BUG: disallow scalar in Categorical constructor (pandas-dev#38472)

Author: jbrockmendel

doc/source/whatsnew/v1.3.0.rst

@@ -144,6 +144,7 @@ Other API changes
 
 Deprecations
 ~~~~~~~~~~~~
+- Deprecating allowing scalars passed to the :class:`Categorical` constructor (:issue:`38433`)
 - Deprecated allowing subclass-specific keyword arguments in the :class:`Index` constructor, use the specific subclass directly instead (:issue:`14093`,:issue:`21311`,:issue:`22315`,:issue:`26974`)
 -
 -

pandas/core/arrays/categorical.py

@@ -320,6 +320,16 @@ def __init__(
             self._dtype = self._dtype.update_dtype(dtype)
             return
 
+        if not is_list_like(values):
+            # GH#38433
+            warn(
+                "Allowing scalars in the Categorical constructor is deprecated "
+                "and will raise in a future version.  Use `[value]` instead",
+                FutureWarning,
+                stacklevel=2,
+            )
+            values = [values]
+
         # null_mask indicates missing values we want to exclude from inference.
         # This means: only missing values in list-likes (not arrays/ndframes).
         null_mask = np.array(False)

pandas/tests/arrays/categorical/test_constructors.py

@@ -26,6 +26,11 @@
 
 
 class TestCategoricalConstructors:
+    def test_categorical_scalar_deprecated(self):
+        # GH#38433
+        with tm.assert_produces_warning(FutureWarning):
+            Categorical("A", categories=["A", "B"])
+
     def test_validate_ordered(self):
         # see gh-14058
         exp_msg = "'ordered' must either be 'True' or 'False'"
@@ -202,13 +207,13 @@ def test_constructor(self):
         assert len(cat.codes) == 1
         assert cat.codes[0] == 0
 
-        # Scalars should be converted to lists
-        cat = Categorical(1)
+        with tm.assert_produces_warning(FutureWarning):
+            # GH#38433
+            cat = Categorical(1)
         assert len(cat.categories) == 1
         assert cat.categories[0] == 1
         assert len(cat.codes) == 1
         assert cat.codes[0] == 0
-
         # two arrays
         #  - when the first is an integer dtype and the second is not
         #  - when the resulting codes are all -1/NaN

pandas/tests/extension/test_categorical.py

@@ -223,7 +223,7 @@ def test_cast_category_to_extension_dtype(self, expected):
     )
     def test_consistent_casting(self, dtype, expected):
         # GH 28448
-        result = Categorical("2015-01-01").astype(dtype)
+        result = Categorical(["2015-01-01"]).astype(dtype)
         assert result == expected
 
 

pandas/tests/series/methods/test_replace.py

@@ -290,7 +290,7 @@ def test_replace_mixed_types_with_string(self):
     @pytest.mark.parametrize(
         "categorical, numeric",
         [
-            (pd.Categorical("A", categories=["A", "B"]), [1]),
+            (pd.Categorical(["A"], categories=["A", "B"]), [1]),
             (pd.Categorical(("A",), categories=["A", "B"]), [1]),
             (pd.Categorical(("A", "B"), categories=["A", "B"]), [1, 2]),
         ],

pandas/tests/test_algos.py

@@ -908,17 +908,17 @@ def test_categorical_from_codes(self):
         # GH 16639
         vals = np.array([0, 1, 2, 0])
         cats = ["a", "b", "c"]
-        Sd = Series(Categorical(1).from_codes(vals, cats))
-        St = Series(Categorical(1).from_codes(np.array([0, 1]), cats))
+        Sd = Series(Categorical([1]).from_codes(vals, cats))
+        St = Series(Categorical([1]).from_codes(np.array([0, 1]), cats))
         expected = np.array([True, True, False, True])
         result = algos.isin(Sd, St)
         tm.assert_numpy_array_equal(expected, result)
 
     def test_categorical_isin(self):
         vals = np.array([0, 1, 2, 0])
         cats = ["a", "b", "c"]
-        cat = Categorical(1).from_codes(vals, cats)
-        other = Categorical(1).from_codes(np.array([0, 1]), cats)
+        cat = Categorical([1]).from_codes(vals, cats)
+        other = Categorical([1]).from_codes(np.array([0, 1]), cats)
 
         expected = np.array([True, True, False, True])
         result = algos.isin(cat, other)