[MRG+1] Fixes #10284 Added store_cv_values to RidgeClassifierCV and a test.

sklearn/linear_model/ridge.py

@@ -1301,10 +1301,15 @@ class RidgeClassifierCV(LinearClassifierMixin, _BaseRidgeCV):
         weights inversely proportional to class frequencies in the input data
         as ``n_samples / (n_classes * np.bincount(y))``
 
+    store_cv_values : boolean, default=False
+        Flag indicating if the cross-validation values corresponding to
+        each alpha should be stored in the `cv_values_` attribute (see
+        below). This flag is only compatible with `cv=None` (i.e. using
+        Generalized Cross-Validation).
+
     Attributes
     ----------
-    cv_values_ : array, shape = [n_samples, n_alphas] or \
-    shape = [n_samples, n_responses, n_alphas], optional
+    cv_values_ : array, shape = [n_samples, n_targets, n_alphas], optional
         Cross-validation values for each alpha (if `store_cv_values=True` and
     `cv=None`). After `fit()` has been called, this attribute will contain \
     the mean squared errors (by default) or the values of the \
@@ -1332,11 +1337,13 @@ class RidgeClassifierCV(LinearClassifierMixin, _BaseRidgeCV):
     a one-versus-all approach. Concretely, this is implemented by taking
     advantage of the multi-variate response support in Ridge.
     """
+
     def __init__(self, alphas=(0.1, 1.0, 10.0), fit_intercept=True,
-                 normalize=False, scoring=None, cv=None, class_weight=None):
+                 normalize=False, scoring=None, cv=None, class_weight=None,
+                 store_cv_values=False):
         super(RidgeClassifierCV, self).__init__(
             alphas=alphas, fit_intercept=fit_intercept, normalize=normalize,
-            scoring=scoring, cv=cv)
+            scoring=scoring, cv=cv, store_cv_values=store_cv_values)
         self.class_weight = class_weight
 
     def fit(self, X, y, sample_weight=None):

sklearn/linear_model/tests/test_ridge.py

@@ -49,8 +49,11 @@
 X_iris = sp.csr_matrix(iris.data)
 y_iris = iris.target
 
-DENSE_FILTER = lambda X: X
-SPARSE_FILTER = lambda X: sp.csr_matrix(X)
+
+def DENSE_FILTER(X): return X
+
+
+def SPARSE_FILTER(X): return sp.csr_matrix(X)
 
 
 def test_ridge():
@@ -352,7 +355,7 @@ def _test_ridge_loo(filter_):
     assert_equal(ridge_gcv2.alpha_, alpha_)
 
     # check that we get same best alpha with custom score_func
-    func = lambda x, y: -mean_squared_error(x, y)
+    def func(x, y): return -mean_squared_error(x, y)
     scoring = make_scorer(func)
     ridge_gcv3 = RidgeCV(fit_intercept=False, scoring=scoring)
     f(ridge_gcv3.fit)(filter_(X_diabetes), y_diabetes)
@@ -576,7 +579,7 @@ def test_class_weights_cv():
 
 def test_ridgecv_store_cv_values():
     # Test _RidgeCV's store_cv_values attribute.
-    rng = rng = np.random.RandomState(42)
+    rng = np.random.RandomState(42)
 
     n_samples = 8
     n_features = 5
@@ -592,10 +595,37 @@ def test_ridgecv_store_cv_values():
     assert_equal(r.cv_values_.shape, (n_samples, n_alphas))
 
     # with len(y.shape) == 2
-    n_responses = 3
-    y = rng.randn(n_samples, n_responses)
+    n_targets = 3
+    y = rng.randn(n_samples, n_targets)
+    r.fit(x, y)
+    assert_equal(r.cv_values_.shape, (n_samples, n_targets, n_alphas))
+
+
+def test_ridge_classifier_cv_store_cv_values():
+    # Test RidgeClassifier
+    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, store_cv_values=True)
+
+    # with len(y.shape) == 1
+    n_targets = 1
+    r.fit(x, y)
+    assert_equal(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_equal(r.cv_values_.shape, (n_samples, n_responses, n_alphas))
+    assert_equal(r.cv_values_.shape, (n_samples, n_targets, n_alphas))
 
 
 def test_ridgecv_sample_weight():