test_validation.py 文件源码

def test_cross_val_predict_input_types():
    iris = load_iris()
    X, y = iris.data, iris.target
    X_sparse = coo_matrix(X)
    multioutput_y = np.column_stack([y, y[::-1]])

    clf = Ridge(fit_intercept=False, random_state=0)
    # 3 fold cv is used --> atleast 3 samples per class
    # Smoke test
    predictions = cross_val_predict(clf, X, y)
    assert_equal(predictions.shape, (150,))

    # test with multioutput y
    predictions = cross_val_predict(clf, X_sparse, multioutput_y)
    assert_equal(predictions.shape, (150, 2))

    predictions = cross_val_predict(clf, X_sparse, y)
    assert_array_equal(predictions.shape, (150,))

    # test with multioutput y
    predictions = cross_val_predict(clf, X_sparse, multioutput_y)
    assert_array_equal(predictions.shape, (150, 2))

    # test with X and y as list
    list_check = lambda x: isinstance(x, list)
    clf = CheckingClassifier(check_X=list_check)
    predictions = cross_val_predict(clf, X.tolist(), y.tolist())

    clf = CheckingClassifier(check_y=list_check)
    predictions = cross_val_predict(clf, X, y.tolist())

    # test with 3d X and
    X_3d = X[:, :, np.newaxis]
    check_3d = lambda x: x.ndim == 3
    clf = CheckingClassifier(check_X=check_3d)
    predictions = cross_val_predict(clf, X_3d, y)
    assert_array_equal(predictions.shape, (150,))