CLN: remove _index_data (#43229)

Author: jbrockmendel

pandas/_libs/reduction.pyx

@@ -64,9 +64,6 @@ cdef class _BaseGrouper:
 
     cdef inline _update_cached_objs(self, object cached_series, object cached_index,
                                     Slider islider, Slider vslider):
-        # See the comment in indexes/base.py about _index_data.
-        # We need this for EA-backed indexes that have a reference
-        # to a 1-d ndarray like datetime / timedelta / period.
         cached_index._engine.clear_mapping()
         cached_index._cache.clear()  # e.g. inferred_freq must go
         cached_series._mgr.set_values(vslider.buf)

pandas/core/indexes/base.py

@@ -639,11 +639,6 @@ def _simple_new(cls: type[_IndexT], values, name: Hashable = None) -> _IndexT:
 
         result = object.__new__(cls)
         result._data = values
-        # _index_data is a (temporary?) fix to ensure that the direct data
-        # manipulation we do in `_libs/reduction.pyx` continues to work.
-        # We need access to the actual ndarray, since we're messing with
-        # data buffers and strides.
-        result._index_data = values
         result._name = name
         result._cache = {}
         result._reset_identity()

pandas/core/indexes/extension.py

@@ -448,19 +448,6 @@ class NDArrayBackedExtensionIndex(ExtensionIndex):
 
     _data: NDArrayBackedExtensionArray
 
-    @classmethod
-    def _simple_new(
-        cls,
-        values: NDArrayBackedExtensionArray,
-        name: Hashable = None,
-    ):
-        result = super()._simple_new(values, name)
-
-        # For groupby perf. See note in indexes/base about _index_data
-        result._index_data = values._ndarray
-
-        return result
-
     def _get_engine_target(self) -> np.ndarray:
         return self._data._ndarray
 

pandas/tests/arithmetic/test_object.py

@@ -341,7 +341,6 @@ class MyIndex(pd.Index):
     def _simple_new(cls, values, name=None, dtype=None):
         result = object.__new__(cls)
         result._data = values
-        result._index_data = values
         result._name = name
         result._calls = 0
         result._reset_identity()
@@ -350,7 +349,7 @@ def _simple_new(cls, values, name=None, dtype=None):
 
     def __add__(self, other):
         self._calls += 1
-        return self._simple_new(self._index_data)
+        return self._simple_new(self._data)
 
     def __radd__(self, other):
         return self.__add__(other)