BUG: fix categorical comparison with missing values (#26504 ) (#26514)

Author: another-green

doc/source/whatsnew/v0.25.0.rst

@@ -414,7 +414,7 @@ Categorical
 ^^^^^^^^^^^
 
 - Bug in :func:`DataFrame.at` and :func:`Series.at` that would raise exception if the index was a :class:`CategoricalIndex` (:issue:`20629`)
--
+- Fixed bug in comparison of ordered :class:`Categorical` that contained missing values with a scalar which sometimes incorrectly resulted in True (:issue:`26504`)
 -
 
 Datetimelike

pandas/core/arrays/categorical.py

@@ -89,18 +89,23 @@ def f(self, other):
             else:
                 other_codes = other._codes
 
-            na_mask = (self._codes == -1) | (other_codes == -1)
+            mask = (self._codes == -1) | (other_codes == -1)
             f = getattr(self._codes, op)
             ret = f(other_codes)
-            if na_mask.any():
+            if mask.any():
                 # In other series, the leads to False, so do that here too
-                ret[na_mask] = False
+                ret[mask] = False
             return ret
 
         if is_scalar(other):
             if other in self.categories:
                 i = self.categories.get_loc(other)
-                return getattr(self._codes, op)(i)
+                ret = getattr(self._codes, op)(i)
+
+                # check for NaN in self
+                mask = (self._codes == -1)
+                ret[mask] = False
+                return ret
             else:
                 if op == '__eq__':
                     return np.repeat(False, len(self))

pandas/tests/arrays/categorical/test_operators.py

@@ -1,4 +1,5 @@
 import operator
+import warnings
 
 import numpy as np
 import pytest
@@ -17,7 +18,6 @@ def test_categories_none_comparisons(self):
         tm.assert_categorical_equal(factor, self.factor)
 
     def test_comparisons(self):
-
         result = self.factor[self.factor == 'a']
         expected = self.factor[np.asarray(self.factor) == 'a']
         tm.assert_categorical_equal(result, expected)
@@ -186,6 +186,36 @@ def test_comparison_with_unknown_scalars(self):
         tm.assert_numpy_array_equal(cat != 4,
                                     np.array([True, True, True]))
 
+    def test_comparison_of_ordered_categorical_with_nan_to_scalar(
+            self, compare_operators_no_eq_ne):
+        # https://github.com/pandas-dev/pandas/issues/26504
+        # BUG: fix ordered categorical comparison with missing values (#26504 )
+        # and following comparisons with scalars in categories with missing
+        # values should be evaluated as False
+
+        cat = Categorical([1, 2, 3, None], categories=[1, 2, 3], ordered=True)
+        scalar = 2
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", RuntimeWarning)
+            expected = getattr(np.array(cat),
+                               compare_operators_no_eq_ne)(scalar)
+        actual = getattr(cat, compare_operators_no_eq_ne)(scalar)
+        tm.assert_numpy_array_equal(actual, expected)
+
+    def test_comparison_of_ordered_categorical_with_nan_to_listlike(
+            self, compare_operators_no_eq_ne):
+        # https://github.com/pandas-dev/pandas/issues/26504
+        # and following comparisons of missing values in ordered Categorical
+        # with listlike should be evaluated as False
+
+        cat = Categorical([1, 2, 3, None], categories=[1, 2, 3], ordered=True)
+        other = Categorical([2, 2, 2, 2], categories=[1, 2, 3], ordered=True)
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", RuntimeWarning)
+            expected = getattr(np.array(cat), compare_operators_no_eq_ne)(2)
+        actual = getattr(cat, compare_operators_no_eq_ne)(other)
+        tm.assert_numpy_array_equal(actual, expected)
+
     @pytest.mark.parametrize('data,reverse,base', [
         (list("abc"), list("cba"), list("bbb")),
         ([1, 2, 3], [3, 2, 1], [2, 2, 2])]