ZPh6;BddlZddlZddlZddlmZddlZddlmZddlm Z ddl m Z ddl m Z ddlmZddlmZmZmZdd lmZdd lmZd d lmZd d lmZd dlmZd dlmZm Z d dl!m"Z"d dl#m$Z$m%Z%ddl&m'Z'eej(e"Gdde Z)dS)N)deepcopy)clone)AdaBoostClassifier)_set_random_states)DecisionTreeClassifier)_safe_indexing)HiddenInterval StrOptions) parse_version)has_fit_parameter) make_pipeline)RandomUnderSampler)BaseUnderSampler) Substitutioncheck_target_type)_random_state_docstring) _fit_contextsklearn_version)*_adaboost_classifier_parameter_constraints)sampling_strategy random_statec eZdZdZeedkrejej Z neje Z e e ddhe e dhgeejddd e hd eegd gd d e vre d = ddddddddfd Zeddfd ZdZddZdZdZdZxZS)RUSBoostClassifieraRandom under-sampling integrated in the learning of AdaBoost. During learning, the problem of class balancing is alleviated by random under-sampling the sample at each iteration of the boosting algorithm. Read more in the :ref:`User Guide `. .. versionadded:: 0.4 Parameters ---------- estimator : estimator object, default=None The base estimator from which the boosted ensemble is built. Support for sample weighting is required, as well as proper ``classes_`` and ``n_classes_`` attributes. If ``None``, then the base estimator is ``DecisionTreeClassifier(max_depth=1)``. .. versionadded:: 0.12 n_estimators : int, default=50 The maximum number of estimators at which boosting is terminated. In case of perfect fit, the learning procedure is stopped early. learning_rate : float, default=1.0 Learning rate shrinks the contribution of each classifier by ``learning_rate``. There is a trade-off between ``learning_rate`` and ``n_estimators``. algorithm : {{'SAMME', 'SAMME.R'}}, default='SAMME.R' If 'SAMME.R' then use the SAMME.R real boosting algorithm. ``base_estimator`` must support calculation of class probabilities. If 'SAMME' then use the SAMME discrete boosting algorithm. The SAMME.R algorithm typically converges faster than SAMME, achieving a lower test error with fewer boosting iterations. .. deprecated:: 0.12 `"SAMME.R"` is deprecated and will be removed in version 0.14. '"SAMME"' will become the default. {sampling_strategy} replacement : bool, default=False Whether or not to sample randomly with replacement or not. {random_state} Attributes ---------- estimator_ : estimator The base estimator from which the ensemble is grown. .. versionadded:: 0.10 estimators_ : list of classifiers The collection of fitted sub-estimators. base_sampler_ : :class:`~imblearn.under_sampling.RandomUnderSampler` The base sampler used to generate the subsequent 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,) The classes labels. n_classes_ : int The number of classes. estimator_weights_ : ndarray of shape (n_estimator,) Weights for each estimator in the boosted ensemble. estimator_errors_ : ndarray of shape (n_estimator,) Classification error for each estimator in the boosted ensemble. feature_importances_ : ndarray of shape (n_features,) The feature importances if supported by the ``base_estimator``. 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. EasyEnsembleClassifier : Ensemble of AdaBoost classifier trained on balanced bootstraps. References ---------- .. [1] Seiffert, C., Khoshgoftaar, T. M., Van Hulse, J., & Napolitano, A. "RUSBoost: A hybrid approach to alleviating class imbalance." IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans 40.1 (2010): 185-197. Examples -------- >>> from imblearn.ensemble import RUSBoostClassifier >>> 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 = RUSBoostClassifier(random_state=0) >>> clf.fit(X, y) RUSBoostClassifier(...) >>> clf.predict(X) array([...]) z1.4SAMMESAMME.R deprecatedrrright)closed> not majority not minorityallautomajorityboolean) algorithmr replacementbase_estimatorN2?r%F) n_estimators learning_rater(rr)rct|||||_||_||_||_dS)N)r-r.r)super__init__r( estimatorrr)) selfr2r-r.r(rr)r __class__s b/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/imblearn/ensemble/_weight_boosting.pyr1zRUSBoostClassifier.__init__sU %'%    #"!2&)prefer_skip_nested_validationc|t|g|_g|_t ||||S)aBuild a boosted classifier from the training set (X, y). Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) The training input samples. Sparse matrix can be CSC, CSR, COO, DOK, or LIL. DOK and LIL are converted to CSR. y : array-like of shape (n_samples,) The target values (class labels). sample_weight : array-like of shape (n_samples,), default=None Sample weights. If None, the sample weights are initialized to ``1 / n_samples``. Returns ------- self : object Returns self. )_validate_paramsr samplers_ pipelines_r0fit)r3Xy sample_weightr4s r5r<zRUSBoostClassifier.fitsR, !  Aq-((( r6ctd}|jt|j|_nt||_|jdkr$t |jdst dt|jds!t|jj j dt|j |j |_dS) zfCheck the estimator and the n_estimator attribute. Sets the `estimator_` attributes. r) max_depthNr predict_probazAdaBoostClassifier with algorithm='SAMME.R' requires that the weak learner supports the calculation of class probabilities with a predict_proba method. Please change the base estimator or set algorithm='SAMME' instead.r?z doesn't support sample_weight.)rr))rr2r estimator_r(hasattr TypeErrorr ValueErrorr4__name__rrr) base_sampler_)r3defaults r5_validate_estimatorz&RUSBoostClassifier._validate_estimators )1555 > %#DN33DOO#GnnDO >Y & &4?O<< 1!/BB ?,5VVV 0"4(   r6Tctj}|jdifdjDtj}| t ||t |||rvj|j|j tt|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).0pr3s r5 z>RUSBoostClassifier._make_sampler_estimator..s%SSS74#3#3SSSr6NrM) rrC set_paramsestimator_paramsrHr estimators_appendr:r;rr)r3rUrr2samplers` r5_make_sampler_estimatorz*RUSBoostClassifier._make_sampler_estimator s $/**  TTSSSST=RSSSTTT*++  # y, 7 7 7 w 5 5 5     # #I . . . N ! !' * * * O " "hw//)1D1DEE   '!!r6c0||\}}|||\}} t||j} ||| | ||} |dkr/t |dd|_t|j|_ |j tj | dd} | |k} tj tj| |d}|dkr|d d fS|j }|j}tjd |dz z d g}| ||ddtjfk}| }tj|tj|jjd| d |jz|d z |z z|tj| zdz}||jdz ks%|tj||dk|dkzzz}|d |fS) z:Implement a single boost using the SAMME.R real algorithm.rr?rclasses_Nr)axisweightsr\r,g)out)rW fit_resamplersample_indices_r<rBrNr[len n_classes_takenpargmaxmeanaveragearraynewaxisclipfinfodtypeepsr.logsumr-exp)r3iboostr=r>r?rr2rVX_resy_ressample_weight_resy_predict_proba y_predict incorrectestimator_error n_classesclassesy_codesy_codingprobaestimator_weights r5 _boost_realzRUSBoostClassifier._boost_reals9!99|9TT 7++Aq11 u*=':QRR eU2C DDD#11!44 Q;;#Iz4@@DM!$-00DOM&&ryq'I'I'IPQ&RR N '"*Y TU"V"V"VWW a   #s* *O -(DIM2C899<<1QQQ ]+; ;<<   rx ,,0$EBBBB   !C9, ."&11166A6>> ? *Q... RV ]Q%6;Ka;O$PQ Mc?22r6c||\}}|||\}} t||j} ||| | ||} |dkr/t |dd|_t|j|_ | |k} tj tj | |d} | dkr|ddfS|j }| dd|z z krw|j d |jd |jd t|j dkrt#d d S|jtjd| z | z tj|dz zz}||jd z ks!|tj|| z|dkzz}||| fS) zr?rr2rVrtrurvrxryrzr{rs r5_boost_discretez"RUSBoostClassifier._boost_discrete\s!99|9TT 7++Aq11 u*=':QRR eU2C DDD%%a(( Q;;#Iz4@@DM!$-00DON '"*Y TU"V"V"VWW a   #s* *O  cS9_5 5 5    $ $ $ N  r " " " O   # # #4#$$)) & $# - FC/)_< = =ySV@W@W W  *Q... RV$4y$@MTUDU$VWW WM.??r6c|jdkrtjdt|jdkr||||||S||||||S)Nrz`algorithm` parameter is deprecated in 0.12 and will be removed in 0.14. In the future, the SAMME algorithm will always be used.r)r(warningswarn FutureWarningrr)r3rsr=r>r?rs r5_boostzRUSBoostClassifier._boostsw >\ ) ) MU     >Y & &##FAq-NN N''1m\RR Rr6)N)TN)rG __module__ __qualname____doc__rr copyrr_parameter_constraintsrupdater r r numbersRealdictcallabler1rr<rJrWrrr __classcell__)r4s@r5rrs {{|--....!.  5" " "/ 6" " !! GY/00zz<.1122 q!G<<< VVVWW " &;  111 "#3 4' '''''''*\666768   >"""",;3;3;3z1@1@1@h S S S S S S Sr6r)*rrrrnumpyrf sklearn.basersklearn.ensemblersklearn.ensemble._baser sklearn.treer sklearn.utilsrsklearn.utils._param_validationr r r sklearn.utils.fixesr sklearn.utils.validationr pipelinerunder_samplingrunder_sampling.baserutilsrrutils._docstringrutils._sklearn_compatrr_commonr_sampling_strategy_docstringrrMr6r5rs //////555555//////((((((HHHHHHHHHH------666666$$$$$$//////22222233333333666666AAAAAAAA??????&C(@S@S@S@S@S+@S@S @S@S@Sr6