test_weight_boosting.py 文件源码

def test_sparse_regression():
    # Check regression with sparse input.

    class CustomSVR(SVR):
        """SVR 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(CustomSVR, self).fit(X, y, sample_weight=sample_weight)
            self.data_type_ = type(X)
            return self

    X, y = datasets.make_regression(n_samples=15, n_features=50, n_targets=1,
                                    random_state=42)

    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 = AdaBoostRegressor(
            base_estimator=CustomSVR(),
            random_state=1
        ).fit(X_train_sparse, y_train)

        # Trained on dense format
        dense_classifier = dense_results = AdaBoostRegressor(
            base_estimator=CustomSVR(),
            random_state=1
        ).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)

        # 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)

        types = [i.data_type_ for i in sparse_classifier.estimators_]

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