def test_iris():
    # Check consistency on dataset iris.
    classes = np.unique(iris.target)
    clf_samme = prob_samme = None

    for alg in ['SAMME', 'SAMME.R']:
        clf = AdaBoostClassifier(algorithm=alg)
        clf.fit(iris.data, iris.target)

        assert_array_equal(classes, clf.classes_)
        proba = clf.predict_proba(iris.data)
        if alg == "SAMME":
            clf_samme = clf
            prob_samme = proba
        assert proba.shape[1] == len(classes)
        assert clf.decision_function(iris.data).shape[1] == len(classes)

        score = clf.score(iris.data, iris.target)
        assert score > 0.9, "Failed with algorithm %s and score = %f" % \
            (alg, score)

        # Check we used multiple estimators
        assert len(clf.estimators_) > 1
        # Check for distinct random states (see issue #7408)
        assert (len(set(est.random_state
                        for est in clf.estimators_)) == len(clf.estimators_))

    # Somewhat hacky regression test: prior to
    # ae7adc880d624615a34bafdb1d75ef67051b8200,
    # predict_proba returned SAMME.R values for SAMME.
    clf_samme.algorithm = "SAMME.R"
    assert_array_less(0,
                      np.abs(clf_samme.predict_proba(iris.data) - prob_samme))
def test_classification_toy(algorithm):
    # Check classification on a toy dataset.
    clf = AdaBoostClassifier(algorithm=algorithm, random_state=0)
    clf.fit(X, y_class)
    assert_array_equal(clf.predict(T), y_t_class)
    assert_array_equal(np.unique(np.asarray(y_t_class)), clf.classes_)
    assert clf.predict_proba(T).shape == (len(T), 2)
    assert clf.decision_function(T).shape == (len(T), )
def test_sparse_classification():
    # Check classification with sparse input.

    class CustomSVC(SVC):
        """SVC variant that records the nature of the training set."""
        def fit(self, X, y, sample_weight=None):
            """Modification on fit caries data type for later verification."""
            super().fit(X, y, sample_weight=sample_weight)
            self.data_type_ = type(X)
            return self

    X, y = datasets.make_multilabel_classification(n_classes=1,
                                                   n_samples=15,
                                                   n_features=5,
                                                   random_state=42)
    # Flatten y to a 1d array
    y = np.ravel(y)

    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

    for sparse_format in [
            csc_matrix, csr_matrix, lil_matrix, coo_matrix, dok_matrix
    ]:
        X_train_sparse = sparse_format(X_train)
        X_test_sparse = sparse_format(X_test)

        # Trained on sparse format
        sparse_classifier = AdaBoostClassifier(
            base_estimator=CustomSVC(probability=True),
            random_state=1,
            algorithm="SAMME").fit(X_train_sparse, y_train)

        # Trained on dense format
        dense_classifier = AdaBoostClassifier(
            base_estimator=CustomSVC(probability=True),
            random_state=1,
            algorithm="SAMME").fit(X_train, y_train)

        # predict
        sparse_results = sparse_classifier.predict(X_test_sparse)
        dense_results = dense_classifier.predict(X_test)
        assert_array_equal(sparse_results, dense_results)

        # decision_function
        sparse_results = sparse_classifier.decision_function(X_test_sparse)
        dense_results = dense_classifier.decision_function(X_test)
        assert_array_almost_equal(sparse_results, dense_results)

        # predict_log_proba
        sparse_results = sparse_classifier.predict_log_proba(X_test_sparse)
        dense_results = dense_classifier.predict_log_proba(X_test)
        assert_array_almost_equal(sparse_results, dense_results)

        # predict_proba
        sparse_results = sparse_classifier.predict_proba(X_test_sparse)
        dense_results = dense_classifier.predict_proba(X_test)
        assert_array_almost_equal(sparse_results, dense_results)

        # score
        sparse_results = sparse_classifier.score(X_test_sparse, y_test)
        dense_results = dense_classifier.score(X_test, y_test)
        assert_array_almost_equal(sparse_results, dense_results)

        # staged_decision_function
        sparse_results = sparse_classifier.staged_decision_function(
            X_test_sparse)
        dense_results = dense_classifier.staged_decision_function(X_test)
        for sprase_res, dense_res in zip(sparse_results, dense_results):
            assert_array_almost_equal(sprase_res, dense_res)

        # staged_predict
        sparse_results = sparse_classifier.staged_predict(X_test_sparse)
        dense_results = dense_classifier.staged_predict(X_test)
        for sprase_res, dense_res in zip(sparse_results, dense_results):
            assert_array_equal(sprase_res, dense_res)

        # staged_predict_proba
        sparse_results = sparse_classifier.staged_predict_proba(X_test_sparse)
        dense_results = dense_classifier.staged_predict_proba(X_test)
        for sprase_res, dense_res in zip(sparse_results, dense_results):
            assert_array_almost_equal(sprase_res, dense_res)

        # staged_score
        sparse_results = sparse_classifier.staged_score(X_test_sparse, y_test)
        dense_results = dense_classifier.staged_score(X_test, y_test)
        for sprase_res, dense_res in zip(sparse_results, dense_results):
            assert_array_equal(sprase_res, dense_res)

        # Verify sparsity of data is maintained during training
        types = [i.data_type_ for i in sparse_classifier.estimators_]

        assert all([(t == csc_matrix or t == csr_matrix) for t in types])