Index class deprecation enforcements

docs/cudf/source/developer_guide/library_design.md

@@ -22,7 +22,7 @@ Finally we tie these pieces together to provide a more holistic view of the proj
 % class IndexedFrame
 % class SingleColumnFrame
 % class BaseIndex
-% class GenericIndex
+% class Index
 % class MultiIndex
 % class RangeIndex
 % class DataFrame
@@ -42,8 +42,8 @@ Finally we tie these pieces together to provide a more holistic view of the proj
 % BaseIndex <|-- MultiIndex
 % Frame <|-- MultiIndex
 %
-% BaseIndex <|-- GenericIndex
-% SingleColumnFrame <|-- GenericIndex
+% BaseIndex <|-- Index
+% SingleColumnFrame <|-- Index
 %
 % @enduml
 
@@ -89,12 +89,12 @@ While we've highlighted some exceptional cases of Indexes before, let's start wi
 In practice, `BaseIndex` does have concrete implementations of a small set of methods.
 However, currently many of these implementations are not applicable to all subclasses and will be eventually be removed.
 
-Almost all indexes are subclasses of `GenericIndex`, a single-columned index with the class hierarchy:
+Almost all indexes are subclasses of `Index`, a single-columned index with the class hierarchy:
 ```python
-class GenericIndex(SingleColumnFrame, BaseIndex)
+class Index(SingleColumnFrame, BaseIndex)
 ```
 Integer, float, or string indexes are all composed of a single column of data.
-Most `GenericIndex` methods are inherited from `Frame`, saving us the trouble of rewriting them.
+Most `Index` methods are inherited from `Frame`, saving us the trouble of rewriting them.
 
 We now consider the three main exceptions to this model:
 

python/cudf/cudf/__init__.py

@@ -35,22 +35,10 @@
     BaseIndex,
     CategoricalIndex,
     DatetimeIndex,
-    Float32Index,
-    Float64Index,
-    GenericIndex,
     Index,
-    Int8Index,
-    Int16Index,
-    Int32Index,
-    Int64Index,
     IntervalIndex,
     RangeIndex,
-    StringIndex,
     TimedeltaIndex,
-    UInt8Index,
-    UInt16Index,
-    UInt32Index,
-    UInt64Index,
     interval_range,
 )
 from cudf.core.missing import NA
@@ -124,15 +112,8 @@
     "DatetimeIndex",
     "Decimal32Dtype",
     "Decimal64Dtype",
-    "Float32Index",
-    "Float64Index",
-    "GenericIndex",
     "Grouper",
     "Index",
-    "Int16Index",
-    "Int32Index",
-    "Int64Index",
-    "Int8Index",
     "IntervalDtype",
     "IntervalIndex",
     "ListDtype",
@@ -141,13 +122,8 @@
     "RangeIndex",
     "Scalar",
     "Series",
-    "StringIndex",
     "StructDtype",
     "TimedeltaIndex",
-    "UInt16Index",
-    "UInt32Index",
-    "UInt64Index",
-    "UInt8Index",
     "api",
     "concat",
     "crosstab",

python/cudf/cudf/_typing.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2021-2022, NVIDIA CORPORATION.
+# Copyright (c) 2021-2023, NVIDIA CORPORATION.
 
 import sys
 from typing import TYPE_CHECKING, Any, Callable, Dict, Iterable, TypeVar, Union
@@ -37,9 +37,7 @@
 
 DataFrameOrSeries = Union["cudf.Series", "cudf.DataFrame"]
 SeriesOrIndex = Union["cudf.Series", "cudf.core.index.BaseIndex"]
-SeriesOrSingleColumnIndex = Union[
-    "cudf.Series", "cudf.core.index.GenericIndex"
-]
+SeriesOrSingleColumnIndex = Union["cudf.Series", "cudf.core.index.Index"]
 
 # Groupby aggregation
 AggType = Union[str, Callable]

python/cudf/cudf/core/_base_index.py

@@ -57,9 +57,9 @@
 >>> import cudf
 >>> index = cudf.Index([1, 2, 3])
 >>> index
-Int64Index([1, 2, 3], dtype='int64')
+Index([1, 2, 3], dtype='int64')
 >>> index.astype('float64')
-Float64Index([1.0, 2.0, 3.0], dtype='float64')
+Index([1.0, 2.0, 3.0], dtype='float64')
 """
 
 BaseIndexT = TypeVar("BaseIndexT", bound="BaseIndex")
@@ -136,7 +136,7 @@ def get_level_values(self, level):
         >>> import cudf
         >>> idx = cudf.Index(["a", "b", "c"])
         >>> idx.get_level_values(0)
-        StringIndex(['a' 'b' 'c'], dtype='object')
+        Index(['a', 'b', 'c'], dtype='object')
         """
 
         if level == self.name:
@@ -226,15 +226,15 @@ def hasnans(self):
         >>> import numpy as np
         >>> index = cudf.Index([1, 2, np.nan, 3, 4], nan_as_null=False)
         >>> index
-        Float64Index([1.0, 2.0, nan, 3.0, 4.0], dtype='float64')
+        Index([1.0, 2.0, nan, 3.0, 4.0], dtype='float64')
         >>> index.hasnans
         True
 
         `hasnans` returns `True` for the presence of any `NA` values:
 
         >>> index = cudf.Index([1, 2, None, 3, 4])
         >>> index
-        Int64Index([1, 2, <NA>, 3, 4], dtype='int64')
+        Index([1, 2, <NA>, 3, 4], dtype='int64')
         >>> index.hasnans
         True
         """
@@ -287,9 +287,9 @@ def set_names(self, names, level=None, inplace=False):
         >>> import cudf
         >>> idx = cudf.Index([1, 2, 3, 4])
         >>> idx
-        Int64Index([1, 2, 3, 4], dtype='int64')
+        Index([1, 2, 3, 4], dtype='int64')
         >>> idx.set_names('quarter')
-        Int64Index([1, 2, 3, 4], dtype='int64', name='quarter')
+        Index([1, 2, 3, 4], dtype='int64', name='quarter')
         >>> idx = cudf.MultiIndex.from_product([['python', 'cobra'],
         ... [2018, 2019]])
         >>> idx
@@ -348,7 +348,7 @@ def union(self, other, sort=None):
         >>> idx1 = cudf.Index([1, 2, 3, 4])
         >>> idx2 = cudf.Index([3, 4, 5, 6])
         >>> idx1.union(idx2)
-        Int64Index([1, 2, 3, 4, 5, 6], dtype='int64')
+        Index([1, 2, 3, 4, 5, 6], dtype='int64')
 
         MultiIndex case
 
@@ -438,7 +438,7 @@ def intersection(self, other, sort=False):
         >>> idx1 = cudf.Index([1, 2, 3, 4])
         >>> idx2 = cudf.Index([3, 4, 5, 6])
         >>> idx1.intersection(idx2)
-        Int64Index([3, 4], dtype='int64')
+        Index([3, 4], dtype='int64')
 
         MultiIndex case
 
@@ -542,9 +542,9 @@ def fillna(self, value, downcast=None):
         >>> import cudf
         >>> index = cudf.Index([1, 2, None, 4])
         >>> index
-        Int64Index([1, 2, <NA>, 4], dtype='int64')
+        Index([1, 2, <NA>, 4], dtype='int64')
         >>> index.fillna(3)
-        Int64Index([1, 2, 3, 4], dtype='int64')
+        Index([1, 2, 3, 4], dtype='int64')
         """
         if downcast is not None:
             raise NotImplementedError(
@@ -636,13 +636,13 @@ def to_pandas(self, nullable=False):
         >>> import cudf
         >>> idx = cudf.Index([-3, 10, 15, 20])
         >>> idx
-        Int64Index([-3, 10, 15, 20], dtype='int64')
+        Index([-3, 10, 15, 20], dtype='int64')
         >>> idx.to_pandas()
-        Int64Index([-3, 10, 15, 20], dtype='int64')
+        Index([-3, 10, 15, 20], dtype='int64')
         >>> type(idx.to_pandas())
-        <class 'pandas.core.indexes.numeric.Int64Index'>
+        <class 'pandas.core.indexes.base.Index'>
         >>> type(idx)
-        <class 'cudf.core.index.Int64Index'>
+        <class 'cudf.core.index.Index'>
         """
         raise NotImplementedError
 
@@ -667,7 +667,7 @@ def isin(self, values):
         --------
         >>> idx = cudf.Index([1,2,3])
         >>> idx
-        Int64Index([1, 2, 3], dtype='int64')
+        Index([1, 2, 3], dtype='int64')
 
         Check whether each index value in a list of values.
 
@@ -737,17 +737,17 @@ def append(self, other):
         >>> import cudf
         >>> idx = cudf.Index([1, 2, 10, 100])
         >>> idx
-        Int64Index([1, 2, 10, 100], dtype='int64')
+        Index([1, 2, 10, 100], dtype='int64')
         >>> other = cudf.Index([200, 400, 50])
         >>> other
-        Int64Index([200, 400, 50], dtype='int64')
+        Index([200, 400, 50], dtype='int64')
         >>> idx.append(other)
-        Int64Index([1, 2, 10, 100, 200, 400, 50], dtype='int64')
+        Index([1, 2, 10, 100, 200, 400, 50], dtype='int64')
 
         append accepts list of Index objects
 
         >>> idx.append([other, other])
-        Int64Index([1, 2, 10, 100, 200, 400, 50, 200, 400, 50], dtype='int64')
+        Index([1, 2, 10, 100, 200, 400, 50, 200, 400, 50], dtype='int64')
         """
         raise NotImplementedError
 
@@ -779,14 +779,14 @@ def difference(self, other, sort=None):
         >>> import cudf
         >>> idx1 = cudf.Index([2, 1, 3, 4])
         >>> idx1
-        Int64Index([2, 1, 3, 4], dtype='int64')
+        Index([2, 1, 3, 4], dtype='int64')
         >>> idx2 = cudf.Index([3, 4, 5, 6])
         >>> idx2
-        Int64Index([3, 4, 5, 6], dtype='int64')
+        Index([3, 4, 5, 6], dtype='int64')
         >>> idx1.difference(idx2)
-        Int64Index([1, 2], dtype='int64')
+        Index([1, 2], dtype='int64')
         >>> idx1.difference(idx2, sort=False)
-        Int64Index([2, 1], dtype='int64')
+        Index([2, 1], dtype='int64')
         """
         if sort not in {None, False}:
             raise ValueError(
@@ -1232,18 +1232,18 @@ def sort_values(
         >>> import cudf
         >>> idx = cudf.Index([10, 100, 1, 1000])
         >>> idx
-        Int64Index([10, 100, 1, 1000], dtype='int64')
+        Index([10, 100, 1, 1000], dtype='int64')
 
         Sort values in ascending order (default behavior).
 
         >>> idx.sort_values()
-        Int64Index([1, 10, 100, 1000], dtype='int64')
+        Index([1, 10, 100, 1000], dtype='int64')
 
         Sort values in descending order, and also get the indices `idx` was
         sorted by.
 
         >>> idx.sort_values(ascending=False, return_indexer=True)
-        (Int64Index([1000, 100, 10, 1], dtype='int64'), array([3, 1, 0, 2],
+        (Index([1000, 100, 10, 1], dtype='int64'), array([3, 1, 0, 2],
                                                             dtype=int32))
 
         Sorting values in a MultiIndex:
@@ -1320,7 +1320,7 @@ def join(
                    names=['a', 'b'])
         >>> rhs = cudf.DataFrame({"a": [1, 4, 3]}).set_index('a').index
         >>> rhs
-        Int64Index([1, 4, 3], dtype='int64', name='a')
+        Index([1, 4, 3], dtype='int64', name='a')
         >>> lhs.join(rhs, how='inner')
         MultiIndex([(3, 4),
                     (1, 2)],
@@ -1403,12 +1403,12 @@ def rename(self, name, inplace=False):
         >>> import cudf
         >>> index = cudf.Index([1, 2, 3], name='one')
         >>> index
-        Int64Index([1, 2, 3], dtype='int64', name='one')
+        Index([1, 2, 3], dtype='int64', name='one')
         >>> index.name
         'one'
         >>> renamed_index = index.rename('two')
         >>> renamed_index
-        Int64Index([1, 2, 3], dtype='int64', name='two')
+        Index([1, 2, 3], dtype='int64', name='two')
         >>> renamed_index.name
         'two'
         """
@@ -1498,9 +1498,9 @@ def from_pandas(cls, index, nan_as_null=None):
         >>> data = [10, 20, 30, np.nan]
         >>> pdi = pd.Index(data)
         >>> cudf.Index.from_pandas(pdi)
-        Float64Index([10.0, 20.0, 30.0, <NA>], dtype='float64')
+        Index([10.0, 20.0, 30.0, <NA>], dtype='float64')
         >>> cudf.Index.from_pandas(pdi, nan_as_null=False)
-        Float64Index([10.0, 20.0, 30.0, nan], dtype='float64')
+        Index([10.0, 20.0, 30.0, nan], dtype='float64')
         """
         if not isinstance(index, pd.Index):
             raise TypeError("not a pandas.Index")
@@ -1671,7 +1671,7 @@ def take(self, indices, axis=0, allow_fill=True, fill_value=None):
         --------
         >>> idx = cudf.Index(['a', 'b', 'c', 'd', 'e'])
         >>> idx.take([2, 0, 4, 3])
-        StringIndex(['c' 'a' 'e' 'd'], dtype='object')
+        Index(['c', 'a', 'e', 'd'], dtype='object')
         """
 
         if axis not in {0, "index"}:
@@ -1722,9 +1722,9 @@ def repeat(self, repeats, axis=None):
         --------
         >>> index = cudf.Index([10, 22, 33, 55])
         >>> index
-        Int64Index([10, 22, 33, 55], dtype='int64')
+        Index([10, 22, 33, 55], dtype='int64')
         >>> index.repeat(5)
-        Int64Index([10, 10, 10, 10, 10, 22, 22, 22, 22, 22, 33,
+        Index([10, 10, 10, 10, 10, 22, 22, 22, 22, 22, 33,
                     33, 33, 33, 33, 55, 55, 55, 55, 55],
                 dtype='int64')
         """

python/cudf/cudf/core/algorithms.py

@@ -46,7 +46,7 @@ def factorize(values, sort=False, use_na_sentinel=True, size_hint=None):
     >>> codes
     array([0, 1, 1], dtype=int8)
     >>> uniques
-    StringIndex(['a' 'c'], dtype='object')
+    Index(['a' 'c'], dtype='object')
 
     When ``use_na_sentinel=True`` (the default), missing values are indicated
     in the `codes` with the sentinel value ``-1`` and missing values are not
@@ -56,7 +56,7 @@ def factorize(values, sort=False, use_na_sentinel=True, size_hint=None):
     >>> codes
     array([ 1, -1,  0,  2,  1], dtype=int8)
     >>> uniques
-    StringIndex(['a' 'b' 'c'], dtype='object')
+    Index(['a', 'b', 'c'], dtype='object')
 
     If NA is in the values, and we want to include NA in the uniques of the
     values, it can be achieved by setting ``use_na_sentinel=False``.
@@ -66,12 +66,12 @@ def factorize(values, sort=False, use_na_sentinel=True, size_hint=None):
     >>> codes
     array([ 0,  1,  0, -1], dtype=int8)
     >>> uniques
-    Float64Index([1.0, 2.0], dtype='float64')
+    Index([1.0, 2.0], dtype='float64')
     >>> codes, uniques = cudf.factorize(values, use_na_sentinel=False)
     >>> codes
     array([1, 2, 1, 0], dtype=int8)
     >>> uniques
-    Float64Index([<NA>, 1.0, 2.0], dtype='float64')
+    Index([<NA>, 1.0, 2.0], dtype='float64')
     """
 
     return_cupy_array = isinstance(values, cp.ndarray)

python/cudf/cudf/core/column/categorical.py

@@ -61,7 +61,7 @@ class CategoricalAccessor(ColumnMethods):
     dtype: category
     Categories (3, int64): [1, 2, 3]
     >>> s.cat.categories
-    Int64Index([1, 2, 3], dtype='int64')
+    Index([1, 2, 3], dtype='int64')
     >>> s.cat.reorder_categories([3,2,1])
     0    1
     1    2
@@ -104,7 +104,7 @@ def __init__(self, parent: SeriesOrSingleColumnIndex):
         super().__init__(parent=parent)
 
     @property
-    def categories(self) -> "cudf.core.index.GenericIndex":
+    def categories(self) -> "cudf.core.index.Index":
         """
         The categories of this categorical.
         """

python/cudf/cudf/core/column/methods.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2022, NVIDIA CORPORATION.
+# Copyright (c) 2020-2023, NVIDIA CORPORATION.
 
 from __future__ import annotations
 
@@ -8,7 +8,7 @@
 
 import cudf
 
-ParentType = Union["cudf.Series", "cudf.core.index.GenericIndex"]
+ParentType = Union["cudf.Series", "cudf.core.index.Index"]
 
 
 class ColumnMethods: