BUG: fixed .str.contains(..., na=False) for categorical series

doc/source/whatsnew/v0.24.0.txt

@@ -704,7 +704,7 @@ Numeric
 Strings
 ^^^^^^^
 
--
+- Bug in :class:`StringMethods` where `str_contains()` was not filling missing values with given argument for na for a categorical Series (:issue:`22158`)
 -
 -
 

pandas/core/strings.py

@@ -1862,7 +1862,7 @@ def __iter__(self):
             g = self.get(i)
 
     def _wrap_result(self, result, use_codes=True,
-                     name=None, expand=None):
+                     name=None, expand=None, fill_value=np.nan):
 
         from pandas.core.index import Index, MultiIndex
 
@@ -1872,7 +1872,8 @@ def _wrap_result(self, result, use_codes=True,
         # so make it possible to skip this step as the method already did this
         # before the transformation...
         if use_codes and self._is_categorical:
-            result = take_1d(result, self._orig.cat.codes)
+            result = take_1d(result, self._orig.cat.codes,
+                             fill_value=fill_value)
 
         if not hasattr(result, 'ndim') or not hasattr(result, 'dtype'):
             return result
@@ -2499,12 +2500,12 @@ def join(self, sep):
     def contains(self, pat, case=True, flags=0, na=np.nan, regex=True):
         result = str_contains(self._parent, pat, case=case, flags=flags, na=na,
                               regex=regex)
-        return self._wrap_result(result)
+        return self._wrap_result(result, fill_value=na)
 
     @copy(str_match)
     def match(self, pat, case=True, flags=0, na=np.nan):
         result = str_match(self._parent, pat, case=case, flags=flags, na=na)
-        return self._wrap_result(result)
+        return self._wrap_result(result, fill_value=na)
 
     @copy(str_replace)
     def replace(self, pat, repl, n=-1, case=None, flags=0, regex=True):

pandas/tests/test_strings.py

@@ -543,10 +543,26 @@ def test_contains(self):
         assert result.dtype == np.bool_
         tm.assert_numpy_array_equal(result, expected)
 
-        # na
-        values = Series(['om', 'foo', np.nan])
-        res = values.str.contains('foo', na="foo")
-        assert res.loc[2] == "foo"
+        # na for category
+        values = Series(["a", "b", "c", "a", np.nan], dtype="category")
+        result = values.str.contains('a', na=True).astype(object)
+        expected = Series([True, False, False, True, True], dtype=np.object_)
+        assert isinstance(result, Series)
+        tm.assert_series_equal(result, expected)
+
+        result = values.str.contains('a', na=False).astype(object)
+        expected = Series([True, False, False, True, False], dtype=np.object_)
+        tm.assert_series_equal(result, expected)
+
+        # na for objects
+        values = Series(["a", "b", "c", "a", np.nan])
+        result = values.str.contains('a', na=True).astype(object)
+        expected = Series([True, False, False, True, True], dtype=np.object_)
+        tm.assert_series_equal(result, expected)
+
+        result = values.str.contains('a', na=False).astype(object)
+        expected = Series([True, False, False, True, False], dtype=np.object_)
+        tm.assert_series_equal(result, expected)
 
     def test_startswith(self):
         values = Series(['om', NA, 'foo_nom', 'nom', 'bar_foo', NA, 'foo'])