FIX SVR complaining about a single class in the input

Decoupled SVC and SVR input validation logic. Fixes scikit-learn#1896.

BaseLibSVM could still do with some more refactoring to move
subclass-specific code out of its methods.

Author: larsmans

sklearn/svm/base.py

@@ -131,19 +131,7 @@ def fit(self, X, y, sample_weight=None):
                              "by not using the ``sparse`` parameter")
 
         X = atleast2d_or_csr(X, dtype=np.float64, order='C')
-
-        if self._impl in ['c_svc', 'nu_svc']:
-            # classification
-            self.classes_, y = unique(y, return_inverse=True)
-            self.class_weight_ = compute_class_weight(self.class_weight,
-                                                      self.classes_, y)
-        else:
-            self.class_weight_ = np.empty(0)
-        if self._impl != "one_class" and len(np.unique(y)) < 2:
-            raise ValueError("The number of classes has to be greater than"
-                             " one.")
-
-        y = np.asarray(y, dtype=np.float64, order='C')
+        y = self._validate_targets(y)
 
         sample_weight = np.asarray([]
                                    if sample_weight is None
@@ -190,6 +178,16 @@ def fit(self, X, y, sample_weight=None):
             self.intercept_ *= -1
         return self
 
+    def _validate_targets(self, y):
+        """Validation of y and class_weight.
+
+        Default implementation for SVR and one-class; overridden in BaseSVC.
+        """
+        # XXX this is ugly.
+        # Regression models should not have a class_weight_ attribute.
+        self.class_weight_ = np.empty(0)
+        return np.asarray(y, dtype=np.float64, order='C')
+
     def _warn_from_fit_status(self):
         assert self.fit_status_ in (0, 1)
         if self.fit_status_ == 1:
@@ -434,6 +432,16 @@ def coef_(self):
 class BaseSVC(BaseLibSVM, ClassifierMixin):
     """ABC for LibSVM-based classifiers."""
 
+    def _validate_targets(self, y):
+        self.classes_, y = unique(y, return_inverse=True)
+        self.class_weight_ = compute_class_weight(self.class_weight,
+                                                  self.classes_, y)
+        if len(np.unique(y)) < 2:
+            raise ValueError(
+                "The number of classes has to be greater than one")
+
+        return np.asarray(y, dtype=np.float64, order='C')
+
     def predict(self, X):
         """Perform classification on samples in X.
 

sklearn/svm/tests/test_svm.py

@@ -175,6 +175,10 @@ def test_svr():
         clf.fit(diabetes.data, diabetes.target)
         assert_greater(clf.score(diabetes.data, diabetes.target), 0.02)
 
+    # non-regression test; previously, BaseLibSVM would check that
+    # len(np.unique(y)) < 2, which must only be done for SVC
+    svm.SVR().fit(diabetes.data, np.ones(len(diabetes.data)))
+
 
 def test_svr_errors():
     X = [[0.0], [1.0]]