REF: simplify CategoricalIndex.__new__

pandas/core/arrays/categorical.py

@@ -298,7 +298,13 @@ class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMi
     _can_hold_na = True
 
     def __init__(
-        self, values, categories=None, ordered=None, dtype=None, fastpath=False
+        self,
+        values,
+        categories=None,
+        ordered=None,
+        dtype=None,
+        fastpath=False,
+        copy: bool = True,
     ):
 
         dtype = CategoricalDtype._from_values_or_dtype(
@@ -359,9 +365,9 @@ def __init__(
             dtype = CategoricalDtype(categories, dtype.ordered)
 
         elif is_categorical_dtype(values.dtype):
-            old_codes = extract_array(values).codes
+            old_codes = extract_array(values)._codes
             codes = recode_for_categories(
-                old_codes, values.dtype.categories, dtype.categories
+                old_codes, values.dtype.categories, dtype.categories, copy=copy
             )
 
         else:
@@ -389,7 +395,7 @@ def _constructor(self) -> Type["Categorical"]:
 
     @classmethod
     def _from_sequence(cls, scalars, *, dtype=None, copy=False):
-        return Categorical(scalars, dtype=dtype)
+        return Categorical(scalars, dtype=dtype, copy=copy)
 
     def astype(self, dtype: Dtype, copy: bool = True) -> ArrayLike:
         """

pandas/core/indexes/category.py

@@ -15,7 +15,6 @@
     is_categorical_dtype,
     is_scalar,
 )
-from pandas.core.dtypes.dtypes import CategoricalDtype
 from pandas.core.dtypes.missing import is_valid_nat_for_dtype, isna, notna
 
 from pandas.core import accessor
@@ -184,28 +183,18 @@ def __new__(
         cls, data=None, categories=None, ordered=None, dtype=None, copy=False, name=None
     ):
 
-        dtype = CategoricalDtype._from_values_or_dtype(data, categories, ordered, dtype)
-
         name = maybe_extract_name(name, data, cls)
 
-        if not is_categorical_dtype(data):
+        if is_scalar(data):
             # don't allow scalars
             # if data is None, then categories must be provided
-            if is_scalar(data):
-                if data is not None or categories is None:
-                    raise cls._scalar_data_error(data)
-                data = []
-
-        assert isinstance(dtype, CategoricalDtype), dtype
-        data = extract_array(data, extract_numpy=True)
+            if data is not None or categories is None:
+                raise cls._scalar_data_error(data)
+            data = []
 
-        if not isinstance(data, Categorical):
-            data = Categorical(data, dtype=dtype)
-        elif isinstance(dtype, CategoricalDtype) and dtype != data.dtype:
-            # we want to silently ignore dtype='category'
-            data = data._set_dtype(dtype)
-
-        data = data.copy() if copy else data
+        data = Categorical(
+            data, categories=categories, ordered=ordered, dtype=dtype, copy=copy
+        )
 
         return cls._simple_new(data, name=name)
 

pandas/tests/arrays/categorical/test_constructors.py

@@ -699,3 +699,14 @@ def test_categorical_extension_array_nullable(self, nulls_fixture):
         result = Categorical(arr)
         expected = Categorical(Series([pd.NA, pd.NA], dtype="object"))
         tm.assert_categorical_equal(result, expected)
+
+    def test_from_sequence_copy(self):
+        cat = Categorical(np.arange(5).repeat(2))
+        result = Categorical._from_sequence(cat, dtype=None, copy=False)
+
+        # more generally, we'd be OK with a view
+        assert result._codes is cat._codes
+
+        result = Categorical._from_sequence(cat, dtype=None, copy=True)
+
+        assert not np.shares_memory(result._codes, cat._codes)

pandas/tests/indexes/categorical/test_category.py

@@ -304,7 +304,7 @@ def test_ensure_copied_data(self, index):
         assert _base(index.values) is not _base(result.values)
 
         result = CategoricalIndex(index.values, copy=False)
-        assert _base(index.values) is _base(result.values)
+        assert result._data._codes is index._data._codes
 
     def test_frame_repr(self):
         df = pd.DataFrame({"A": [1, 2, 3]}, index=CategoricalIndex(["a", "b", "c"]))