REF: de-duplicate Categorical _validate_foo_value (#41919)

Author: jbrockmendel

doc/source/user_guide/categorical.rst

@@ -777,8 +777,8 @@ value is included in the ``categories``:
     df
     try:
         df.iloc[2:4, :] = [["c", 3], ["c", 3]]
-    except ValueError as e:
-        print("ValueError:", str(e))
+    except TypeError as e:
+        print("TypeError:", str(e))
 
 Setting values by assigning categorical data will also check that the ``categories`` match:
 
@@ -788,8 +788,8 @@ Setting values by assigning categorical data will also check that the ``categori
     df
     try:
         df.loc["j":"k", "cats"] = pd.Categorical(["b", "b"], categories=["a", "b", "c"])
-    except ValueError as e:
-        print("ValueError:", str(e))
+    except TypeError as e:
+        print("TypeError:", str(e))
 
 Assigning a ``Categorical`` to parts of a column of other types will use the values:
 

doc/source/whatsnew/v1.4.0.rst

@@ -174,7 +174,11 @@ Bug fixes
 
 Categorical
 ^^^^^^^^^^^
--
+- Bug in setting dtype-incompatible values into a :class:`Categorical` (or ``Series`` or ``DataFrame`` backed by ``Categorical``) raising ``ValueError`` instead of ``TypeError`` (:issue:`41919`)
+- Bug in :meth:`Categorical.searchsorted` when passing a dtype-incompatible value raising ``KeyError`` instead of ``TypeError`` (:issue:`41919`)
+- Bug in :meth:`Series.where` with ``CategoricalDtype`` when passing a dtype-incompatible value raising ``ValueError`` instead of ``TypeError`` (:issue:`41919`)
+- Bug in :meth:`Categorical.fillna` when passing a dtype-incompatible value raising ``ValueError`` instead of ``TypeError`` (:issue:`41919`)
+- Bug in :meth:`Categorical.fillna` with a tuple-like category raising ``ValueError`` instead of ``TypeError`` when filling with a non-category tuple (:issue:`41919`)
 -
 
 Datetimelike

pandas/core/arrays/categorical.py

@@ -1394,17 +1394,14 @@ def map(self, mapper):
     # -------------------------------------------------------------
     # Validators; ideally these can be de-duplicated
 
-    def _validate_searchsorted_value(self, value):
-        # searchsorted is very performance sensitive. By converting codes
-        # to same dtype as self.codes, we get much faster performance.
-        if is_scalar(value):
-            codes = self._unbox_scalar(value)
+    def _validate_setitem_value(self, value):
+        if not is_hashable(value):
+            # wrap scalars and hashable-listlikes in list
+            return self._validate_listlike(value)
         else:
-            locs = [self.categories.get_loc(x) for x in value]
-            # error: Incompatible types in assignment (expression has type
-            # "ndarray", variable has type "int")
-            codes = np.array(locs, dtype=self.codes.dtype)  # type: ignore[assignment]
-        return codes
+            return self._validate_scalar(value)
+
+    _validate_searchsorted_value = _validate_setitem_value
 
     def _validate_scalar(self, fill_value):
         """
@@ -1430,8 +1427,8 @@ def _validate_scalar(self, fill_value):
             fill_value = self._unbox_scalar(fill_value)
         else:
             raise TypeError(
-                f"'fill_value={fill_value}' is not present "
-                "in this Categorical's categories"
+                "Cannot setitem on a Categorical with a new "
+                f"category ({fill_value}), set the categories first"
             )
         return fill_value
 
@@ -2016,37 +2013,35 @@ def __getitem__(self, key):
             deprecate_ndim_indexing(result)
         return result
 
-    def _validate_setitem_value(self, value):
+    def _validate_listlike(self, value):
+        # NB: here we assume scalar-like tuples have already been excluded
         value = extract_array(value, extract_numpy=True)
 
         # require identical categories set
         if isinstance(value, Categorical):
             if not is_dtype_equal(self.dtype, value.dtype):
-                raise ValueError(
+                raise TypeError(
                     "Cannot set a Categorical with another, "
                     "without identical categories"
                 )
             # is_dtype_equal implies categories_match_up_to_permutation
             value = self._encode_with_my_categories(value)
             return value._codes
 
-        # wrap scalars and hashable-listlikes in list
-        rvalue = value if not is_hashable(value) else [value]
-
         from pandas import Index
 
         # tupleize_cols=False for e.g. test_fillna_iterable_category GH#41914
-        to_add = Index(rvalue, tupleize_cols=False).difference(self.categories)
+        to_add = Index(value, tupleize_cols=False).difference(self.categories)
 
         # no assignments of values not in categories, but it's always ok to set
         # something to np.nan
         if len(to_add) and not isna(to_add).all():
-            raise ValueError(
+            raise TypeError(
                 "Cannot setitem on a Categorical with a new "
                 "category, set the categories first"
             )
 
-        codes = self.categories.get_indexer(rvalue)
+        codes = self.categories.get_indexer(value)
         return codes.astype(self._ndarray.dtype, copy=False)
 
     def _reverse_indexer(self) -> dict[Hashable, npt.NDArray[np.intp]]:

pandas/core/internals/blocks.py

@@ -1628,6 +1628,10 @@ def where(self, other, cond, errors="raise") -> list[Block]:
             # NotImplementedError for class not implementing `__setitem__`
             # TypeError for SparseArray, which implements just to raise
             # a TypeError
+            if isinstance(result, Categorical):
+                # TODO: don't special-case
+                raise
+
             result = type(self.values)._from_sequence(
                 np.where(cond, self.values, other), dtype=dtype
             )

pandas/tests/arrays/categorical/test_analytics.py

@@ -186,15 +186,19 @@ def test_searchsorted(self, ordered):
         tm.assert_numpy_array_equal(res_ser, exp)
 
         # Searching for a single value that is not from the Categorical
-        with pytest.raises(KeyError, match="cucumber"):
+        with pytest.raises(TypeError, match="cucumber"):
             cat.searchsorted("cucumber")
-        with pytest.raises(KeyError, match="cucumber"):
+        with pytest.raises(TypeError, match="cucumber"):
             ser.searchsorted("cucumber")
 
         # Searching for multiple values one of each is not from the Categorical
-        with pytest.raises(KeyError, match="cucumber"):
+        msg = (
+            "Cannot setitem on a Categorical with a new category, "
+            "set the categories first"
+        )
+        with pytest.raises(TypeError, match=msg):
             cat.searchsorted(["bread", "cucumber"])
-        with pytest.raises(KeyError, match="cucumber"):
+        with pytest.raises(TypeError, match=msg):
             ser.searchsorted(["bread", "cucumber"])
 
     def test_unique(self, ordered):

pandas/tests/arrays/categorical/test_indexing.py

@@ -73,7 +73,7 @@ def test_setitem_different_unordered_raises(self, other):
         target = Categorical(["a", "b"], categories=["a", "b"])
         mask = np.array([True, False])
         msg = "Cannot set a Categorical with another, without identical categories"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             target[mask] = other[mask]
 
     @pytest.mark.parametrize(
@@ -89,7 +89,7 @@ def test_setitem_same_ordered_raises(self, other):
         target = Categorical(["a", "b"], categories=["a", "b"], ordered=True)
         mask = np.array([True, False])
         msg = "Cannot set a Categorical with another, without identical categories"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             target[mask] = other[mask]
 
     def test_setitem_tuple(self):
@@ -260,7 +260,7 @@ def test_where_other_categorical(self):
     def test_where_new_category_raises(self):
         ser = Series(Categorical(["a", "b", "c"]))
         msg = "Cannot setitem on a Categorical with a new category"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             ser.where([True, False, True], "d")
 
     def test_where_ordered_differs_rasies(self):
@@ -270,7 +270,7 @@ def test_where_ordered_differs_rasies(self):
         other = Categorical(
             ["b", "c", "a"], categories=["a", "c", "b", "d"], ordered=True
         )
-        with pytest.raises(ValueError, match="without identical categories"):
+        with pytest.raises(TypeError, match="without identical categories"):
             ser.where([True, False, True], other)
 
 

pandas/tests/arrays/categorical/test_missing.py

@@ -84,7 +84,12 @@ def test_fillna_raises(self, fillna_kwargs, msg):
         # https://github.com/pandas-dev/pandas/issues/13628
         cat = Categorical([1, 2, 3, None, None])
 
-        with pytest.raises(ValueError, match=msg):
+        if len(fillna_kwargs) == 1 and "value" in fillna_kwargs:
+            err = TypeError
+        else:
+            err = ValueError
+
+        with pytest.raises(err, match=msg):
             cat.fillna(**fillna_kwargs)
 
     @pytest.mark.parametrize("named", [True, False])
@@ -104,7 +109,7 @@ def test_fillna_iterable_category(self, named):
         #  not NotImplementedError GH#41914
         cat = Categorical(np.array([Point(1, 0), Point(0, 1), None], dtype=object))
         msg = "Cannot setitem on a Categorical with a new category"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             cat.fillna(Point(0, 0))
 
     def test_fillna_array(self):

pandas/tests/arrays/categorical/test_take.py

@@ -81,7 +81,7 @@ def test_take_fill_value(self):
     def test_take_fill_value_new_raises(self):
         # https://github.com/pandas-dev/pandas/issues/23296
         cat = Categorical(["a", "b", "c"])
-        xpr = r"'fill_value=d' is not present in this Categorical's categories"
+        xpr = r"Cannot setitem on a Categorical with a new category \(d\)"
         with pytest.raises(TypeError, match=xpr):
             cat.take([0, 1, -1], fill_value="d", allow_fill=True)
 

pandas/tests/frame/indexing/test_indexing.py

@@ -1283,7 +1283,7 @@ def test_object_casting_indexing_wraps_datetimelike(using_array_manager):
     assert isinstance(val, pd.Timedelta)
 
 
-msg1 = "Cannot setitem on a Categorical with a new category, set the categories first"
+msg1 = r"Cannot setitem on a Categorical with a new category( \(.*\))?, set the"
 msg2 = "Cannot set a Categorical with another, without identical categories"
 
 
@@ -1348,7 +1348,7 @@ def test_loc_iloc_setitem_list_of_lists(self, orig, exp_multi_row, indexer):
         tm.assert_frame_equal(df, exp_multi_row)
 
         df = orig.copy()
-        with pytest.raises(ValueError, match=msg1):
+        with pytest.raises(TypeError, match=msg1):
             indexer(df)[key, :] = [["c", 2], ["c", 2]]
 
     @pytest.mark.parametrize("indexer", [tm.loc, tm.iloc, tm.at, tm.iat])
@@ -1367,7 +1367,7 @@ def test_loc_iloc_at_iat_setitem_single_value_in_categories(
         tm.assert_frame_equal(df, exp_single_cats_value)
 
         # "c" is not among the categories for df["cat"]
-        with pytest.raises(ValueError, match=msg1):
+        with pytest.raises(TypeError, match=msg1):
             indexer(df)[key] = "c"
 
     @pytest.mark.parametrize("indexer", [tm.loc, tm.iloc])
@@ -1401,7 +1401,7 @@ def test_loc_iloc_setitem_full_row_non_categorical_rhs(
         tm.assert_frame_equal(df, exp_single_row)
 
         # "c" is not among the categories for df["cat"]
-        with pytest.raises(ValueError, match=msg1):
+        with pytest.raises(TypeError, match=msg1):
             indexer(df)[key, :] = ["c", 2]
 
     @pytest.mark.parametrize("indexer", [tm.loc, tm.iloc])
@@ -1423,14 +1423,14 @@ def test_loc_iloc_setitem_partial_col_categorical_rhs(
 
         # categories do not match df["cat"]'s, but "b" is among them
         semi_compat = Categorical(list("bb"), categories=list("abc"))
-        with pytest.raises(ValueError, match=msg2):
+        with pytest.raises(TypeError, match=msg2):
             # different categories but holdable values
             #  -> not sure if this should fail or pass
             indexer(df)[key] = semi_compat
 
         # categories do not match df["cat"]'s, and "c" is not among them
         incompat = Categorical(list("cc"), categories=list("abc"))
-        with pytest.raises(ValueError, match=msg2):
+        with pytest.raises(TypeError, match=msg2):
             # different values
             indexer(df)[key] = incompat
 
@@ -1450,5 +1450,5 @@ def test_loc_iloc_setitem_non_categorical_rhs(
         tm.assert_frame_equal(df, exp_parts_cats_col)
 
         # "c" not part of the categories
-        with pytest.raises(ValueError, match=msg1):
+        with pytest.raises(TypeError, match=msg1):
             indexer(df)[key] = ["c", "c"]

pandas/tests/frame/methods/test_fillna.py

@@ -173,7 +173,7 @@ def test_na_actions_categorical(self):
         tm.assert_frame_equal(res, df_exp_fill)
 
         msg = "Cannot setitem on a Categorical with a new category"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             df.fillna(value={"cats": 4, "vals": "c"})
 
         res = df.fillna(method="pad")

pandas/tests/frame/test_stack_unstack.py

@@ -255,7 +255,7 @@ def test_unstack_fill_frame_categorical(self):
         tm.assert_frame_equal(result, expected)
 
         # Fill with non-category results in a ValueError
-        msg = r"'fill_value=d' is not present in"
+        msg = r"Cannot setitem on a Categorical with a new category \(d\)"
         with pytest.raises(TypeError, match=msg):
             data.unstack(fill_value="d")
 

pandas/tests/indexes/categorical/test_fillna.py

@@ -15,9 +15,9 @@ def test_fillna_categorical(self):
 
         cat = idx._data
 
-        # fill by value not in categories raises ValueError on EA, casts on CI
+        # fill by value not in categories raises TypeError on EA, casts on CI
         msg = "Cannot setitem on a Categorical with a new category"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             cat.fillna(2.0)
 
         result = idx.fillna(2.0)
@@ -48,5 +48,5 @@ def test_fillna_validates_with_no_nas(self):
         tm.assert_index_equal(res, ci)
 
         # Same check directly on the Categorical
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             cat.fillna(False)

pandas/tests/indexes/categorical/test_indexing.py

@@ -322,7 +322,7 @@ def test_where_non_categories(self):
         tm.assert_index_equal(result, expected)
 
         msg = "Cannot setitem on a Categorical with a new category"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             # Test the Categorical method directly
             ci._data.where(mask, 2)
 

pandas/tests/indexes/categorical/test_reindex.py

@@ -62,7 +62,7 @@ def test_reindex_empty_index(self):
     def test_reindex_missing_category(self):
         # GH: 18185
         ser = Series([1, 2, 3, 1], dtype="category")
-        msg = "'fill_value=-1' is not present in this Categorical's categories"
+        msg = r"Cannot setitem on a Categorical with a new category \(-1\)"
         with pytest.raises(TypeError, match=msg):
             ser.reindex([1, 2, 3, 4, 5], fill_value=-1)
 

pandas/tests/series/methods/test_fillna.py

@@ -677,14 +677,14 @@ def test_fillna_categorical_raises(self):
         cat = ser._values
 
         msg = "Cannot setitem on a Categorical with a new category"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             ser.fillna("d")
 
         msg2 = "Length of 'value' does not match."
         with pytest.raises(ValueError, match=msg2):
             cat.fillna(Series("d"))
 
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(TypeError, match=msg):
             ser.fillna({1: "d", 3: "a"})
 
         msg = '"value" parameter must be a scalar or dict, but you passed a "list"'

pandas/tests/series/methods/test_shift.py

@@ -169,7 +169,7 @@ def test_shift_categorical_fill_value(self):
         tm.assert_equal(res, expected)
 
         # check for incorrect fill_value
-        msg = "'fill_value=f' is not present in this Categorical's categories"
+        msg = r"Cannot setitem on a Categorical with a new category \(f\)"
         with pytest.raises(TypeError, match=msg):
             ts.shift(1, fill_value="f")