Ensure that :func: in :class: only replaces null values

Author: Marco Gorelli

doc/source/whatsnew/v0.25.1.rst

@@ -21,6 +21,8 @@ Other enhancements
 Bug fixes
 ~~~~~~~~~
 
+- Bug in :func:`fill_na` in :class:`Categorical` would replace all values, not just those that are NaN (:issue:`26215`)
+
 
 Categorical
 ^^^^^^^^^^^

pandas/core/arrays/categorical.py

@@ -1824,7 +1824,6 @@ def fillna(self, value=None, method=None, limit=None):
 
         # pad / bfill
         if method is not None:
-
             values = self.to_dense().reshape(-1, len(self))
             values = interpolate_2d(values, method, 0, None, value).astype(
                 self.categories.dtype
@@ -1838,10 +1837,9 @@ def fillna(self, value=None, method=None, limit=None):
             if isinstance(value, ABCSeries):
                 if not value[~value.isin(self.categories)].isna().all():
                     raise ValueError("fill value must be in categories")
-
                 values_codes = _get_codes_for_values(value, self.categories)
-                indexer = np.where(values_codes != -1)
-                codes[indexer] = values_codes[values_codes != -1]
+                indexer = np.where(codes == -1)
+                codes[indexer] = values_codes[codes == -1]
 
             # If value is not a dict or Series it should be a scalar
             elif is_hashable(value):

pandas/tests/series/test_missing.py

@@ -578,6 +578,28 @@ def test_fillna_categorical(self, fill_value, expected_output):
         exp = Series(Categorical(expected_output, categories=["a", "b"]))
         tm.assert_series_equal(s.fillna(fill_value), exp)
 
+    @pytest.mark.parametrize(
+        "new_categories, fill_value, expected_output",
+        [
+            (
+                ["c", "d", "e"],
+                Series(["a", "b", "c", "d", "e"]),
+                ["a", "b", "b", "d", "e"],
+            )
+        ],
+    )
+    def test_fillna_categorical_with_new_categories(
+        self, new_categories, fill_value, expected_output
+    ):
+        # GH 26215
+        data = ["a", np.nan, "b", np.nan, np.nan]
+        s = Series(Categorical(data, categories=["a", "b"]))
+        s.cat.add_categories(new_categories, inplace=True)
+        exp = Series(
+            Categorical(expected_output, categories=["a", "b"] + new_categories)
+        )
+        tm.assert_series_equal(s.fillna(fill_value), exp)
+
     def test_fillna_categorical_raise(self):
         data = ["a", np.nan, "b", np.nan, np.nan]
         s = Series(Categorical(data, categories=["a", "b"]))