STY: Bump pre-commit checks (#61246)

* Bump pre-commit version, bump clang-format and meson

* Fix type checking abbreviation

* Bump to 0.11.4

* Put minimum version at 4

* Change misc to arg-type

Author: mroeschke

.pre-commit-config.yaml

@@ -1,4 +1,4 @@
-minimum_pre_commit_version: 2.15.0
+minimum_pre_commit_version: 4.0.0
 exclude: ^LICENSES/|\.(html|csv|svg)$
 # reserve "manual" for relatively slow hooks which we still want to run in CI
 default_stages: [
@@ -19,13 +19,13 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.9
+    rev: v0.11.4
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
         exclude: ^pandas/tests/frame/test_query_eval.py
     -   id: ruff
-        # TODO: remove autofixe-only rules when they are checked by ruff
+        # TODO: remove autofix only rules when they are checked by ruff
         name: ruff-selected-autofixes
         alias: ruff-selected-autofixes
         files: ^pandas
@@ -34,7 +34,7 @@ repos:
     -   id: ruff-format
         exclude: ^scripts|^pandas/tests/frame/test_query_eval.py
 -   repo: https://github.com/jendrikseipp/vulture
-    rev: 'v2.14'
+    rev: v2.14
     hooks:
       - id: vulture
         entry: python scripts/run_vulture.py
@@ -95,14 +95,14 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v19.1.7
+    rev: v20.1.0
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
       args: [-i]
       types_or: [c, c++]
 -   repo: https://github.com/trim21/pre-commit-mirror-meson
-    rev: v1.7.0
+    rev: v1.7.2
     hooks:
     - id: meson-fmt
       args: ['--inplace']

asv_bench/benchmarks/frame_methods.py

@@ -517,7 +517,7 @@ def setup(self):
         self.df = DataFrame(np.random.randn(1000, 100))
 
         self.s = Series(np.arange(1028.0))
-        self.df2 = DataFrame({i: self.s for i in range(1028)})
+        self.df2 = DataFrame(dict.fromkeys(range(1028), self.s))
         self.df3 = DataFrame(np.random.randn(1000, 3), columns=list("ABC"))
 
     def time_apply_user_func(self):

environment.yml

@@ -80,7 +80,7 @@ dependencies:
   - flake8=7.1.0  # run in subprocess over docstring examples
   - mypy=1.13.0  # pre-commit uses locally installed mypy
   - tokenize-rt  # scripts/check_for_inconsistent_pandas_namespace.py
-  - pre-commit>=4.0.1
+  - pre-commit>=4.2.0
 
   # documentation
   - gitpython  # obtain contributors from git for whatsnew

pandas/_libs/tslibs/timedeltas.pyi

@@ -3,7 +3,6 @@ from typing import (
     ClassVar,
     Literal,
     TypeAlias,
-    TypeVar,
     overload,
 )
 
@@ -60,7 +59,6 @@ UnitChoices: TypeAlias = Literal[
     "nanos",
     "nanosecond",
 ]
-_S = TypeVar("_S", bound=timedelta)
 
 def get_unit_for_round(freq, creso: int) -> int: ...
 def disallow_ambiguous_unit(unit: str | None) -> None: ...
@@ -95,11 +93,11 @@ class Timedelta(timedelta):
     _value: int  # np.int64
     # error: "__new__" must return a class instance (got "Union[Timestamp, NaTType]")
     def __new__(  # type: ignore[misc]
-        cls: type[_S],
+        cls: type[Self],
         value=...,
         unit: str | None = ...,
         **kwargs: float | np.integer | np.floating,
-    ) -> _S | NaTType: ...
+    ) -> Self | NaTType: ...
     @classmethod
     def _from_value_and_reso(cls, value: np.int64, reso: int) -> Timedelta: ...
     @property

pandas/core/apply.py

@@ -327,7 +327,7 @@ def transform(self) -> DataFrame | Series:
             if is_series:
                 func = {com.get_callable_name(v) or v: v for v in func}
             else:
-                func = {col: func for col in obj}
+                func = dict.fromkeys(obj, func)
 
         if is_dict_like(func):
             func = cast(AggFuncTypeDict, func)

pandas/core/arrays/string_arrow.py

@@ -281,7 +281,7 @@ def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:
         ]
 
         # short-circuit to return all False array.
-        if not len(value_set):
+        if not value_set:
             return np.zeros(len(self), dtype=bool)
 
         result = pc.is_in(

pandas/core/generic.py

@@ -9705,7 +9705,7 @@ def _where(
             # CoW: Make sure reference is not kept alive
             if cond.ndim == 1 and self.ndim == 2:
                 cond = cond._constructor_expanddim(
-                    {i: cond for i in range(len(self.columns))},
+                    dict.fromkeys(range(len(self.columns)), cond),
                     copy=False,
                 )
                 cond.columns = self.columns

pandas/core/groupby/generic.py

@@ -2505,7 +2505,7 @@ def _apply_to_column_groupbys(self, func) -> DataFrame:
         )
         results = [func(sgb) for sgb in sgbs]
 
-        if not len(results):
+        if not results:
             # concat would raise
             res_df = DataFrame([], columns=columns, index=self._grouper.result_index)
         else:

pandas/core/groupby/groupby.py

@@ -5175,8 +5175,8 @@ def diff(
                 shifted = shifted.astype("float32")
         else:
             to_coerce = [c for c, dtype in obj.dtypes.items() if dtype in dtypes_to_f32]
-            if len(to_coerce):
-                shifted = shifted.astype({c: "float32" for c in to_coerce})
+            if to_coerce:
+                shifted = shifted.astype(dict.fromkeys(to_coerce, "float32"))
 
         return obj - shifted
 

pandas/core/internals/blocks.py

@@ -805,7 +805,7 @@ def replace_list(
             for x, y in zip(src_list, dest_list)
             if (self._can_hold_element(x) or (self.dtype == "string" and is_re(x)))
         ]
-        if not len(pairs):
+        if not pairs:
             return [self.copy(deep=False)]
 
         src_len = len(pairs) - 1