ZPhY.dZddlZddlZddlZddlmZddlmZm Z ddl m Z ddl m Z ddlmZmZddlmZdd lmZdd lmZdd lmZmZdd lmZd dlmZd dlmZd dl m!Z!d dl"m#Z#m$Z$m%Z%d dl&m'Z'm(Z(d dl)m*Z*m+Z+m,Z,m-Z-ddl.m/Z/m0Z0ej1ej2j3Z4e#e!j5e'e(Gdde Z6dS)z4Class to perform under-sampling using easy ensemble.N)clone)AdaBoostClassifierBaggingClassifier)_parallel_decision_function)_partition_estimators)Interval StrOptions) _safe_tags) parse_version) available_if)Paralleldelayed)check_is_fitted)Pipeline)RandomUnderSampler)BaseUnderSampler) Substitutioncheck_sampling_strategycheck_target_type)_n_jobs_docstring_random_state_docstring) _fit_contextget_tagssklearn_version validate_data)_bagging_parameter_constraints_estimator_has)sampling_strategyn_jobs random_statec*eZdZdZeedkrejej Z neje Z hdZ e D]Z e e de eejdddehd eegd gd d e vre d = ddddddddfd ZfdZedfdZedfdZd fd ZeeddZedZ dZ!dZ"fdZ#xZ$S)!EasyEnsembleClassifiera=Bag of balanced boosted learners also known as EasyEnsemble. This algorithm is known as EasyEnsemble [1]_. The classifier is an ensemble of AdaBoost learners trained on different balanced bootstrap samples. The balancing is achieved by random under-sampling. Read more in the :ref:`User Guide `. .. versionadded:: 0.4 Parameters ---------- n_estimators : int, default=10 Number of AdaBoost learners in the ensemble. estimator : estimator object, default=AdaBoostClassifier() The base AdaBoost classifier used in the inner ensemble. Note that you can set the number of inner learner by passing your own instance. .. versionadded:: 0.10 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 sample randomly with replacement or not. {n_jobs} {random_state} verbose : int, default=0 Controls the verbosity of the building process. 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. estimators_samples_ : list of arrays The subset of drawn samples for each base estimator. estimators_features_ : list of arrays The subset of drawn features for each base estimator. classes_ : array, shape (n_classes,) The classes labels. n_classes_ : int or list The number of classes. 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 -------- BalancedBaggingClassifier : Bagging classifier for which each base estimator is trained on a balanced bootstrap. BalancedRandomForestClassifier : Random forest applying random-under sampling to balance the different bootstraps. RUSBoostClassifier : AdaBoost classifier were each bootstrap is balanced using random-under sampling at each round of boosting. Notes ----- The method is described in [1]_. Supports multi-class resampling by sampling each class independently. References ---------- .. [1] X. Y. Liu, J. Wu and Z. H. Zhou, "Exploratory Undersampling for Class-Imbalance Learning," in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 39, no. 2, pp. 539-550, April 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 EasyEnsembleClassifier >>> 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) >>> eec = EasyEnsembleClassifier(random_state=42) >>> eec.fit(X_train, y_train) EasyEnsembleClassifier(...) >>> y_pred = eec.predict(X_test) >>> print(confusion_matrix(y_test, y_pred)) [[ 23 0] [ 2 225]] 1.4> bootstrap oob_score max_samples max_featuresbootstrap_featuresNrrright)closed> not majority not minorityallautomajoritybooleanr replacementbase_estimator Fr0) warm_startr r4r!r"verbosec t|ddddd|||| ||_||_||_dS)Ng?F) n_estimatorsr(r)r&r*r'r7r!r"r8)super__init__ estimatorr r4) selfr:r=r7r r4r!r"r8 __class__s `/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/imblearn/ensemble/_easy_ensemble.pyr<zEasyEnsembleClassifier.__init__sc %$!%  #!2&c t|}tjtr:fdt j|dD_n j_|S)Ncji|]/\}}tjj|kdd|0S)r)npwhereclasses_).0keyvaluer>s r@ z6EasyEnsembleClassifier._validate_y..sJ'''C#-..q1!4e'''rAzunder-sampling)r; _validate_y isinstancer dictritems_sampling_strategy)r>y y_encodedr?s` r@rKz"EasyEnsembleClassifier._validate_ysGG''** d,d 3 3 =''''"9*$##%'' '''D # #'+&defaultr=rVs r@_validate_estimatorz*EasyEnsembleClassifier._validate_estimatorsl > %dn--IIgI$"5(   #Y$8<:S#TUUrA)prefer_skip_nested_validationcp|t||S)a+Build a Bagging ensemble of estimators from the training set (X, y). Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) The training input samples. Sparse matrices are accepted only if they are supported by the base estimator. y : array-like of shape (n_samples,) The target values (class labels in classification, real numbers in regression). Returns ------- self : object Fitted estimator. )_validate_paramsr;fit)r>XrPr?s r@r^zEasyEnsembleClassifier.fits/& ww{{1a   rAcrt|t|||jSN)rr;_fitr()r>r_rPr( max_depth sample_weightr?s r@rbzEasyEnsembleClassifier._fits0!ww||Aq$"2333rAdecision_functionc lttddgdtjjrdnddt jj\}}t|j fd t|D}t|jz }|S) aAverage of the decision functions of the base classifiers. 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. Returns ------- score : ndarray of shape (n_samples, k) The decision function of the input samples. The columns correspond to the classes in sorted order, as they appear in the attribute ``classes_``. Regression and binary classification are special cases with ``k == 1``, otherwise ``k==n_classes``. csrcscN allow_nanTF)r_ accept_sparsedtypeensure_all_finitereset)r!r8c 3K|][}ttj||dzj||dzV\dS)rN)rr estimators_estimators_features_)rGir_r>startss r@ z;EasyEnsembleClassifier.decision_function..;sF F  1G/ 0 0 VAE]!:;)&)fQUm*CD  F F F F F F rA) rrr input_tagsrirr:r!r r8rangesum)r>r_r!_ all_decisions decisionsrrs`` @r@rez(EasyEnsembleClassifier.decision_functions$    %.'~~8BL  2$2CT[QQ6E EEEF F F F F F 6]] F F F    &&):: rAc>t|jjd}|)z2Attribute for older sklearn version compatibility.z+ object has no attribute 'base_estimator_'.)AttributeErrorr?__name__)r>errors r@base_estimator_z&EasyEnsembleClassifier.base_estimator_Is+~& S S S   rAc|jMtdtcxkrtdkrnntdStS|jS)Nr%z1.6rRrS)r=r rrr>s r@_get_estimatorz%EasyEnsembleClassifier._get_estimatorQsa > !U##MMMMu9M9MMMMMM)G<<<<)+++~rAcJdt|diS)Nri)r rrs r@ _more_tagsz!EasyEnsembleClassifier._more_tagsYs#Z(;(;(=(={KKLLrAct}t|jj|j_|Sra)r;__sklearn_tags__rrrtri)r>tagsr?s r@rz'EasyEnsembleClassifier.__sklearn_tags__\sAww''))$,T-@-@-B-B$C$C$N$X! rA)r6N)NNN)%r| __module__ __qualname____doc__rr copydeepcopyr_parameter_constraintsrexcluded_paramsparampopupdaternumbersRealr rMcallabler<rKrrZrr^rbr rrepropertyr~rrr __classcell__)r?s@r@r$r$&s ttn--....!./@/W!X!X!./M!N!NO!00""5$////!!q!G<<< VVVWW " &;     111 "#3 4'  '''''''8     +=*rs5::  BBBBBBBBAAAAAA888888@@@@@@@@******------55555544444444444444//////222222LLLLLLLLLLIIIIIIII DCCCCCCC "(28   &C ( ttttt.tt  tttrA