STY: pyupgrade to 3.9 (#54044)

Author: mroeschke

.pre-commit-config.yaml

@@ -20,7 +20,7 @@ repos:
     rev: 23.3.0
     hooks:
       - id: black
--   repo: https://github.com/charliermarsh/ruff-pre-commit
+-   repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.0.270
     hooks:
     -   id: ruff
@@ -94,7 +94,7 @@ repos:
     rev: v3.4.0
     hooks:
     -   id: pyupgrade
-        args: [--py38-plus]
+        args: [--py39-plus]
 -   repo: https://github.com/pre-commit/pygrep-hooks
     rev: v1.10.0
     hooks:
@@ -179,9 +179,6 @@ repos:
             |np\.bool[^_8`]
             |np\.object[^_8`]
 
-            # imports from collections.abc instead of `from collections import abc`
-            |from\ collections\.abc\ import
-
             # Numpy
             |from\ numpy\ import\ random
             |from\ numpy\.random\ import

doc/source/conf.py

@@ -586,14 +586,7 @@ class AccessorCallableDocumenter(AccessorLevelDocumenter, MethodDocumenter):
     priority = 0.5
 
     def format_name(self):
-        if sys.version_info < (3, 9):
-            # NOTE pyupgrade will remove this when we run it with --py39-plus
-            # so don't remove the unnecessary `else` statement below
-            from pandas.util._str_methods import removesuffix
-
-            return removesuffix(MethodDocumenter.format_name(self), ".__call__")
-        else:
-            return MethodDocumenter.format_name(self).removesuffix(".__call__")
+        return MethodDocumenter.format_name(self).removesuffix(".__call__")
 
 
 class PandasAutosummary(Autosummary):

pandas/_config/config.py

@@ -56,11 +56,10 @@
 )
 import re
 from typing import (
+    TYPE_CHECKING,
     Any,
     Callable,
-    Generator,
     Generic,
-    Iterable,
     NamedTuple,
     cast,
 )
@@ -72,6 +71,12 @@
 )
 from pandas.util._exceptions import find_stack_level
 
+if TYPE_CHECKING:
+    from collections.abc import (
+        Generator,
+        Iterable,
+    )
+
 
 class DeprecatedOption(NamedTuple):
     key: str

pandas/_config/localization.py

@@ -10,10 +10,13 @@
 import platform
 import re
 import subprocess
-from typing import Generator
+from typing import TYPE_CHECKING
 
 from pandas._config.config import options
 
+if TYPE_CHECKING:
+    from collections.abc import Generator
+
 
 @contextmanager
 def set_locale(

pandas/_testing/__init__.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import collections
+from collections import Counter
 from datetime import datetime
 from decimal import Decimal
 import operator
@@ -12,8 +13,6 @@
     TYPE_CHECKING,
     Callable,
     ContextManager,
-    Counter,
-    Iterable,
     cast,
 )
 
@@ -109,6 +108,8 @@
 from pandas.core.construction import extract_array
 
 if TYPE_CHECKING:
+    from collections.abc import Iterable
+
     from pandas._typing import (
         Dtype,
         Frequency,

pandas/_testing/_warnings.py

@@ -7,14 +7,18 @@
 import re
 import sys
 from typing import (
-    Generator,
+    TYPE_CHECKING,
     Literal,
-    Sequence,
-    Type,
     cast,
 )
 import warnings
 
+if TYPE_CHECKING:
+    from collections.abc import (
+        Generator,
+        Sequence,
+    )
+
 
 @contextmanager
 def assert_produces_warning(
@@ -91,7 +95,7 @@ class for all warnings. To raise multiple types of exceptions,
             yield w
         finally:
             if expected_warning:
-                expected_warning = cast(Type[Warning], expected_warning)
+                expected_warning = cast(type[Warning], expected_warning)
                 _assert_caught_expected_warning(
                     caught_warnings=w,
                     expected_warning=expected_warning,
@@ -195,7 +199,7 @@ def _is_unexpected_warning(
     """Check if the actual warning issued is unexpected."""
     if actual_warning and not expected_warning:
         return True
-    expected_warning = cast(Type[Warning], expected_warning)
+    expected_warning = cast(type[Warning], expected_warning)
     return bool(not issubclass(actual_warning.category, expected_warning))
 
 

pandas/_testing/contexts.py

@@ -8,7 +8,6 @@
     IO,
     TYPE_CHECKING,
     Any,
-    Generator,
 )
 import uuid
 
@@ -20,6 +19,8 @@
 from pandas.io.common import get_handle
 
 if TYPE_CHECKING:
+    from collections.abc import Generator
+
     from pandas._typing import (
         BaseBuffer,
         CompressionOptions,

pandas/_typing.py

@@ -1,5 +1,11 @@
 from __future__ import annotations
 
+from collections.abc import (
+    Hashable,
+    Iterator,
+    Mapping,
+    Sequence,
+)
 from datetime import (
     datetime,
     timedelta,
@@ -11,16 +17,9 @@
     TYPE_CHECKING,
     Any,
     Callable,
-    Dict,
-    Hashable,
-    Iterator,
-    List,
     Literal,
-    Mapping,
     Optional,
     Protocol,
-    Sequence,
-    Tuple,
     Type as type_t,
     TypeVar,
     Union,
@@ -111,7 +110,7 @@
 # Cannot use `Sequence` because a string is a sequence, and we don't want to
 # accept that.  Could refine if https://github.com/python/typing/issues/256 is
 # resolved to differentiate between Sequence[str] and str
-ListLike = Union[AnyArrayLike, List, range]
+ListLike = Union[AnyArrayLike, list, range]
 
 # scalars
 
@@ -146,10 +145,10 @@
 Axis = Union[AxisInt, Literal["index", "columns", "rows"]]
 IndexLabel = Union[Hashable, Sequence[Hashable]]
 Level = Hashable
-Shape = Tuple[int, ...]
-Suffixes = Tuple[Optional[str], Optional[str]]
+Shape = tuple[int, ...]
+Suffixes = tuple[Optional[str], Optional[str]]
 Ordered = Optional[bool]
-JSONSerializable = Optional[Union[PythonScalar, List, Dict]]
+JSONSerializable = Optional[Union[PythonScalar, list, dict]]
 Frequency = Union[str, "BaseOffset"]
 Axes = ListLike
 
@@ -166,15 +165,15 @@
 Dtype = Union["ExtensionDtype", NpDtype]
 AstypeArg = Union["ExtensionDtype", "npt.DTypeLike"]
 # DtypeArg specifies all allowable dtypes in a functions its dtype argument
-DtypeArg = Union[Dtype, Dict[Hashable, Dtype]]
+DtypeArg = Union[Dtype, dict[Hashable, Dtype]]
 DtypeObj = Union[np.dtype, "ExtensionDtype"]
 
 # converters
-ConvertersArg = Dict[Hashable, Callable[[Dtype], Dtype]]
+ConvertersArg = dict[Hashable, Callable[[Dtype], Dtype]]
 
 # parse_dates
 ParseDatesArg = Union[
-    bool, List[Hashable], List[List[Hashable]], Dict[Hashable, List[Hashable]]
+    bool, list[Hashable], list[list[Hashable]], dict[Hashable, list[Hashable]]
 ]
 
 # For functions like rename that convert one label to another
@@ -195,10 +194,10 @@
 
 # types of `func` kwarg for DataFrame.aggregate and Series.aggregate
 AggFuncTypeBase = Union[Callable, str]
-AggFuncTypeDict = Dict[Hashable, Union[AggFuncTypeBase, List[AggFuncTypeBase]]]
+AggFuncTypeDict = dict[Hashable, Union[AggFuncTypeBase, list[AggFuncTypeBase]]]
 AggFuncType = Union[
     AggFuncTypeBase,
-    List[AggFuncTypeBase],
+    list[AggFuncTypeBase],
     AggFuncTypeDict,
 ]
 AggObjType = Union[
@@ -286,18 +285,18 @@ def closed(self) -> bool:
 FilePath = Union[str, "PathLike[str]"]
 
 # for arbitrary kwargs passed during reading/writing files
-StorageOptions = Optional[Dict[str, Any]]
+StorageOptions = Optional[dict[str, Any]]
 
 
 # compression keywords and compression
-CompressionDict = Dict[str, Any]
+CompressionDict = dict[str, Any]
 CompressionOptions = Optional[
     Union[Literal["infer", "gzip", "bz2", "zip", "xz", "zstd", "tar"], CompressionDict]
 ]
 
 # types in DataFrameFormatter
 FormattersType = Union[
-    List[Callable], Tuple[Callable, ...], Mapping[Union[str, int], Callable]
+    list[Callable], tuple[Callable, ...], Mapping[Union[str, int], Callable]
 ]
 ColspaceType = Mapping[Hashable, Union[str, int]]
 FloatFormatType = Union[str, Callable, "EngFormatter"]
@@ -347,9 +346,9 @@ def closed(self) -> bool:
 # https://bugs.python.org/issue41810
 # Using List[int] here rather than Sequence[int] to disallow tuples.
 ScalarIndexer = Union[int, np.integer]
-SequenceIndexer = Union[slice, List[int], np.ndarray]
+SequenceIndexer = Union[slice, list[int], np.ndarray]
 PositionalIndexer = Union[ScalarIndexer, SequenceIndexer]
-PositionalIndexerTuple = Tuple[PositionalIndexer, PositionalIndexer]
+PositionalIndexerTuple = tuple[PositionalIndexer, PositionalIndexer]
 PositionalIndexer2D = Union[PositionalIndexer, PositionalIndexerTuple]
 if TYPE_CHECKING:
     TakeIndexer = Union[Sequence[int], Sequence[np.integer], npt.NDArray[np.integer]]

pandas/_version.py

@@ -16,10 +16,7 @@
 import re
 import subprocess
 import sys
-from typing import (
-    Callable,
-    Dict,
-)
+from typing import Callable
 
 
 def get_keywords():
@@ -57,8 +54,8 @@ class NotThisMethod(Exception):
     """Exception raised if a method is not valid for the current scenario."""
 
 
-LONG_VERSION_PY: Dict[str, str] = {}
-HANDLERS: Dict[str, Dict[str, Callable]] = {}
+LONG_VERSION_PY: dict[str, str] = {}
+HANDLERS: dict[str, dict[str, Callable]] = {}
 
 
 def register_vcs_handler(vcs, method):  # decorator

pandas/compat/pickle_compat.py

@@ -7,7 +7,7 @@
 import copy
 import io
 import pickle as pkl
-from typing import Generator
+from typing import TYPE_CHECKING
 
 import numpy as np
 
@@ -22,6 +22,9 @@
 )
 from pandas.core.internals import BlockManager
 
+if TYPE_CHECKING:
+    from collections.abc import Generator
+
 
 def load_reduce(self):
     stack = self.stack

pandas/conftest.py

@@ -32,9 +32,8 @@
 import os
 from pathlib import Path
 from typing import (
+    TYPE_CHECKING,
     Callable,
-    Hashable,
-    Iterator,
 )
 
 from dateutil.tz import (
@@ -73,6 +72,12 @@
     MultiIndex,
 )
 
+if TYPE_CHECKING:
+    from collections.abc import (
+        Hashable,
+        Iterator,
+    )
+
 try:
     import pyarrow as pa
 except ImportError: