ZPhm4dZddlZddlZddlZddlmZddlmZddl m Z ddl m Z m Z mZddlmZdd lmZdd lmZdd lmZdd lmZmZmZdd lmZmZddlmZm Z ddl!m"Z"eej#eeGddeZ$dS)z9Bagging classifier trained on balanced bootstrap samples.N)clone)BaggingClassifier)DecisionTreeClassifier) HasMethodsInterval StrOptions) parse_version)Pipeline)RandomUnderSampler)BaseUnderSampler) Substitutioncheck_sampling_strategycheck_target_type)_n_jobs_docstring_random_state_docstring) _fit_contextsklearn_version)_bagging_parameter_constraints)sampling_strategyn_jobs random_stateceZdZdZeedkrejej Z neje Z e e e jdddehdeegdged gd gd d e vre d = dddddddddd d dd d fd ZfdZefdZedfdZdfd ZedZfdZfdZxZS)BalancedBaggingClassifieruA Bagging classifier with additional balancing. This implementation of Bagging is similar to the scikit-learn implementation. It includes an additional step to balance the training set at fit time using a given sampler. This classifier can serves as a basis to implement various methods such as Exactly Balanced Bagging [6]_, Roughly Balanced Bagging [7]_, Over-Bagging [6]_, or SMOTE-Bagging [8]_. Read more in the :ref:`User Guide `. Parameters ---------- estimator : estimator object, default=None The base estimator to fit on random subsets of the dataset. If None, then the base estimator is a decision tree. .. versionadded:: 0.10 n_estimators : int, default=10 The number of base estimators in the ensemble. max_samples : int or float, default=1.0 The number of samples to draw from X to train each base estimator. - If int, then draw ``max_samples`` samples. - If float, then draw ``max_samples * X.shape[0]`` samples. max_features : int or float, default=1.0 The number of features to draw from X to train each base estimator. - If int, then draw ``max_features`` features. - If float, then draw ``max_features * X.shape[1]`` features. bootstrap : bool, default=True Whether samples are drawn with replacement. .. note:: Note that this bootstrap will be generated from the resampled dataset. bootstrap_features : bool, default=False Whether features are drawn with replacement. oob_score : bool, default=False Whether to use out-of-bag samples to estimate the generalization error. 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 ensemble. {sampling_strategy} replacement : bool, default=False Whether or not to randomly sample with replacement or not when `sampler is None`, corresponding to a :class:`~imblearn.under_sampling.RandomUnderSampler`. {n_jobs} {random_state} verbose : int, default=0 Controls the verbosity of the building process. sampler : sampler object, default=None The sampler used to balanced the dataset before to bootstrap (if `bootstrap=True`) and `fit` a base estimator. By default, a :class:`~imblearn.under_sampling.RandomUnderSampler` is used. .. versionadded:: 0.8 Attributes ---------- estimator_ : estimator The base estimator from which the ensemble is grown. .. versionadded:: 0.10 estimators_ : list of estimators The collection of fitted base estimators. sampler_ : sampler object The validate sampler created from the `sampler` parameter. estimators_samples_ : list of ndarray The subset of drawn samples (i.e., the in-bag samples) for each base estimator. Each subset is defined by a boolean mask. estimators_features_ : list of ndarray The subset of drawn features for each base estimator. classes_ : ndarray of shape (n_classes,) The classes labels. n_classes_ : int or list The number of classes. 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. 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 See Also -------- BalancedRandomForestClassifier : Random forest applying random-under sampling to balance the different bootstraps. 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. Notes ----- This is possible to turn this classifier into a balanced random forest [5]_ by passing a :class:`~sklearn.tree.DecisionTreeClassifier` with `max_features='auto'` as a base estimator. See :ref:`sphx_glr_auto_examples_ensemble_plot_comparison_ensemble_classifier.py`. References ---------- .. [1] L. Breiman, "Pasting small votes for classification in large databases and on-line", Machine Learning, 36(1), 85-103, 1999. .. [2] L. Breiman, "Bagging predictors", Machine Learning, 24(2), 123-140, 1996. .. [3] T. Ho, "The random subspace method for constructing decision forests", Pattern Analysis and Machine Intelligence, 20(8), 832-844, 1998. .. [4] G. Louppe and P. Geurts, "Ensembles on Random Patches", Machine Learning and Knowledge Discovery in Databases, 346-361, 2012. .. [5] C. Chen Chao, A. Liaw, and L. Breiman. "Using random forest to learn imbalanced data." University of California, Berkeley 110, 2004. .. [6] R. Maclin, and D. Opitz. "An empirical evaluation of bagging and boosting." AAAI/IAAI 1997 (1997): 546-551. .. [7] S. Hido, H. Kashima, and Y. Takahashi. "Roughly balanced bagging for imbalanced data." Statistical Analysis and Data Mining: The ASA Data Science Journal 2.5‐6 (2009): 412-426. .. [8] S. Wang, and X. Yao. "Diversity analysis on imbalanced data sets by using ensemble models." 2009 IEEE symposium on computational intelligence and data mining. IEEE, 2009. Examples -------- >>> from collections import Counter >>> from sklearn.datasets import make_classification >>> from sklearn.model_selection import train_test_split >>> from sklearn.metrics import confusion_matrix >>> from imblearn.ensemble import BalancedBaggingClassifier >>> X, y = make_classification(n_classes=2, class_sep=2, ... weights=[0.1, 0.9], n_informative=3, n_redundant=1, flip_y=0, ... n_features=20, n_clusters_per_class=1, n_samples=1000, random_state=10) >>> print('Original dataset shape %s' % Counter(y)) Original dataset shape Counter({{1: 900, 0: 100}}) >>> X_train, X_test, y_train, y_test = train_test_split(X, y, ... random_state=0) >>> bbc = BalancedBaggingClassifier(random_state=42) >>> bbc.fit(X_train, y_train) BalancedBaggingClassifier(...) >>> y_pred = bbc.predict(X_test) >>> print(confusion_matrix(y_test, y_pred)) [[ 23 0] [ 2 225]] z1.4rrright)closed> not majority not minorityallautomajorityboolean fit_resampleN)r replacementsamplerbase_estimator g?TFr!) max_samples max_features bootstrapbootstrap_features oob_score warm_startrr%rrverboser&c t|||||||| | |  ||_| |_| |_||_dS)N) n_estimatorsr)r*r+r,r-r.rrr/)super__init__ estimatorrr%r&)selfr4r1r)r*r+r,r-r.rr%rrr/r& __class__s Z/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/imblearn/ensemble/_bagging.pyr3z"BalancedBaggingClassifier.__init__sh$ %#%1!%  #!2& c@t|}tjtrTjjdkrDfdtj|jjD_ n j_ |S)Nbypasscji|]/\}}tjj|kdd|0S)r)npwhereclasses_).0keyvaluer5s r7 z9BalancedBaggingClassifier._validate_y..!sJ'''C#-..q1!4e'''r8) r2 _validate_y isinstancerdictsampler__sampling_typeritems_sampling_strategy)r5y y_encodedr6s` r7rCz%BalancedBaggingClassifier._validate_ysGG''** t-t 4 4 = ,88''''"9*M0##%'' '''D # #'+& %dn--IIgI = '8 3 3 M $ $t7N $ O O O" ', )B C  r8)prefer_skip_nested_validationcp|t||S)a+Build a Bagging ensemble of estimators from the training set (X, y). Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) The training input samples. Sparse matrices are accepted only if they are supported by the base estimator. y : array-like of shape (n_samples,) The target values (class labels in classification, real numbers in regression). Returns ------- self : object Fitted estimator. )_validate_paramsr2fit)r5XrJr6s r7rUzBalancedBaggingClassifier.fit<s/( ww{{1a   r8ct||jt|j|_nt |j|_t |||jS)N)r%) rr&r r%rFrr2_fitr))r5rVrJr) max_depth sample_weightr6s r7rXzBalancedBaggingClassifier._fitSsk! < . ,DMM"$,//DMww||Aq$"2333r8c>t|jjd}|)z2Attribute for older sklearn version compatibility.z+ object has no attribute 'base_estimator_'.)AttributeErrorr6__name__)r5errors r7base_estimator_z)BalancedBaggingClassifier.base_estimator_bs+~& S S S   r8ct}d}d}d}||vr ||||<n||i||<|S)N _xfail_checkscheck_estimators_nan_infz9Fails because the sampler removed infinity and NaN values)r2 _more_tags)r5tagstags_key failing_testreasonr6s r7rcz$BalancedBaggingClassifier._more_tagsjsVww!!##"1 L t  +1DN< ( (*F3DN r8cHt}|S)N)r2__sklearn_tags__)r5rdr6s r7riz*BalancedBaggingClassifier.__sklearn_tags__usww'')) r8)Nr()NNN)r] __module__ __qualname____doc__rr copydeepcopyr_parameter_constraintsrupdaternumbersRealrrEcallablerr3rCrrQrrUrXpropertyr_rcri __classcell__)r6s@r7rrs. @@F--....!./@/W!X!X!./M!N!N!!q!G<<< VVVWW " &;" N#344d;    111 "#3 4!   !!!!!!!!F$+A*@*B*B     \666!!!!76!, 4 4 4 4 4 4X     r8r)%rlrmrqnumpyr< sklearn.basersklearn.ensembler sklearn.treersklearn.utils._param_validationrrrsklearn.utils.fixesr pipeliner under_samplingr under_sampling.baser utilsrrrutils._docstringrrutils._sklearn_compatrr_commonr_sampling_strategy_docstringrr8r7rs??  ......//////LLLLLLLLLL------//////222222LLLLLLLLLLIIIIIIIIAAAAAAAA333333&C ( XXXXX 1XX  XXXr8