf_nodes : int or None, optional (default=None) Grow trees with ``max_leaf_nodes`` in best-first fashion. Best nodes are defined as relative reduction in impurity. If None then unlimited number of leaf nodes. min_impurity_decrease : float, optional (default=0.) A node will be split if this split induces a decrease of the impurity greater than or equal to this value. The weighted impurity decrease equation is the following:: N_t / N * (impurity - N_t_R / N_t * right_impurity - N_t_L / N_t * left_impurity) where ``N`` is the total number of samples, ``N_t`` is the number of samples at the current node, ``N_t_L`` is the number of samples in the left child, and ``N_t_R`` is the number of samples in the right child. ``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum, if ``sample_weight`` is passed. .. versionadded:: 0.19 min_impurity_split : float, (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. deprecated:: 0.19 ``min_impurity_split`` has been deprecated in favor of ``min_impurity_decrease`` in 0.19. The default value of ``min_impurity_split`` will change from 1e-7 to 0 in 0.23 and it will be removed in 0.25. Use ``min_impurity_decrease`` instead. sparse_output : bool, optional (default=True) Whether or not to return a sparse CSR matrix, as default behavior, or to return a dense array compatible with dense pipeline operators. n_jobs : int or None, optional (default=None) The number of jobs to run in parallel for both `fit` and `predict`. ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity when fitting and predicting. warm_start : bool, optional (default=False) When set to ``True``, reuse the solution of the previous call to fit and add more estimators to the ensemble, otherwise, just fit a whole new forest. See :term:`the Glossary `. Attributes ---------- estimators_ : list of DecisionTreeClassifier The collection of fitted sub-estimators. References ---------- .. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees", Machine Learning, 63(1), 3-42, 2006. .. [2] Moosmann, F. and Triggs, B. and Jurie, F. "Fast discriminative visual codebooks using randomized clustering forests" NIPS 2007 RiiigicC stt|jdtd|dddtdtd| d | d| d| d|_||_||_||_||_ d|_ ||_ ||_ ||_ | |_dS(NRQRRRSRRRRRRRRRR&R<RVRWRKRXRi( RRRRRRRRRR&(RTR$RURRDRRRRRRRRRt sparse_output(RYRRRRRRRRRRRWR&RKRX((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRUvs0          cC stddS(Ns)OOB score not supported by tree embedding(tNotImplementedError(RYRGRH((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRscC s|j||d||S(sAFit estimator. Parameters ---------- X : array-like or sparse matrix, shape=(n_samples, n_features) The input samples. Use ``dtype=np.float32`` for maximum efficiency. Sparse matrices are also supported, use sparse ``csc_matrix`` for maximum efficiency. sample_weight : array-like, shape = [n_samples] or None Sample weights. If None, then samples are equally weighted. Splits that would create child nodes with net zero or negative weight are ignored while searching for a split in each node. In the case of classification, splits are also ignored if they would result in any single class carrying a negative weight in either child node. Returns ------- self : object R:(t fit_transform(RYRGRHR:((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRCscC st|ddg}t|r.|jnt|j}|jd|jd}tt|j ||d|t d|j dd|_ |j j |j|S( sNFit estimator and transform dataset. Parameters ---------- X : array-like or sparse matrix, shape=(n_samples, n_features) Input data used to build forests. Use ``dtype=np.float32`` for maximum efficiency. sample_weight : array-like, shape = [n_samples] or None Sample weights. If None, then samples are equally weighted. Splits that would create child nodes with net zero or negative weight are ignored while searching for a split in each node. In the case of classification, splits are also ignored if they would result in any single class carrying a negative weight in either child node. Returns ------- X_transformed : sparse matrix, shape=(n_samples, n_out) Transformed dataset. RlRmRpiR:tsparset categoriesR7(RRRwRR&tuniformR=RTR$RCRRtone_hot_encoder_RR\(RYRGRHR:trnd((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRs   cC s|jj|j|S(sTransform dataset. Parameters ---------- X : array-like or sparse matrix, shape=(n_samples, n_features) Input data to be transformed. Use ``dtype=np.float32`` for maximum efficiency. Sparse matrices are also supported, use sparse ``csr_matrix`` for maximum efficiency. Returns ------- X_transformed : sparse matrix, shape=(n_samples, n_out) Transformed dataset. (Rt transformR\(RYRG((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyRsN( RRRR>RRDRURRCRR(((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyR$s$  $(HRt __future__RtwarningsRRRRtabcRRtnumpyR,t scipy.sparseRRRftbaseRR t utils._joblibR R t externalsR tmetricsR t preprocessingRRERRRRt tree._treeRRtutilsRRRt exceptionsRRRRt utils.fixesRRtutils.multiclassRtutils.validationRt__all__tiinfotint32tmaxRR*R3R>ROtwith_metaclassRPRRRR R!R"R#R$(((s6lib/python2.7/site-packages/sklearn/ensemble/forest.pyt!sV   "   " %r!