Refactor Index hierarchy

python/cudf/cudf/_lib/groupby.pyx

@@ -99,10 +99,12 @@ cdef class GroupBy:
         c_grouped_values = move(c_groups.values)
         c_group_offsets = c_groups.offsets
 
-        grouped_keys = cudf.Index._from_data(*data_from_unique_ptr(
-            move(c_grouped_keys),
-            column_names=range(c_grouped_keys.get()[0].num_columns())
-        ))
+        grouped_keys = cudf.core.index._index_from_data(
+            *data_from_unique_ptr(
+                move(c_grouped_keys),
+                column_names=range(c_grouped_keys.get()[0].num_columns())
+            )
+        )
         grouped_values = data_from_unique_ptr(
             move(c_grouped_values),
             index_names=values._index_names,
@@ -186,7 +188,8 @@ cdef class GroupBy:
                     Column.from_unique_ptr(move(c_result.second[i].results[j]))
                 )
 
-        return result_data, cudf.Index._from_data(grouped_keys)
+        return result_data, cudf.core.index._index_from_data(
+            grouped_keys)
 
     def scan_internal(self, Table values, aggregations):
         from cudf.core.column_accessor import ColumnAccessor
@@ -264,7 +267,8 @@ cdef class GroupBy:
                     Column.from_unique_ptr(move(c_result.second[i].results[j]))
                 )
 
-        return result_data, cudf.Index._from_data(grouped_keys)
+        return result_data, cudf.core.index._index_from_data(
+            grouped_keys)
 
     def aggregate(self, Table values, aggregations):
         """
@@ -311,10 +315,12 @@ cdef class GroupBy:
                 self.c_obj.get()[0].shift(view, offsets, c_fill_values)
             )
 
-        grouped_keys = cudf.Index._from_data(*data_from_unique_ptr(
-            move(c_result.first),
-            column_names=self.keys._column_names
-        ))
+        grouped_keys = cudf.core.index._index_from_data(
+            *data_from_unique_ptr(
+                move(c_result.first),
+                column_names=self.keys._column_names
+            )
+        )
 
         shifted, _ = data_from_unique_ptr(
             move(c_result.second), column_names=values._column_names

python/cudf/cudf/_lib/table.pyx

@@ -34,9 +34,17 @@ cdef class Table:
         """
         if data is None:
             data = {}
-        self._data = cudf.core.column_accessor.ColumnAccessor(data)
+        self._column_accessor = cudf.core.column_accessor.ColumnAccessor(data)
         self._index = index
 
+    @property
+    def _data(self) -> cudf.core.column_accessor.ColumnAccessor:
+        return self._column_accessor
+
+    @_data.setter
+    def _data(self, value):
+        self._column_accessor = value
+
     @property
     def _num_columns(self):
         return len(self._data)

python/cudf/cudf/_lib/utils.pyx

@@ -251,7 +251,7 @@ cdef data_from_unique_ptr(
         # Frame factories we may want to look for a less dissonant approach
         # that does not impose performance penalties. The same applies to
         # data_from_table_view below.
-        cudf.Index._from_data(
+        cudf.core.index._index_from_data(
             {
                 name: columns[i]
                 for i, name in enumerate(index_names)
@@ -301,7 +301,8 @@ cdef data_from_table_view(
                 )
             )
             column_idx += 1
-        index = cudf.Index._from_data(dict(zip(index_names, index_columns)))
+        index = cudf.core.index._index_from_data(
+            dict(zip(index_names, index_columns)))
 
     # Construct the data dict
     cdef size_type source_column_idx = 0

python/cudf/cudf/_typing.py

@@ -29,3 +29,6 @@
 
 DataFrameOrSeries = Union["cudf.Series", "cudf.DataFrame"]
 SeriesOrIndex = Union["cudf.Series", "cudf.core.index.BaseIndex"]
+SeriesOrSingleColumnIndex = Union[
+    "cudf.Series", "cudf.core.index.GenericIndex"
+]

python/cudf/cudf/api/types.py

@@ -194,7 +194,7 @@ def wrapped_func(obj):
 
 
 def _union_categoricals(
-    to_union: List[Union[cudf.Series, cudf.Index]],
+    to_union: List[Union[cudf.Series, cudf.CategoricalIndex]],
     sort_categories: bool = False,
     ignore_order: bool = False,
 ):