REF: re-use validate_setitem_value in Categorical.fillna (#37597)

Author: jbrockmendel

pandas/core/arrays/categorical.py

@@ -1655,21 +1655,15 @@ def fillna(self, value=None, method=None, limit=None):
             codes = self._ndarray.copy()
             mask = self.isna()
 
+            new_codes = self._validate_setitem_value(value)
+
             if isinstance(value, (np.ndarray, Categorical)):
                 # We get ndarray or Categorical if called via Series.fillna,
                 #  where it will unwrap another aligned Series before getting here
-
-                not_categories = ~algorithms.isin(value, self.categories)
-                if not isna(value[not_categories]).all():
-                    # All entries in `value` must either be a category or NA
-                    raise ValueError("fill value must be in categories")
-
-                values_codes = _get_codes_for_values(value, self.categories)
-                codes[mask] = values_codes[mask]
+                codes[mask] = new_codes[mask]
 
             else:
-                new_code = self._validate_fill_value(value)
-                codes[mask] = new_code
+                codes[mask] = new_codes
 
         return self._from_backing_data(codes)
 

pandas/tests/arrays/categorical/test_missing.py

@@ -60,7 +60,10 @@ def test_set_item_nan(self):
             ),
             (dict(), "Must specify a fill 'value' or 'method'."),
             (dict(method="bad"), "Invalid fill method. Expecting .* bad"),
-            (dict(value=Series([1, 2, 3, 4, "a"])), "fill value must be in categories"),
+            (
+                dict(value=Series([1, 2, 3, 4, "a"])),
+                "Cannot setitem on a Categorical with a new category",
+            ),
         ],
     )
     def test_fillna_raises(self, fillna_kwargs, msg):

pandas/tests/frame/methods/test_fillna.py

@@ -170,7 +170,7 @@ def test_na_actions_categorical(self):
         res = df.fillna(value={"cats": 3, "vals": "b"})
         tm.assert_frame_equal(res, df_exp_fill)
 
-        msg = "'fill_value=4' is not present in this Categorical's categories"
+        msg = "Cannot setitem on a Categorical with a new category"
         with pytest.raises(ValueError, match=msg):
             df.fillna(value={"cats": 4, "vals": "c"})
 

pandas/tests/indexes/categorical/test_fillna.py

@@ -14,7 +14,7 @@ def test_fillna_categorical(self):
         tm.assert_index_equal(idx.fillna(1.0), exp)
 
         # fill by value not in categories raises ValueError
-        msg = "'fill_value=2.0' is not present in this Categorical's categories"
+        msg = "Cannot setitem on a Categorical with a new category"
         with pytest.raises(ValueError, match=msg):
             idx.fillna(2.0)
 
@@ -36,7 +36,7 @@ def test_fillna_validates_with_no_nas(self):
         ci = CategoricalIndex([2, 3, 3])
         cat = ci._data
 
-        msg = "'fill_value=False' is not present in this Categorical's categories"
+        msg = "Cannot setitem on a Categorical with a new category"
         with pytest.raises(ValueError, match=msg):
             ci.fillna(False)
 

pandas/tests/series/methods/test_fillna.py

@@ -653,14 +653,14 @@ def test_fillna_categorical_raises(self):
         data = ["a", np.nan, "b", np.nan, np.nan]
         ser = Series(Categorical(data, categories=["a", "b"]))
 
-        msg = "'fill_value=d' is not present in this Categorical's categories"
+        msg = "Cannot setitem on a Categorical with a new category"
         with pytest.raises(ValueError, match=msg):
             ser.fillna("d")
 
-        with pytest.raises(ValueError, match="fill value must be in categories"):
+        with pytest.raises(ValueError, match=msg):
             ser.fillna(Series("d"))
 
-        with pytest.raises(ValueError, match="fill value must be in categories"):
+        with pytest.raises(ValueError, match=msg):
             ser.fillna({1: "d", 3: "a"})
 
         msg = '"value" parameter must be a scalar or dict, but you passed a "list"'