o i҂ @s dZddlZddlmZddlZddlZddlmZddl m Z ddl m Z ddl mZmZmZmZddlmZmZmZmZmZmZdd lmZmZdd lmZmZmZm Z dd l!m"Z"m#Z#dd l$m%Z%m&Z&m'Z'm(Z(dd l)m*Z*m+Z+m,Z,ddl-m.Z.ddl/m0Z0ddl1m2Z2ddl3m4Z4m5Z5m6Z6ddl7m8Z8m9Z9m:Z:m;Z;ddlm?Z?m@Z@mAZAddlBmCZCmDZDmEZEeZFeFjGeFjHZIZJeZKeKjGeKjHZLZMeddd\ZNZOeddd\ZPZQejRSdde+ddddgejRSddeddgejRSdd dgd!d"ZTd#d$ZUd%d&ZVd'd(ZWejRSdde*ddddgejRSd)difeddifed*difgejRSdd dgd+d,ZXejRSd-eCeDeEd.d/ZYejRSd-eCeDeEd0d1ZZd2d3Z[Gd4d5d5eeZ\Gd6d7d7eeZ]ejRSd8eMd9gie^d:feMd;e&fdfgd?d@e^dAfeMd9d;e&fdBe]fgie_dCfeMd;e&fdBe5d=d>fge]dDe_dCfgdEdFZ`ejRSd8eJd9gie^d:feJd9d;e%fdBe\fgie_dCfeJd;e%fdBe6fge\dDe_dCfgdGdHZaejRjSdIed;e&ddfd             rZc Cstdd\}}tt|||dd\}}}}dtfdtddfg}t|dd }|||||}|jd d ks;Jdtfd t fg}|j |d |||||}|jd d ks_JdS)NTZ return_X_yr1r9r:rfr7r0r=r4rAr3r;r=) r rr!rrrrHrLrMr#rN) XyrPrQrR_r=rTrUrXrXrY:test_stacking_classifier_drop_column_binary_classificationqs         rbcCstttttdd\}}}}ddtddfg}tddd}tdtddfg|d d }t||d d }||||||t| || |t| || |t| || |dS) Nr1r9r:rCr;rr7r?Z n_estimatorsr2r=r6r4) rr!rFrGr#rrrHr*rIrJrL)rPrQrRrar=r\rTZclf_droprXrXrY'test_stacking_classifier_drop_estimators     rgcCsttttdd\}}}}ddtddfg}tddd}tdtddfg|dd }t||dd }||||||t| || |t| || |dS) Nr1r7rcsvrrr?rdrerf) rr! X_diabetes y_diabetesr$rrrHr*rIrL)rPrQrRrar=r\regZreg_droprXrXrY&test_stacking_regressor_drop_estimators    rlzfinal_estimator, predict_paramsZ return_stdcCs2ttttdd\}}}}dtfdtfg}t||||d} | ||| j|fi|} |r2dnd} |r>t | | ks>J| |} |rGdnd} | j d| ksRJ|rat || ddd df| j d d | ||| || |} |r{d nd}| j d|ksJ|rt || ddd dfdSdS) Nr1r7r:rhr<r3rA rCrD )rr!rirjrr$rrHrIlenrLrMr*rN)r4r6Zpredict_paramsr8rPrQrRrar=rkresultZexpected_result_lengthrUrVrWrXrXrY test_stacking_regressor_diabetess:          rrsparse_containerc Ct|tttdd\}}}}dtfdtfg}tddd}t||ddd }|||| |}t ||ddd dft |sFJ|j |j ksNJdS) Nr1r7r:rhr?rdreTr<rn)rr!rirjrr$rrrHrLr+rissparseformat rsrPrQrRrar=r\rTrUrXrXrY*test_stacking_regressor_sparse_passthrough   rxc Crt) Nr1r7r:r;r?rdreTr<rB)rr!rFrGrr#rrrHrLr+rrurvrwrXrXrY+test_stacking_classifier_sparse_passthroughryrzcCshttddtdd}}dtfdtfg}t|d}|||||}|jddks2JdS)Ndr:r\r^rAr3) r!rFrGrrrrHrLrM)ZX_Zy_r=rTZX_metarXrXrY)test_stacking_classifier_drop_binary_prob s    r|c@seZdZddZddZdS)NoWeightRegressorcCst|_|j||SN)rrkrHselfr_r`rXrXrYrHszNoWeightRegressor.fitcCst|jdS)Nr)nponesrM)rr_rXrXrYrI szNoWeightRegressor.predictN)__name__ __module__ __qualname__rHrIrXrXrXrYr}s r}c@seZdZddZdS)NoWeightClassifiercCstdd|_|j||S)NZ stratified)Zstrategy)rrTrHrrXrXrYrH%s zNoWeightClassifier.fitN)rrrrHrXrXrXrYr$s rzy, params, type_err, msg_errr=zInvalid 'estimators' attribute,r:svmiPZmax_iterrJ)r= stack_methodz+does not implement the method predict_probaZcorzdoes not support sample weightr=r6cCjtj||d$tdi|ddi}|jtt|ttjddWddS1s.wYdSNmatchr4r0r sample_weightrX) pytestraisesrrHr!rFrrrM)r`paramstype_errmsg_errrTrXrXrYtest_stacking_classifier_error*s*""rcCrr) rrrrHr!rirrrM)r`rrrrkrXrXrYtest_stacking_regressor_errorYs""rzestimator, X, yr^r{rr)ZidscCst|}|jtdtjdddt|}|jdd|jtdtjdddt||||ddddf||||dS)NTrr5r2r4rCrDrA) r rNrrrandomZ RandomStater*rHrL) estimatorr_r`Zestimator_fullZestimator_droprXrXrYtest_stacking_randomnessws  rcCs2tdtddfdtddfgd}|ttdS)Nr:i'rrr^)rrr#rHrFrG)rTrXrXrY)test_stacking_classifier_stratify_defaults   rz stacker, X, yrrfr[c CsBt|d}tdg|dgt||}t|||dd\}}}}} }ttd|||Wdn1s;wY||} ttd|j||t|j dWdn1sawY||} t | | ttd|j||| dWdn1swY||} t | |  dksJdS) Nr3g?g?r1r7)categoryrr) rprarrayrr,rrHrIrrMr*abssum) stackerr_r`Zn_half_samplesZtotal_sample_weightrPrQrRraZsample_weight_trainZy_pred_no_weightZy_pred_unit_weightZ y_pred_biasedrXrXrY test_stacking_with_sample_weights* !       rcCs>tdtddfgtddd}|jttttjdddS)Nr:T)Zexpected_sample_weightrrr)rr)rHrFrGrrrM)rrXrXrY0test_stacking_classifier_sample_weight_fit_params  rz-ignore::sklearn.exceptions.ConvergenceWarningcCst|}t|}|jdd|jdd||||||t|j|jD] \}}t|j|jq'tjt ddt|j j|j jWddS1sOwYdS)Nr0rrez Not equalr) r rNrHzip estimators_r*Zcoef_rrAssertionErrorfinal_estimator_)rr_r`Z stacker_cv_3Z stacker_cv_5Zest_cv_3Zest_cv_5rXrXrYtest_stacking_cv_influences!     "rz7Stacker, Estimator, stack_method, final_estimator, X, yrIcCst||ddd\}}}} d|||fd|||fg} | D]\} } tdd| _t| |} t| d}||_t| ||q || d |d }||| |jd d | DksWJtd d|jDscJ|jD] } t| |}||qfdS)z2Check the behaviour of stacking when `cv='prefit'`r1g?)r2Z test_sizeZd0Zd1rH)name)Z side_effectprefit)r=r4r6cSsg|]\}}|qSrXrX).0rarrXrXrY Xsz(test_stacking_prefit..css|] }|jjdkVqdS)rN)rHZ call_count)rrrXrXrY Zsz'test_stacking_prefit..N) rrHrgetattrrsetattrrallZassert_called_with)ZStacker Estimatorrr6r_r`ZX_train1ZX_train2Zy_train1Zy_train2r=rarZ stack_funcZpredict_method_mockedrZstack_func_mockrXrXrYtest_stacking_prefit*s,        rrr]cCs<tt|||WddS1swYdSr~)rrrrH)rr_r`rXrXrYtest_stacking_prefit_errorbs "rz!make_dataset, Stacking, EstimatorcCsGddd|}|ddd\}}|d|fgd}|jd}tjt|d  |jWdn1s4wY|||d }tjt|d  |jWddS1sWwYdS) Ncs eZdZdZfddZZS)z8test_stacking_without_n_features_in..MyEstimatorz Estimator without n_features_in_cst|||`dSr~)superrHn_features_in_r __class__rXrYrHsz.MyEstimator.fit)rrr__doc__rH __classcell__rXrXrrY MyEstimatorsrrr{)r2Z n_samplesr:r^z' object has no attribute n_features_in_rz6'MyEstimator' object has no attribute 'n_features_in_')rrrAttributeErrorrrH)Z make_datasetZStackingrrr_r`rmsgrXrXrY#test_stacking_without_n_features_ins   "rrr rc Csttttdd\}}}}d}d|fg}t|tdd||}||}|j|jd|fks0Jtt |j dd d r>J| |} | j|jksKJd S) zCheck the behaviour for the multilabel classification case and the `predict_proba` stacking method. Estimators are not consistent with the output arrays and we need to ensure that we handle all cases. r1r9r0estrJr=r6rrrA)Zaxisg?N) r X_multilabel y_multilabelrrrHrLrManyriscloserrI) rrPrQrRrS n_outputsr=rrUy_predrXrXrY1test_stacking_classifier_multilabel_predict_probas"   rc Csttttdd\}}}}d}dtfg}t|tdd||}||}|j|jd|fks1J| |}|j|jks>JdS) zCheck the behaviour for the multilabel classification case and the `decision_function` stacking method. Only `RidgeClassifier` supports this case. r1r9r0rrOrrN) rrrrrrrHrLrMrI) rPrQrRrSrr=rrUrrXrXrY5test_stacking_classifier_multilabel_decision_functions    rrautocCsttttdd\}}}}|}d}dtddfdtddfdtfg}t} t|| ||d ||} t ||| |} | j |j ksEJ|d krNgd } nd gt |} | j| ks\J|t |} |rk| |j d 7} | |}|j |j d | fks|Jt | jtd d gg|dS)zCheck the behaviour for the multilabel classification case for stack methods supported for all estimators or automatically picked up. r1r9r0Zmlpr7r\ridge)r=r6r8rr)rJrJrOrIrArN)rrrcopyr rrrrrHrrIrMrpZ stack_method_rLZclasses_rr)rr8rPrQrRrSZy_train_before_fitrr=r6rTrZexpected_stack_methodsZn_features_X_transrUrXrXrY0test_stacking_classifier_multilabel_auto_predicts>        rz,stacker, feature_names, X, y, expected_names)Zstackingclassifier_lr0Zstackingclassifier_lr1Zstackingclassifier_lr2Zstackingclassifier_svm0Zstackingclassifier_svm1Zstackingclassifier_svm2)otherrCZstackingclassifier_lrZstackingclassifier_svmZstackingregressor_lrZstackingregressor_svm)ZStackingClassifier_multiclassZStackingClassifier_binaryrcCsF|j|d|t|||rt||f}||}t||dS)z/Check get_feature_names_out works for stacking.)r8N)rNrHr!rZ concatenateZget_feature_names_outr)r feature_namesr_r`Zexpected_namesr8Z names_outrXrXrYtest_get_feature_names_outs B rcCsftttttdd\}}}}tdtfgd}|||||||| ||dks1JdS)zNCheck that a regressor can be used as the first layer in `StackingClassifier`.r1r9rr^r>N) rr!rFrGrrrHrIrJrK)rPrQrRrSrTrXrXrY'test_stacking_classifier_base_regressor\s    rcCstdd\}}dtfdtdddfg}tddd}t||dd}d }d }tjt|d }||||Wd n1s@wYt |j j tsNJ|t |j j vsXJd S) a Check that we raise the proper AttributeError when the final estimator does not implement the `decision_function` method, which is decorated with `available_if`. Non-regression test for: https://github.com/scikit-learn/scikit-learn/issues/28108 r1r7r:r\r3rdr0rfz>This 'StackingClassifier' has no attribute 'decision_function'zD'RandomForestClassifier' object has no attribute 'decision_function'rN) r rrrrrrrHrO isinstancevalue __cause__str)r_r`r=r6rTZ outer_msgZ inner_msgZ exec_inforXrXrY-test_stacking_final_estimator_attribute_errorhs rzEstimator, ChildcCsTtjtdd|d|gjttgdddWddS1s#wYdS)zTest that the right error message is raised when metadata is passed while not supported when `enable_metadata_routing=False`.z1is only supported if enable_metadata_routing=TruerrT)rArArArArAarmetadataN)rr ValueErrorrHrFrG)rChildrXrXrY*test_routing_passed_metadata_not_supporteds  "r)Zenable_metadata_routingcCs|d|fg}|dS)Nsub_est)Zget_metadata_routing)rrrrXrXrY%test_get_metadata_routing_without_fits rzprop, prop_valuer)rrc Cs&|d|tdjd i|difd|tdjd i|difg|tdjd i|did}|jttfi||i|jttfi||i|jtfi||i|jD] }|dj }t |scJ|D]}t d |dd|d||iqeqV|j j }t |sJt d |d d d |d||id S) z5Test that metadata is routed correctly for Stacking*.Zsub_est1)registryTZsub_est2)r6rArH)objmethodparentZ split_paramsrINrX) r'Zset_fit_requestZset_predict_requestrHrFrGZ fit_transformrIr=rrpr(r)rrpropZ prop_valuerrrrrXrXrY-test_metadata_routing_for_stacking_estimatorssH      rcCsttjdd}}|d|fg}d|jd}tjtt |d|j tt ||dWddS1s9wYdS) zCTest that the right error is raised when metadata is not requested.rrrzb[sample_weight, metadata] are passed but are not explicitly set as requested or not requested for z.fitrrN) rrrFrMrrrrreescaperHrG)rrrrr error_messagerXrXrY3test_metadata_routing_error_for_stacking_estimatorss "r)xrrZ unittest.mockrnumpyrrZ numpy.testingrZscipyrZsklearnrZ sklearn.baserrrr Zsklearn.datasetsr r r r rrZ sklearn.dummyrrZsklearn.ensemblerrrrZsklearn.exceptionsrrZsklearn.linear_modelrrrrZsklearn.model_selectionrrrZsklearn.neighborsrZsklearn.neural_networkr Zsklearn.preprocessingr!Z sklearn.svmr"r#r$Z%sklearn.tests.metadata_routing_commonr%r&r'r(Zsklearn.utils._mockingr)Zsklearn.utils._testingr*r+r,Zsklearn.utils.fixesr-r.r/ZdiabetesdatatargetrirjZirisrFrGrrZX_binaryZy_binarymarkZ parametrizerZrbrgrlrrrxrzr|r}rr TypeErrorrrrrrrfilterwarningsrrrrrrrrrrrrrrrMrrrXrXrXrYs          '  $          )                       #     -       4<  !   .