fixes #56

Author: Will McGinnis

category_encoders/ordinal.py

@@ -267,7 +267,7 @@ def ordinal_encoding(X_in, mapping=None, cols=None, impute_missing=True, handle_
         else:
             mapping_out = []
             for col in cols:
-                categories = pd.unique(X[col].values)
+                categories = [x for x in pd.unique(X[col].values) if x is not None]
 
                 X[str(col) + '_tmp'] = np.nan
                 for idx, val in enumerate(categories):

category_encoders/tests/test_encoders.py

@@ -483,7 +483,7 @@ def test_onehot(self):
 
         enc = encoders.OneHotEncoder(verbose=1, return_df=False)
         enc.fit(X, None)
-        self.assertTrue(enc.transform(X_t[X_t['D'] != 'A']).shape[1] == 19)
+        self.assertTrue(enc.transform(X_t[X_t['D'] != 'A']).shape[1] == 18)
 
         enc = encoders.OneHotEncoder(verbose=1, return_df=True, impute_missing=True, handle_unknown='impute')
         enc.fit(X, None)

category_encoders/tests/test_none_nan.py

@@ -0,0 +1,29 @@
+import unittest
+import pandas as pd
+import category_encoders as ce
+import numpy as np
+
+__author__ = 'willmcginnis'
+
+
+class TestDist(unittest.TestCase):
+    """
+    """
+
+    def test_dist(self):
+        data = np.array([
+            ['apple', None],
+            ['peach', 'lemon']
+        ])
+        encoder = ce.OrdinalEncoder(impute_missing=True)
+        encoder.fit(data)
+        a = encoder.transform(data)
+        print(a)
+        self.assertEqual(a.values[0, 1], -1)
+        self.assertEqual(a.values[1, 1], 0)
+
+        encoder = ce.OrdinalEncoder(impute_missing=False)
+        encoder.fit(data)
+        a = encoder.transform(data)
+        self.assertTrue(np.isnan(a.values[0, 1]))
+        self.assertEqual(a.values[1, 1], 0)