t]e?pddlZddlZddlZddlZddlmZddlZddlZddlm Z ddl m Z ddl m Z ddlmZddlmZmZddlmZd d lmZd d lmZd d lmZd d lmZd dlmZmZd dl m!Z!d dl"m#Z#m$Z$d dl%m&Z&ddl'm(Z(eej)Z*eej+e!Gddee Z,dS)N)deepcopy)clone)AdaBoostClassifier)_set_random_states)DecisionTreeClassifier)_safe_indexing parse_version)has_fit_parameter)_ParamsValidationMixin) make_pipeline)RandomUnderSampler)BaseUnderSampler) Substitutioncheck_target_type)_random_state_docstring)Interval StrOptions) _fit_context)*_adaboost_classifier_parameter_constraints)sampling_strategy random_statec veZdZdZeedkrejej Z neje Z e e e jdddehdeegdgd  dd d d ddd ddfd Zeddfd ZdZddZdZdZedZxZS)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. {sampling_strategy} replacement : bool, default=False Whether or not to sample randomly with replacement or not. {random_state} base_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)``. .. deprecated:: 0.10 `base_estimator` is deprecated in version 0.10 and will be removed in 0.12. Use `estimator` instead. Attributes ---------- estimator_ : estimator The base estimator from which the ensemble is grown. .. versionadded:: 0.10 base_estimator_ : estimator The base estimator from which the ensemble is grown. .. 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 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([...]) z1.3rrright)closed> not majority not minorityallautomajoritybooleanr replacementN2?SAMME.Rr!F deprecated) n_estimators learning_rate algorithmrr%rbase_estimatorc tjtj} d|i} d| jvr|| d<n||_tjdi| ||||d||_||_dS)Nr- estimator)r*r+r,r)inspect signaturesuper__init__ parametersr/rr%) selfr/r*r+r,rr%rr-bagging_classifier_signatureestimator_params __class__s Blib/python3.11/site-packages/imblearn/ensemble/_weight_boosting.pyr4zRUSBoostClassifier.__init__s(/'89I'J'J$,n= 6A A A,5 [ ) )&DN   %'%      "3&)prefer_skip_nested_validationc|t|g|_g|_t ||||S)aBuild a boosted classifier from the training set (X, y). Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) The training input samples. Sparse matrix can be CSC, CSR, COO, DOK, or LIL. DOK and LIL are converted to CSR. y : array-like of shape (n_samples,) The target values (class labels). sample_weight : array-like of shape (n_samples,), default=None Sample weights. If None, the sample weights are initialized to ``1 / n_samples``. Returns ------- self : object Returns self. )_validate_paramsr samplers_ pipelines_r3fit)r6Xy sample_weightr9s r:rAzRUSBoostClassifier.fitsR, !  Aq-((( r;c~|j|jdvrtdtd}|jt |j}nG|jdvr/t jdtt |j}nt |}||_ |j|_ n#t$rYnwxYw|j dkr$t|jdstd t|jd s!t|jjjd t#|j|j |_dS) zfCheck the estimator and the n_estimator attribute. Sets the `estimator_` attributes. N)Nr)zEBoth `estimator` and `base_estimator` were set. Only set `estimator`.r) max_depthzX`base_estimator` was renamed to `estimator` in version 0.10 and will be removed in 0.12.r( predict_probazAdaBoostClassifier with algorithm='SAMME.R' requires that the weak learner supports the calculation of class probabilities with a predict_proba method. Please change the base estimator or set algorithm='SAMME' instead.rDz doesn't support sample_weight.r$)r/r- ValueErrorrrwarningswarn FutureWarning _estimatorbase_estimator_AttributeErrorr,hasattr TypeErrorr r9__name__rrr% base_sampler_)r6defaultr-s r:_validate_estimatorz&RUSBoostClassifier._validate_estimators > %  '; ; ;W )1555 > %"4>22NN  (< < < M+    #4#677NN"7^^N( #'?D     D  >Y & &4?O<< 1!/BB ?,5VVV 0"4(   s B(( B54B5Tctj}|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|Sr0)getattr).0pr6s r: z>RUSBoostClassifier._make_sampler_estimator..9s%SSS74#3#3SSSr;Nr0) rrL set_paramsr8rRr estimators_appendr?r@r r)r6r]rr/samplers` r:_make_sampler_estimatorz*RUSBoostClassifier._make_sampler_estimator3s $/**  TTSSSST=RSSSTTT*++  # y, 7 7 7 w 5 5 5     # #I . . . N ! !' * * * O " "hw//)1D1DEE   '!!r;c0||\}}|||\}} t||j} ||| | ||} |dkr/t |dd|_t|j|_ |j tj | dd} | |k} tj tj| |d}|dkr|d d fS|j }|j}tjd |dz z d g}| ||ddtjfk}| }tj|tj|jjd| d |jz|d z |z z|tj| zdz}||jdz ks%|tj||dk|dkzzz}|d |fS) z:Implement a single boost using the SAMME.R real algorithm.rrDrclasses_Nr)axisweightsrdr'g)out)r_ fit_resamplersample_indices_rArGrWrclen n_classes_takenpargmaxmeanaveragearraynewaxisclipfinfodtypeepsr+logsumr*exp)r6iboostrBrCrDrr/r^X_resy_ressample_weight_resy_predict_proba y_predict incorrectestimator_error n_classesclassesy_codesy_codingprobaestimator_weights r: _boost_realzRUSBoostClassifier._boost_realIs9!99|9TT 7++Aq11 u*=':QRR eU2C DDD#11!44 Q;;#Iz4@@DM!$-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?22r;c||\}}|||\}} 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) zrs //////555555//////77777777666666))))))$$$$$$//////22222233333333666666::::::::&&&&&&??????- 344&C(\\\\\/1C\\ \\\r;