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

pandas/core/internals/construction.py

@@ -864,7 +864,7 @@ def _finalize_columns_and_data(
         # GH#26429 do not raise user-facing AssertionError
         raise ValueError(err) from err
 
-    if len(contents) and contents[0].dtype == np.object_:
+    if contents and contents[0].dtype == np.object_:
         contents = convert_object_array(contents, dtype=dtype)
 
     return contents, columns

pandas/core/internals/managers.py

@@ -1298,7 +1298,7 @@ def value_getitem(placement):
                     # Defer setting the new values to enable consolidation
                     self._iset_split_block(blkno_l, blk_locs, refs=refs)
 
-        if len(removed_blknos):
+        if removed_blknos:
             # Remove blocks & update blknos accordingly
             is_deleted = np.zeros(self.nblocks, dtype=np.bool_)
             is_deleted[removed_blknos] = True

pandas/io/formats/format.py

@@ -566,7 +566,7 @@ def _initialize_colspace(self, col_space: ColspaceArgType | None) -> ColspaceTyp
             result = {}
         elif isinstance(col_space, (int, str)):
             result = {"": col_space}
-            result.update({column: col_space for column in self.frame.columns})
+            result.update(dict.fromkeys(self.frame.columns, col_space))
         elif isinstance(col_space, Mapping):
             for column in col_space.keys():
                 if column not in self.frame.columns and column != "":

pandas/io/formats/style_render.py

@@ -1225,7 +1225,7 @@ def format(
         data = self.data.loc[subset]
 
         if not isinstance(formatter, dict):
-            formatter = {col: formatter for col in data.columns}
+            formatter = dict.fromkeys(data.columns, formatter)
 
         cis = self.columns.get_indexer_for(data.columns)
         ris = self.index.get_indexer_for(data.index)
@@ -1411,7 +1411,7 @@ def format_index(
             return self  # clear the formatter / revert to default and avoid looping
 
         if not isinstance(formatter, dict):
-            formatter = {level: formatter for level in levels_}
+            formatter = dict.fromkeys(levels_, formatter)
         else:
             formatter = {
                 obj._get_level_number(level): formatter_
@@ -1708,7 +1708,7 @@ def format_index_names(
             return self  # clear the formatter / revert to default and avoid looping
 
         if not isinstance(formatter, dict):
-            formatter = {level: formatter for level in levels_}
+            formatter = dict.fromkeys(levels_, formatter)
         else:
             formatter = {
                 obj._get_level_number(level): formatter_

pandas/io/pytables.py

@@ -1760,7 +1760,7 @@ def info(self) -> str:
 
         if self.is_open:
             lkeys = sorted(self.keys())
-            if len(lkeys):
+            if lkeys:
                 keys = []
                 values = []
 
@@ -4540,7 +4540,7 @@ def write_data(self, chunksize: int | None, dropna: bool = False) -> None:
                     masks.append(mask.astype("u1", copy=False))
 
         # consolidate masks
-        if len(masks):
+        if masks:
             mask = masks[0]
             for m in masks[1:]:
                 mask = mask & m
@@ -4660,7 +4660,7 @@ def delete(
             groups = list(diff[diff > 1].index)
 
             # 1 group
-            if not len(groups):
+            if not groups:
                 groups = [0]
 
             # final element

pandas/io/sql.py

@@ -1901,7 +1901,7 @@ def prep_table(
                 # Type[str], Type[float], Type[int], Type[complex], Type[bool],
                 # Type[object]]]]"; expected type "Union[ExtensionDtype, str,
                 # dtype[Any], Type[object]]"
-                dtype = {col_name: dtype for col_name in frame}  # type: ignore[misc]
+                dtype = dict.fromkeys(frame, dtype)  # type: ignore[arg-type]
             else:
                 dtype = cast(dict, dtype)
 
@@ -2615,7 +2615,7 @@ def _create_table_setup(self):
         ]
 
         ix_cols = [cname for cname, _, is_index in column_names_and_types if is_index]
-        if len(ix_cols):
+        if ix_cols:
             cnames = "_".join(ix_cols)
             cnames_br = ",".join([escape(c) for c in ix_cols])
             create_stmts.append(
@@ -2859,7 +2859,7 @@ def to_sql(
                 # Type[str], Type[float], Type[int], Type[complex], Type[bool],
                 # Type[object]]]]"; expected type "Union[ExtensionDtype, str,
                 # dtype[Any], Type[object]]"
-                dtype = {col_name: dtype for col_name in frame}  # type: ignore[misc]
+                dtype = dict.fromkeys(frame, dtype)  # type: ignore[arg-type]
             else:
                 dtype = cast(dict, dtype)
 

pandas/tests/apply/test_frame_apply.py

@@ -334,7 +334,7 @@ def test_apply_broadcast_scalars(float_frame):
 def test_apply_broadcast_scalars_axis1(float_frame):
     result = float_frame.apply(np.mean, axis=1, result_type="broadcast")
     m = float_frame.mean(axis=1)
-    expected = DataFrame({c: m for c in float_frame.columns})
+    expected = DataFrame(dict.fromkeys(float_frame.columns, m))
     tm.assert_frame_equal(result, expected)
 
 
@@ -361,7 +361,7 @@ def test_apply_broadcast_lists_index(float_frame):
     )
     m = list(range(len(float_frame.index)))
     expected = DataFrame(
-        {c: m for c in float_frame.columns},
+        dict.fromkeys(float_frame.columns, m),
         dtype="float64",
         index=float_frame.index,
     )

pandas/tests/dtypes/cast/test_maybe_box_native.py

@@ -17,7 +17,7 @@
     "obj,expected_dtype",
     [
         (b"\x00\x10", bytes),
-        (int(4), int),
+        ((4), int),
         (np.uint(4), int),
         (np.int32(-4), int),
         (np.uint8(4), int),

pandas/tests/io/parser/test_na_values.py

@@ -546,7 +546,7 @@ def test_na_values_dict_null_column_name(all_parsers):
     parser = all_parsers
     data = ",x,y\n\nMA,1,2\nNA,2,1\nOA,,3"
     names = [None, "x", "y"]
-    na_values = {name: STR_NA_VALUES for name in names}
+    na_values = dict.fromkeys(names, STR_NA_VALUES)
     dtype = {None: "object", "x": "float64", "y": "float64"}
 
     if parser.engine == "pyarrow":

pandas/tests/series/accessors/test_cat_accessor.py

@@ -40,7 +40,7 @@ def test_getname_categorical_accessor(self, method):
     def test_cat_accessor(self):
         ser = Series(Categorical(["a", "b", np.nan, "a"]))
         tm.assert_index_equal(ser.cat.categories, Index(["a", "b"]))
-        assert not ser.cat.ordered, False
+        assert not ser.cat.ordered
 
         exp = Categorical(["a", "b", np.nan, "a"], categories=["b", "a"])
 

pandas/tests/series/test_constructors.py

@@ -632,7 +632,7 @@ def test_constructor_maskedarray_hardened(self):
 
     def test_series_ctor_plus_datetimeindex(self):
         rng = date_range("20090415", "20090519", freq="B")
-        data = {k: 1 for k in rng}
+        data = dict.fromkeys(rng, 1)
 
         result = Series(data, index=rng)
         assert result.index.is_(rng)

pyproject.toml

@@ -234,8 +234,8 @@ select = [
   "TID",
   # implicit string concatenation
   "ISC",
-  # type-checking imports
-  "TCH",
+  # flake8-type-checking
+  "TC",
   # comprehensions
   "C4",
   # pygrep-hooks
@@ -390,6 +390,8 @@ ignore = [
   "PLW0108",
   # global-statement
   "PLW0603",
+  # runtime-cast-value
+  "TC006",
 ]
 
 exclude = [
@@ -429,7 +431,7 @@ exclude = [
 "pandas/tests/*" = ["B028", "FLY"]
 "scripts/*" = ["B028"]
 # Keep this one enabled
-"pandas/_typing.py" = ["TCH"]
+"pandas/_typing.py" = ["TC"]
 
 [tool.ruff.lint.flake8-pytest-style]
 fixture-parentheses = false

requirements-dev.txt

@@ -57,7 +57,7 @@ asv>=0.6.1
 flake8==7.1.0
 mypy==1.13.0
 tokenize-rt
-pre-commit>=4.0.1
+pre-commit>=4.2.0
 gitpython
 gitdb
 google-auth

setup.py

@@ -364,7 +364,7 @@ def run(self) -> None:
 # enable coverage by building cython files by setting the environment variable
 # "PANDAS_CYTHON_COVERAGE" (with a Truthy value) or by running build_ext
 # with `--with-cython-coverage`enabled
-linetrace = os.environ.get("PANDAS_CYTHON_COVERAGE", False)
+linetrace = os.environ.get("PANDAS_CYTHON_COVERAGE", False)  # noqa: PLW1508
 if "--with-cython-coverage" in sys.argv:
     linetrace = True
     sys.argv.remove("--with-cython-coverage")