Merge pull request #5234 from vighneshbirodkar/mcd_fix

ogrisel · ogrisel · commit 8d273a1e493d · 2015-10-12T13:33:54.000+02:00
[MRG + 1]Deprecating 1D inputs in fast_mcd
diff --git a/sklearn/covariance/robust_covariance.py b/sklearn/covariance/robust_covariance.py
@@ -361,11 +361,7 @@ def fast_mcd(X, support_fraction=None,
     """
     random_state = check_random_state(random_state)
 
-    X = np.asarray(X)
-    if X.ndim == 1:
-        X = np.reshape(X, (1, -1))
-        warnings.warn("Only one sample available. "
-                      "You may want to reshape your data array")
+    X = check_array(X, ensure_min_samples=2, estimator='fast_mcd')
     n_samples, n_features = X.shape
 
     # minimum breakdown value
@@ -609,7 +605,7 @@ def fit(self, X, y=None):
             Returns self.
 
         """
-        X = check_array(X)
+        X = check_array(X, ensure_min_samples=2, estimator='MinCovDet')
         random_state = check_random_state(self.random_state)
         n_samples, n_features = X.shape
         # check that the empirical covariance is full rank
diff --git a/sklearn/covariance/tests/test_robust_covariance.py b/sklearn/covariance/tests/test_robust_covariance.py
@@ -8,12 +8,14 @@
 
 from sklearn.utils.testing import assert_almost_equal
 from sklearn.utils.testing import assert_array_almost_equal
-from sklearn.utils.testing import assert_raises
+from sklearn.utils.testing import assert_raises, assert_warns
+from sklearn.utils.testing import assert_raise_message
 from sklearn.utils.validation import NotFittedError
 
 from sklearn import datasets
 from sklearn.covariance import empirical_covariance, MinCovDet, \
     EllipticEnvelope
+from sklearn.covariance import fast_mcd
 
 X = datasets.load_iris().data
 X_1d = X[:, 0]
@@ -40,6 +42,19 @@ def test_mcd():
     launch_mcd_on_dataset(500, 1, 100, 0.001, 0.001, 350)
 
 
+def test_fast_mcd_on_invalid_input():
+    X = np.arange(100)
+    assert_raise_message(ValueError, 'fast_mcd expects at least 2 samples',
+                         fast_mcd, X)
+
+
+def test_mcd_class_on_invalid_input():
+    X = np.arange(100)
+    mcd = MinCovDet()
+    assert_raise_message(ValueError, 'MinCovDet expects at least 2 samples',
+                         mcd.fit, X)
+
+
 def launch_mcd_on_dataset(n_samples, n_features, n_outliers, tol_loc, tol_cov,
                           tol_support):
 
diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
@@ -374,6 +374,10 @@ def check_array(array, accept_sparse=None, dtype="numeric", order=None,
 
         if ensure_2d:
             if array.ndim == 1:
+                if ensure_min_samples >= 2:
+                    raise ValueError("%s expects at least 2 samples provided "
+                                     "in a 2 dimensional array-like input"
+                                     % estimator_name)
                 warnings.warn(
                     "Passing 1d arrays as data is deprecated in 0.17 and will"
                     "raise ValueError in 0.19. Reshape your data either using "
