def test_thresholded_scorers_multilabel_indicator_data(): """Test that the scorer work with multilabel-indicator format for multilabel and multi-output multi-class classifier """ X, y = make_multilabel_classification(return_indicator=True, allow_unlabeled=False, random_state=0) X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) # Multi-output multi-class predict_proba clf = DecisionTreeClassifier() clf.fit(X_train, y_train) y_proba = clf.predict_proba(X_test) score1 = SCORERS['roc_auc'](clf, X_test, y_test) score2 = roc_auc_score(y_test, np.vstack(p[:, -1] for p in y_proba).T) assert_almost_equal(score1, score2) # Multi-output multi-class decision_function # TODO Is there any yet? clf = DecisionTreeClassifier() clf.fit(X_train, y_train) clf._predict_proba = clf.predict_proba clf.predict_proba = None clf.decision_function = lambda X: [p[:, 1] for p in clf._predict_proba(X)] y_proba = clf.decision_function(X_test) score1 = SCORERS['roc_auc'](clf, X_test, y_test) score2 = roc_auc_score(y_test, np.vstack(p for p in y_proba).T) assert_almost_equal(score1, score2) # Multilabel predict_proba clf = OneVsRestClassifier(DecisionTreeClassifier()) clf.fit(X_train, y_train) score1 = SCORERS['roc_auc'](clf, X_test, y_test) score2 = roc_auc_score(y_test, clf.predict_proba(X_test)) assert_almost_equal(score1, score2) # Multilabel decision function clf = OneVsRestClassifier(LinearSVC(random_state=0)) clf.fit(X_train, y_train) score1 = SCORERS['roc_auc'](clf, X_test, y_test) score2 = roc_auc_score(y_test, clf.decision_function(X_test)) assert_almost_equal(score1, score2)
def test_thresholded_scorers_multilabel_indicator_data(): """Test that the scorer work with multilabel-indicator format for multilabel and multi-output multi-class classifier """ X, y = make_multilabel_classification(return_indicator=True, allow_unlabeled=False, random_state=0) X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) # Multi-output multi-class predict_proba clf = DecisionTreeClassifier() clf.fit(X_train, y_train) y_proba = clf.predict_proba(X_test) score1 = SCORERS['roc_auc'](clf, X_test, y_test) score2 = roc_auc_score(y_test, np.vstack(p[:, -1] for p in y_proba).T) assert_almost_equal(score1, score2) # Multi-output multi-class decision_function # TODO Is there any yet? clf = DecisionTreeClassifier() clf.fit(X_train, y_train) clf._predict_proba = clf.predict_proba clf.predict_proba = None clf.decision_function = lambda X: [p[:, 1] for p in clf._predict_proba(X)] y_proba = clf.decision_function(X_test) score1 = SCORERS['roc_auc'](clf, X_test, y_test) score2 = roc_auc_score(y_test, np.vstack(p for p in y_proba).T) assert_almost_equal(score1, score2) # Multilabel predict_proba clf = OneVsRestClassifier(DecisionTreeClassifier()) clf.fit(X_train, y_train) score1 = SCORERS['roc_auc'](clf, X_test, y_test) score2 = roc_auc_score(y_test, clf.predict_proba(X_test)) assert_almost_equal(score1, score2) # Multilabel decision function clf = OneVsRestClassifier(LinearSVC(random_state=0)) clf.fit(X_train, y_train) score1 = SCORERS['roc_auc'](clf, X_test, y_test) score2 = roc_auc_score(y_test, clf.decision_function(X_test)) assert_almost_equal(score1, score2)