scikit-learn
diff --git a/‎sklearn/preprocessing/_encoders.py
Lines changed: 20 additions & 8 deletions b/‎sklearn/preprocessing/_encoders.py
Lines changed: 20 additions & 8 deletions
diff --git a/‎sklearn/preprocessing/tests/test_encoders.py
Lines changed: 37 additions & 0 deletions b/‎sklearn/preprocessing/tests/test_encoders.py
Lines changed: 37 additions & 0 deletions
@@ -10,11 +10,12 @@
 import numpy as np
 from scipy import sparse
 
+from .. import get_config as _get_config
 from ..base import BaseEstimator, TransformerMixin
 from ..externals import six
 from ..utils import check_array
 from ..utils import deprecated
-from ..utils.fixes import _argmax
+from ..utils.fixes import _argmax, _object_dtype_isnan
 from ..utils.validation import check_is_fitted
 
 from .base import _transform_selected
@@ -37,14 +38,30 @@ class _BaseEncoder(BaseEstimator, TransformerMixin):
 
     """
 
-    def _fit(self, X, handle_unknown='error'):
+    def _check_X(self, X):
+        """
+        Perform custom check_array:
+        - convert list of strings to object dtype
+        - check for missing values for object dtype data (check_array does
+          not do that)
 
+        """
         X_temp = check_array(X, dtype=None)
         if not hasattr(X, 'dtype') and np.issubdtype(X_temp.dtype, np.str_):
             X = check_array(X, dtype=np.object)
         else:
             X = X_temp
 
+        if X.dtype == np.dtype('object'):
+            if not _get_config()['assume_finite']:
+                if _object_dtype_isnan(X).any():
+                    raise ValueError("Input contains NaN")
+
+        return X
+
+    def _fit(self, X, handle_unknown='error'):
+        X = self._check_X(X)
+
         n_samples, n_features = X.shape
 
         if self._categories != 'auto':
@@ -74,12 +91,7 @@ def _fit(self, X, handle_unknown='error'):
             self.categories_.append(cats)
 
     def _transform(self, X, handle_unknown='error'):
-
-        X_temp = check_array(X, dtype=None)
-        if not hasattr(X, 'dtype') and np.issubdtype(X_temp.dtype, np.str_):
-            X = check_array(X, dtype=np.object)
-        else:
-            X = X_temp
+        X = self._check_X(X)
 
         _, n_features = X.shape
         X_int = np.zeros_like(X, dtype=np.int)
 
@@ -497,6 +497,25 @@ def test_one_hot_encoder_feature_names_unicode():
     assert_array_equal([u'n👍me_c❤t1', u'n👍me_dat2'], feature_names)
 
 
+@pytest.mark.parametrize("X", [np.array([[1, np.nan]]).T,
+                               np.array([['a', np.nan]], dtype=object).T],
+                         ids=['numeric', 'object'])
+@pytest.mark.parametrize("handle_unknown", ['error', 'ignore'])
+def test_one_hot_encoder_raise_missing(X, handle_unknown):
+    ohe = OneHotEncoder(categories='auto', handle_unknown=handle_unknown)
+
+    with pytest.raises(ValueError, match="Input contains NaN"):
+        ohe.fit(X)
+
+    with pytest.raises(ValueError, match="Input contains NaN"):
+        ohe.fit_transform(X)
+
+    ohe.fit(X[:1, :])
+
+    with pytest.raises(ValueError, match="Input contains NaN"):
+        ohe.transform(X)
+
+
 @pytest.mark.parametrize("X", [
     [['abc', 2, 55], ['def', 1, 55]],
     np.array([[10, 2, 55], [20, 1, 55]]),
@@ -524,6 +543,24 @@ def test_ordinal_encoder_inverse():
     assert_raises_regex(ValueError, msg, enc.inverse_transform, X_tr)
 
 
+@pytest.mark.parametrize("X", [np.array([[1, np.nan]]).T,
+                               np.array([['a', np.nan]], dtype=object).T],
+                         ids=['numeric', 'object'])
+def test_ordinal_encoder_raise_missing(X):
+    ohe = OrdinalEncoder()
+
+    with pytest.raises(ValueError, match="Input contains NaN"):
+        ohe.fit(X)
+
+    with pytest.raises(ValueError, match="Input contains NaN"):
+        ohe.fit_transform(X)
+
+    ohe.fit(X[:1, :])
+
+    with pytest.raises(ValueError, match="Input contains NaN"):
+        ohe.transform(X)
+
+
 def test_encoder_dtypes():
     # check that dtypes are preserved when determining categories
     enc = OneHotEncoder(categories='auto')