FIX _estimator_type in robust estimators (#108)

Author: TimotheeMathieu

doc/changelog.rst

@@ -1,6 +1,12 @@
 Changelog
 =========
 
+Unreleased
+----------
+
+- Fix `_estimator_type` for :class:`~sklearn_extra.robust` estimators. Fix
+  misbehavior of scikit-learn's :class:`~sklearn.model_selection.cross_val_score` and
+  :class:`~sklearn.grid_search.GridSearchCV` for :class:`~sklearn_extra.robust.RobustWeightedClassifier`
 
 Version 0.2.0
 -------------

sklearn_extra/robust/robust_weighted_estimator.py

@@ -790,6 +790,8 @@ def fit(self, X, y):
             sgd_args = self.sgd_args
 
         # Define the base estimator
+        X, y = self._validate_data(X, y, y_numeric=False)
+
         base_robust_estimator_ = _RobustWeightedEstimator(
             SGDClassifier(**sgd_args, eta0=self.eta0),
             weighting=self.weighting,
@@ -874,10 +876,6 @@ def predict_proba(self):
     def _predict_proba(self, X):
         return self.base_estimator_.predict_proba(X)
 
-    @property
-    def _estimator_type(self):
-        return self.base_estimator._estimator_type
-
     def score(self, X, y=None):
         """Returns the score on the given data, using
         ``base_estimator_.score``.
@@ -1103,6 +1101,8 @@ def fit(self, X, y):
 
         # Define the base estimator
 
+        X, y = self._validate_data(X, y, y_numeric=True)
+
         self.base_estimator_ = _RobustWeightedEstimator(
             SGDRegressor(**sgd_args, eta0=self.eta0),
             weighting=self.weighting,
@@ -1142,10 +1142,6 @@ def predict(self, X):
         check_is_fitted(self, attributes=["base_estimator_"])
         return self.base_estimator_.predict(X)
 
-    @property
-    def _estimator_type(self):
-        return self.base_estimator._estimator_type
-
     def score(self, X, y=None):
         """Returns the score on the given data, using
         ``base_estimator_.score``.
@@ -1350,14 +1346,13 @@ def fit(self, X, y=None):
             kmeans_args = {}
         else:
             kmeans_args = self.kmeans_args
-        X = check_array(
+        X = self._validate_data(
             X,
             accept_sparse="csr",
             dtype=[np.float64, np.float32],
             order="C",
             accept_large_sparse=False,
         )
-
         self.base_estimator_ = _RobustWeightedEstimator(
             MiniBatchKMeans(
                 self.n_clusters,
@@ -1404,10 +1399,6 @@ def predict(self, X):
         check_is_fitted(self, attributes=["base_estimator_"])
         return self.base_estimator_.predict(X)
 
-    @property
-    def _estimator_type(self):
-        return self.base_estimator._estimator_type
-
     def score(self, X, y=None):
         """Returns the score on the given data, using
         ``base_estimator_.score``.