BUG: RangeIndex.astype('category') (#41263)

Author: topper-123

doc/source/whatsnew/v1.3.0.rst

@@ -780,6 +780,7 @@ Indexing
 - Bug in :meth:`DatetimeIndex.insert` when inserting ``np.datetime64("NaT")`` into a timezone-aware index incorrectly treating the timezone-naive value as timezone-aware (:issue:`39769`)
 - Bug in incorrectly raising in :meth:`Index.insert`, when setting a new column that cannot be held in the existing ``frame.columns``, or in :meth:`Series.reset_index` or :meth:`DataFrame.reset_index` instead of casting to a compatible dtype (:issue:`39068`)
 - Bug in :meth:`RangeIndex.append` where a single object of length 1 was concatenated incorrectly (:issue:`39401`)
+- Bug in :meth:`RangeIndex.astype` where when converting to :class:`CategoricalIndex`, the categories became a :class:`Int64Index` instead of a :class:`RangeIndex` (:issue:`41263`)
 - Bug in setting ``numpy.timedelta64`` values into an object-dtype :class:`Series` using a boolean indexer (:issue:`39488`)
 - Bug in setting numeric values into a into a boolean-dtypes :class:`Series` using ``at`` or ``iat`` failing to cast to object-dtype (:issue:`39582`)
 - Bug in :meth:`DataFrame.__setitem__` and :meth:`DataFrame.iloc.__setitem__` raising ``ValueError`` when trying to index with a row-slice and setting a list as values (:issue:`40440`)
@@ -945,6 +946,7 @@ Other
 - Bug in :meth:`Series.where` with numeric dtype and ``other = None`` not casting to ``nan`` (:issue:`39761`)
 - :meth:`Index.where` behavior now mirrors :meth:`Index.putmask` behavior, i.e. ``index.where(mask, other)`` matches ``index.putmask(~mask, other)`` (:issue:`39412`)
 - Bug in :func:`pandas.testing.assert_series_equal`, :func:`pandas.testing.assert_frame_equal`, :func:`pandas.testing.assert_index_equal` and :func:`pandas.testing.assert_extension_array_equal` incorrectly raising when an attribute has an unrecognized NA type (:issue:`39461`)
+- Bug in :func:`pandas.testing.assert_index_equal` with ``exact=True`` not raising when comparing :class:`CategoricalIndex` instances with ``Int64Index`` and ``RangeIndex`` categories (:issue:`41263`)
 - Bug in :meth:`DataFrame.equals`, :meth:`Series.equals`, :meth:`Index.equals` with object-dtype containing ``np.datetime64("NaT")`` or ``np.timedelta64("NaT")`` (:issue:`39650`)
 - Bug in :func:`pandas.util.show_versions` where console JSON output was not proper JSON (:issue:`39701`)
 - Bug in :meth:`DataFrame.convert_dtypes` incorrectly raised ValueError when called on an empty DataFrame (:issue:`40393`)

pandas/_testing/asserters.py

@@ -309,18 +309,22 @@ def assert_index_equal(
     __tracebackhide__ = True
 
     def _check_types(left, right, obj="Index"):
-        if exact:
-            assert_class_equal(left, right, exact=exact, obj=obj)
+        if not exact:
+            return
 
-            # Skip exact dtype checking when `check_categorical` is False
-            if check_categorical:
-                assert_attr_equal("dtype", left, right, obj=obj)
+        assert_class_equal(left, right, exact=exact, obj=obj)
 
-            # allow string-like to have different inferred_types
-            if left.inferred_type in ("string"):
-                assert right.inferred_type in ("string")
-            else:
-                assert_attr_equal("inferred_type", left, right, obj=obj)
+        # Skip exact dtype checking when `check_categorical` is False
+        if check_categorical:
+            assert_attr_equal("dtype", left, right, obj=obj)
+            if is_categorical_dtype(left.dtype) and is_categorical_dtype(right.dtype):
+                assert_index_equal(left.categories, right.categories, exact=exact)
+
+        # allow string-like to have different inferred_types
+        if left.inferred_type in ("string"):
+            assert right.inferred_type in ("string")
+        else:
+            assert_attr_equal("inferred_type", left, right, obj=obj)
 
     def _get_ilevel_values(index, level):
         # accept level number only

pandas/core/indexes/base.py

@@ -907,9 +907,7 @@ def astype(self, dtype, copy=True):
         elif is_categorical_dtype(dtype):
             from pandas.core.indexes.category import CategoricalIndex
 
-            return CategoricalIndex(
-                self._values, name=self.name, dtype=dtype, copy=copy
-            )
+            return CategoricalIndex(self, name=self.name, dtype=dtype, copy=copy)
 
         elif is_extension_array_dtype(dtype):
             return Index(np.asarray(self), name=self.name, dtype=dtype, copy=copy)

pandas/tests/indexes/categorical/test_constructors.py

@@ -108,8 +108,8 @@ def test_construction_with_dtype(self):
         tm.assert_index_equal(result, ci, exact=True)
 
         # make sure indexes are handled
-        expected = CategoricalIndex([0, 1, 2], categories=[0, 1, 2], ordered=True)
         idx = Index(range(3))
+        expected = CategoricalIndex([0, 1, 2], categories=idx, ordered=True)
         result = CategoricalIndex(idx, categories=idx, ordered=True)
         tm.assert_index_equal(result, expected, exact=True)
 

pandas/tests/indexes/common.py

@@ -672,20 +672,20 @@ def test_astype_category(self, copy, name, ordered, simple_index):
         # standard categories
         dtype = CategoricalDtype(ordered=ordered)
         result = idx.astype(dtype, copy=copy)
-        expected = CategoricalIndex(idx.values, name=name, ordered=ordered)
-        tm.assert_index_equal(result, expected)
+        expected = CategoricalIndex(idx, name=name, ordered=ordered)
+        tm.assert_index_equal(result, expected, exact=True)
 
         # non-standard categories
         dtype = CategoricalDtype(idx.unique().tolist()[:-1], ordered)
         result = idx.astype(dtype, copy=copy)
-        expected = CategoricalIndex(idx.values, name=name, dtype=dtype)
-        tm.assert_index_equal(result, expected)
+        expected = CategoricalIndex(idx, name=name, dtype=dtype)
+        tm.assert_index_equal(result, expected, exact=True)
 
         if ordered is False:
             # dtype='category' defaults to ordered=False, so only test once
             result = idx.astype("category", copy=copy)
-            expected = CategoricalIndex(idx.values, name=name)
-            tm.assert_index_equal(result, expected)
+            expected = CategoricalIndex(idx, name=name)
+            tm.assert_index_equal(result, expected, exact=True)
 
     def test_is_unique(self, simple_index):
         # initialize a unique index

pandas/tests/util/test_assert_index_equal.py

@@ -3,9 +3,11 @@
 
 from pandas import (
     Categorical,
+    CategoricalIndex,
     Index,
     MultiIndex,
     NaT,
+    RangeIndex,
 )
 import pandas._testing as tm
 
@@ -199,6 +201,28 @@ def test_index_equal_category_mismatch(check_categorical):
         tm.assert_index_equal(idx1, idx2, check_categorical=check_categorical)
 
 
+@pytest.mark.parametrize("exact", [False, True])
+def test_index_equal_range_categories(check_categorical, exact):
+    # GH41263
+    msg = """\
+Index are different
+
+Index classes are different
+\\[left\\]:  RangeIndex\\(start=0, stop=10, step=1\\)
+\\[right\\]: Int64Index\\(\\[0, 1, 2, 3, 4, 5, 6, 7, 8, 9\\], dtype='int64'\\)"""
+
+    rcat = CategoricalIndex(RangeIndex(10))
+    icat = CategoricalIndex(list(range(10)))
+
+    if check_categorical and exact:
+        with pytest.raises(AssertionError, match=msg):
+            tm.assert_index_equal(rcat, icat, check_categorical=True, exact=True)
+    else:
+        tm.assert_index_equal(
+            rcat, icat, check_categorical=check_categorical, exact=exact
+        )
+
+
 def test_assert_index_equal_mixed_dtype():
     # GH#39168
     idx = Index(["foo", "bar", 42])