t]e:DdZddlZddlmZddlmZddlZddlZddlm Z ddlm Z ddl mZddlmZmZdd lmZdd lmZdd lmZmZmZdd lmZdd lmZddlmZm Z m!Z!ddl"m#Z#ddl$m%Z% ddl&m'Z'm(Z(n#e)e*f$rddl+m'Z'ddl,m(Z(YnwxYwddl-m.Z.ddl/m0Z0ddl1m2Z2ddl3m4Z4ddl5m6Z6m7Z7ddl8m9Z9m:Z:m;Z;ddlm?Z?ddl@mAZAejBejCjDZEe!ejFZG d#dZHe4e6e7 Gd!d"e.eZIdS)$z9Forest classifiers trained on balanced boostrasp samples.N)deepcopy)warn)float32)float64)issparse)clone is_classifier)RandomForestClassifier)_set_random_states)_generate_unsampled_indices_get_n_samples_bootstrap_parallel_build_trees)DataConversionWarning)DecisionTreeClassifier)_safe_indexingcheck_random_state parse_version)type_of_target)_check_sample_weight)Paralleldelayed)r)r)_ParamsValidationMixin) make_pipeline)RandomUnderSampler) Substitution)_n_jobs_docstring_random_state_docstring)HiddenInterval StrOptions)check_sampling_strategy) _fit_context)/_random_forest_classifier_parameter_constraintsc D|||\} } |t||j}tt | | jd} t tdkrt||| | ||||| |  }nt|| | | ||||| |  }||fS)Nrz1.1)verbose class_weightn_samples_bootstrap) fit_resamplersample_indices_r minshapesklearn_versionrr)samplertree bootstrapXy sample_weighttree_idxn_treesr'r(r)forest X_resampled y_resampleds 9lib/python3.11/site-packages/imblearn/ensemble/_forest.py_local_parallel_build_treesr;2s '33Aq99K &}g6MNN +!"5{7H7KLL-....$       % 3    %       % 3     D=)n_jobs random_stateceZdZdZeedkreejZn ee Ze e e j dddehdeeeedhgd eedhgd  dd d ddddd dddddd d ddd dd dfd ZefdZddZedddZdZdZedZedZdZxZS) BalancedRandomForestClassifiera2A balanced random forest classifier. A balanced random forest randomly under-samples each bootstrap sample to balance it. Read more in the :ref:`User Guide `. .. versionadded:: 0.4 Parameters ---------- n_estimators : int, default=100 The number of trees in the forest. criterion : {{"gini", "entropy"}}, 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 : int, 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 or float, 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 percentage and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. min_samples_leaf : int or float, default=1 The minimum number of samples required to be at a leaf node: - 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. min_weight_fraction_leaf : float, default=0.0 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 : {{"auto", "sqrt", "log2"}}, int, float, or None, default="sqrt" 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 percentage 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, 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, default=0.0 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. bootstrap : bool, default=True Whether bootstrap samples are used when building trees. oob_score : bool, default=False Whether to use out-of-bag samples to estimate the generalization accuracy. sampling_strategy : float, str, dict, callable, default="auto" Sampling information to sample the data set. - When ``float``, it corresponds to the desired ratio of the number of samples in the minority class over the number of samples in the majority class after resampling. Therefore, the ratio is expressed as :math:`\alpha_{{us}} = N_{{m}} / N_{{rM}}` where :math:`N_{{m}}` is the number of samples in the minority class and :math:`N_{{rM}}` is the number of samples in the majority class after resampling. .. warning:: ``float`` is only available for **binary** classification. An error is raised for multi-class classification. - When ``str``, specify the class targeted by the resampling. The number of samples in the different classes will be equalized. Possible choices are: ``'majority'``: resample only the majority class; ``'not minority'``: resample all classes but the minority class; ``'not majority'``: resample all classes but the majority class; ``'all'``: resample all classes; ``'auto'``: equivalent to ``'not minority'``. - When ``dict``, the keys correspond to the targeted classes. The values correspond to the desired number of samples for each targeted class. - When callable, function taking ``y`` and returns a ``dict``. The keys correspond to the targeted classes. The values correspond to the desired number of samples for each class. .. versionchanged:: 0.11 The default of `sampling_strategy` will change from `"auto"` to `"all"` in version 0.13. This forces to use a bootstrap of the minority class as proposed in [1]_. replacement : bool, default=False Whether or not to sample randomly with replacement or not. .. versionchanged:: 0.11 The default of `replacement` will change from `False` to `True` in version 0.13. This forces to use a bootstrap of the minority class and draw with replacement as proposed in [1]_. {n_jobs} {random_state} verbose : int, default=0 Controls the verbosity of the tree building process. warm_start : bool, 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. class_weight : dict, list of dicts, {{"balanced", "balanced_subsample"}}, default=None Weights associated with classes in the form dictionary with the key being the class_label and the value the 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. ccp_alpha : non-negative float, default=0.0 Complexity parameter used for Minimal Cost-Complexity Pruning. The subtree with the largest cost complexity that is smaller than ``ccp_alpha`` will be chosen. By default, no pruning is performed. .. versionadded:: 0.6 Added in `scikit-learn` in 0.22 max_samples : int or float, default=None If bootstrap is True, the number of samples to draw from X to train each base estimator. - If None (default), then draw `X.shape[0]` samples. - If int, then draw `max_samples` samples. - If float, then draw `max_samples * X.shape[0]` samples. Thus, `max_samples` should be in the interval `(0, 1)`. Be aware that the final number samples used will be the minimum between the number of samples given in `max_samples` and the number of samples obtained after resampling. .. versionadded:: 0.6 Added in `scikit-learn` in 0.22 Attributes ---------- estimator_ : :class:`~sklearn.tree.DecisionTreeClassifier` instance The child estimator template used to create the collection of fitted sub-estimators. .. versionadded:: 0.10 base_estimator_ : :class:`~sklearn.tree.DecisionTreeClassifier` instance The child estimator template used to create the collection of fitted sub-estimators. .. deprecated:: 1.2 `base_estimator_` is deprecated in `scikit-learn` 1.2 and will be removed in 1.4. Use `estimator_` instead. When the minimum version of `scikit-learn` supported by `imbalanced-learn` will reach 1.4, this attribute will be removed. estimators_ : list of :class:`~sklearn.tree.DecisionTreeClassifier` The collection of fitted sub-estimators. base_sampler_ : :class:`~imblearn.under_sampling.RandomUnderSampler` The base sampler used to construct the subsequent list of samplers. samplers_ : list of :class:`~imblearn.under_sampling.RandomUnderSampler` The collection of fitted samplers. pipelines_ : list of Pipeline. The collection of fitted pipelines (samplers + trees). classes_ : ndarray 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. .. deprecated:: 1.0 `n_features_` is deprecated in `scikit-learn` 1.0 and will be removed in version 1.2. When the minimum version of `scikit-learn` supported by `imbalanced-learn` will reach 1.2, this attribute will be removed. n_features_in_ : int Number of features in the input dataset. .. versionadded:: 0.9 feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during `fit`. Defined only when `X` has feature names that are all strings. .. versionadded:: 0.9 n_outputs_ : int The number of outputs when ``fit`` is performed. feature_importances_ : ndarray 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_ : ndarray 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. See Also -------- BalancedBaggingClassifier : Bagging classifier for which each base estimator is trained on a balanced bootstrap. EasyEnsembleClassifier : Ensemble of AdaBoost classifier trained on balanced bootstraps. RUSBoostClassifier : AdaBoost classifier were each bootstrap is balanced using random-under sampling at each round of boosting. References ---------- .. [1] Chen, Chao, Andy Liaw, and Leo Breiman. "Using random forest to learn imbalanced data." University of California, Berkeley 110 (2004): 1-12. Examples -------- >>> from imblearn.ensemble import BalancedRandomForestClassifier >>> from sklearn.datasets import make_classification >>> >>> X, y = make_classification(n_samples=1000, n_classes=3, ... n_informative=4, weights=[0.2, 0.3, 0.5], ... random_state=0) >>> clf = BalancedRandomForestClassifier( ... sampling_strategy="all", replacement=True, max_depth=2, random_state=0) >>> clf.fit(X, y) BalancedRandomForestClassifier(...) >>> print(clf.feature_importances_) [...] >>> print(clf.predict([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])) [1] z1.3rr$right)closed> not majority not minorityallautomajorityrbooleansampling_strategy replacementdginiNrgsqrtTF) criterion max_depthmin_samples_splitmin_samples_leafmin_weight_fraction_leaf max_featuresmax_leaf_nodesmin_impurity_decreaser1 oob_scorerJrKr=r>r' warm_startr( ccp_alpha max_samplesct|||| | ||||||||||| ||| |_| |_dS)N)rOrP n_estimatorsr1rWr=r>r'rXr(rQrRrSrTrUrVrYrZ)super__init__rJrK)selfr\rOrPrQrRrSrTrUrVr1rWrJrKr=r>r'rXr(rYrZ __class__s r:r^z'BalancedRandomForestClassifier.__init__st0 %%!%/-%=%)"7#%    *"3&r<ct|dr|j}n|j}|t||_nt||_ |j|_n#t $rYnwxYwt|j|j |_ dS)zZCheck the estimator and the n_estimator attribute, set the `estimator_` attribute. estimatorNrI) hasattrrbbase_estimatorr _estimatorbase_estimator_AttributeErrorr_sampling_strategy _replacement base_sampler_)r_defaultrds r:_validate_estimatorz2BalancedRandomForestClassifier._validate_estimators 4 % % 1!^NN!0N  %#N33DOO#GnnDO #'?D     D 0"5)   s A A&%A&ctj}|jdifdjDtj}| t ||t ||||fS)zMake and configure a copy of the `base_estimator_` attribute. Warning: This method should be used to properly instantiate new sub-estimators. c2i|]}|t|S)getattr).0pr_s r: zJBalancedRandomForestClassifier._make_sampler_estimator..s%SSS74#3#3SSSr<Nro)rre set_paramsestimator_paramsrjr )r_r>rbr/s` r:_make_sampler_estimatorz6BalancedRandomForestClassifier._make_sampler_estimators $/**  TTSSSST=RSSSTTT*++  # y, 7 7 7 w 5 5 5'!!r<)prefer_skip_nested_validationc V  jdkrtdtd_n j_jdkrtdtd_n j_t|rtd |ddt \}tj d _ trtj|}|jd kr(|j d d krtd t$d |jd krtj|d}|j d _|\}t-|dd t.ks |jjstjt.t7jt8r:fdt;j|dD_n j_| |zn|t?j dj  !j"sj#rtdtIj%}j&rtOdsg_(g_)g_*j+tYj(z }|dkr+tdj+tYj(fz|dkrtdnij&rFtYj(dkr.|-t\tYj(gg}t_|D]E}0|\} } 1| |1| Ftej3j4d fdtktm|D} tm| \}j(7j)7|j*7dtm|Dj#r._sO'''Cq)S011!4Q7'''r<zunder-samplingr) n_samplesrZz6Out of bag estimation only available if bootstrap=True estimators_zTn_estimators=%d must be larger or equal to len(estimators_)=%d when warm_start==TruezJWarm-start fitting without increasing n_estimators does not fit new trees.)size)r>threads)r=r'preferc3K|]O\}\}}tt||j |tjj VPdS))r'r(r)r7N)rr;r1lenr'r() rqistr2r)r4r_trees y_encodeds r: z5BalancedRandomForestClassifier.fit..sAv15344N!JJ L!%!2(;   r<chg|]/\}}tt|t|0Sro)rr)rqrrs r: z6BalancedRandomForestClassifier.fit..sB1"(1++x{{;;r<)zmulticlass-multioutputunknownz@The type of target cannot be used to compute OOB estimates. Got zv while only the following are supported: continuous, continuous-multioutput, binary, multiclass, multilabel-indicator.r)<_validate_paramsrJr FutureWarningrhrKrir ValueError_validate_dataDTYPErr- _n_features sort_indicesr atleast_1dndimrreshape n_outputs__validate_y_class_weightrpDOUBLEflags contiguousascontiguousarray isinstancedictr"itemsr rZrlr1rWrr>rXrcr samplers_ pipelines_r\rrandintMAX_INTrangervappendrr=r' enumeratezipextendr_set_oob_score_and_attributes n_classes_r)r_r2r3r4expanded_class_weightr>n_more_estimatorssamplers_r0r/samplers_treesy_typer)rrs`` ` @@@r:fitz"BalancedRandomForestClassifier.fits6   !V + + :    '-D # #&*&''''"9*$##%'' '''D # #'+&=D # ,( -0E E 5 7gajd.>      """~ W$. WUVV V)$*;<<  !gdM&B&B !!D DN DO -D4D0E0EE q <$c$*:&;&;<=  ! # # !      J3t'7#8#81#<#<$$W3t7G3H3H$IIIEH,-- ) ) $ < <, < W W g T"""((((X{  "+3x+?+?!@!@ N*">2OHe   # #E * * * N ! !( + + + O " " #He 4 4    > =#A&&F>>> !8&,888  . .q) < < < 4 $ $ -A)=)="oa0DO M!,DM r<c||||_|jjddkr |jd|_ddlm}||t j|jd|_dS)aCompute and set the OOB score and attributes. Parameters ---------- X : array-like of shape (n_samples, n_features) The data matrix. y : ndarray of shape (n_samples, n_outputs) The target matrix. r~r$)axisr)accuracy_scoreN) _compute_oob_predictionsoob_decision_function_r-squeezesklearn.metricsrrargmax oob_score_)r_r2r3rs r:rz_get_oob_predictionsranyr UserWarning)r_r2r3r n_outputsoob_pred_shapeoob_pred n_oob_predr/rb X_resample y_resamplen_sample_subsetr)unsampled_indicesy_predindicesks r:rz7BalancedRandomForestClassifier._compute_oob_predictionss7" A;;  AGAJ O    774#>#> 7();YGNN (I6N8. CCCXy)4BHEEE "%dnd6F"G"G ( ( GY723J723J(.q1O":!1## !<&9L!! ..:&7&:;F-.?@G Wc\ " " "f , " " " wz " " "a ' " " " "y!! 5 5Aa$$&& 0!  /0 :?+ S!V    38 4 4    r<c|jS)z$Estimator used to grow the ensemble.)rer_s r: estimator_z)BalancedRandomForestClassifier.estimator_9s r<c:tdt|jS)z-Number of features when ``fit`` is performed.z`n_features_` was deprecated in scikit-learn 1.0. This attribute will not be accessible when the minimum supported version of scikit-learn is 1.2.)rrn_features_in_rs r: n_features_z*BalancedRandomForestClassifier.n_features_?s+       ""r<c dddS)NF) multioutput multilabelrors r: _more_tagsz)BalancedRandomForestClassifier._more_tagsJs    r<)rL)N)__name__ __module__ __qualname____doc__r.rrr _parameter_constraintsr%updater numbersRealr!rcallablerr^rrlrvr#rrrpropertyrrr __classcell__)r`s@r:r@r@es? ll^ --....!)*@*W!X!X!) ;" " !!q!G<<< VVVWWzz6(++,, "&vvjj&.B.B'C'CD    .'!$! -.'.'.'.'.'.'.'`+A*@*B*B    0 " " " "\555VVV65Vp   (EEEPX ##X#       r<r@)rNNN)Jrrcopyrwarningsrnumpyrsklearnrrrr scipy.sparser sklearn.baserr sklearn.ensembler sklearn.ensemble._baser sklearn.ensemble._forestr r rsklearn.exceptionsr sklearn.treer sklearn.utilsrrrsklearn.utils.multiclassrsklearn.utils.validationrsklearn.utils.parallelrr ImportErrorModuleNotFoundErrorjoblibsklearn.utils.fixesbaserpipelinerunder_samplingrutilsrutils._docstringrrutils._param_validationrr r!utils._validationr" utils.fixesr#_commonr%iinfoint32maxr __version__r.r;r@ror<r:r s/?? """"""######!!!!!!--------333333555555 544444//////KKKKKKKKKK333333999999,888888888(),,,++++++++,*)))))$$$$$$////// IIIIIIIIBBBBBBBBBB777777&&&&&&DDDDDD "(28   - 344  0000f (e  e  e  e  e  %;=Se  e  e  e  e  s.A77B  B