def _test_ridge_classifiers(filter_):
    n_classes = np.unique(y_iris).shape[0]
    n_features = X_iris.shape[1]
    for reg in (RidgeClassifier(), RidgeClassifierCV()):
        reg.fit(filter_(X_iris), y_iris)
        assert_equal(reg.coef_.shape, (n_classes, n_features))
        y_pred = reg.predict(filter_(X_iris))
        assert_greater(np.mean(y_iris == y_pred), .79)

    cv = KFold(5)
    reg = RidgeClassifierCV(cv=cv)
    reg.fit(filter_(X_iris), y_iris)
    y_pred = reg.predict(filter_(X_iris))
    assert_true(np.mean(y_iris == y_pred) >= 0.8)

def _test_ridge_classifiers(filter_):
    n_classes = np.unique(y_iris).shape[0]
    n_features = X_iris.shape[1]
    for clf in (RidgeClassifier(), RidgeClassifierCV()):
        clf.fit(filter_(X_iris), y_iris)
        assert_equal(clf.coef_.shape, (n_classes, n_features))
        y_pred = clf.predict(filter_(X_iris))
        assert_greater(np.mean(y_iris == y_pred), .79)

    n_samples = X_iris.shape[0]
    cv = KFold(n_samples, 5)
    clf = RidgeClassifierCV(cv=cv)
    clf.fit(filter_(X_iris), y_iris)
    y_pred = clf.predict(filter_(X_iris))
    assert_true(np.mean(y_iris == y_pred) >= 0.8)

def test_ridge_classifier_cv_store_cv_values():
    x = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0],
                  [1.0, 1.0], [1.0, 0.0]])
    y = np.array([1, 1, 1, -1, -1])

    n_samples = x.shape[0]
    alphas = [1e-1, 1e0, 1e1]
    n_alphas = len(alphas)

    r = RidgeClassifierCV(alphas=alphas, cv=None, store_cv_values=True)

    # with len(y.shape) == 1
    n_targets = 1
    r.fit(x, y)
    assert r.cv_values_.shape == (n_samples, n_targets, n_alphas)

    # with len(y.shape) == 2
    y = np.array([[1, 1, 1, -1, -1],
                  [1, -1, 1, -1, 1],
                  [-1, -1, 1, -1, -1]]).transpose()
    n_targets = y.shape[1]
    r.fit(x, y)
    assert r.cv_values_.shape == (n_samples, n_targets, n_alphas)

def test_class_weights_cv():
    # Test class weights for cross validated ridge classifier.
    X = np.array([[-1.0, -1.0], [-1.0, 0], [-0.8, -1.0], [1.0, 1.0], [1.0, 0.0]])
    y = [1, 1, 1, -1, -1]

    clf = RidgeClassifierCV(class_weight=None, alphas=[0.01, 0.1, 1])
    clf.fit(X, y)

    # we give a small weights to class 1
    clf = RidgeClassifierCV(class_weight={1: 0.001}, alphas=[0.01, 0.1, 1, 10])
    clf.fit(X, y)

    assert_array_equal(clf.predict([[-0.2, 2]]), np.array([-1]))