[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.12
+    rev: v0.12.2
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -47,7 +47,7 @@ repos:
         types_or: [python, rst, markdown, cython, c]
         additional_dependencies: [tomli]
 -   repo: https://github.com/MarcoGorelli/cython-lint
-    rev: v0.16.6
+    rev: v0.16.7
     hooks:
     -   id: cython-lint
     -   id: double-quote-cython-strings
@@ -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: v20.1.5
+    rev: v20.1.7
     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: v1.8.1
+    rev: v1.8.2
     hooks:
     - id: meson-fmt
       args: ['--inplace']

asv_bench/benchmarks/gil.py

@@ -36,7 +36,7 @@
 from .pandas_vb_common import BaseIO  # isort:skip
 
 
-def test_parallel(num_threads=2, kwargs_list=None):
+def run_parallel(num_threads=2, kwargs_list=None):
     """
     Decorator to run the same function multiple times in parallel.
 
@@ -95,7 +95,7 @@ def setup(self, threads, method):
             {"key": np.random.randint(0, ngroups, size=N), "data": np.random.randn(N)}
         )
 
-        @test_parallel(num_threads=threads)
+        @run_parallel(num_threads=threads)
         def parallel():
             getattr(df.groupby("key")["data"], method)()
 
@@ -123,7 +123,7 @@ def setup(self, threads):
         ngroups = 10**3
         data = Series(np.random.randint(0, ngroups, size=size))
 
-        @test_parallel(num_threads=threads)
+        @run_parallel(num_threads=threads)
         def get_groups():
             data.groupby(data).groups
 
@@ -142,7 +142,7 @@ def setup(self, dtype):
         df = DataFrame({"col": np.arange(N, dtype=dtype)})
         indexer = np.arange(100, len(df) - 100)
 
-        @test_parallel(num_threads=2)
+        @run_parallel(num_threads=2)
         def parallel_take1d():
             take_nd(df["col"].values, indexer)
 
@@ -163,7 +163,7 @@ def setup(self):
         k = 5 * 10**5
         kwargs_list = [{"arr": np.random.randn(N)}, {"arr": np.random.randn(N)}]
 
-        @test_parallel(num_threads=2, kwargs_list=kwargs_list)
+        @run_parallel(num_threads=2, kwargs_list=kwargs_list)
         def parallel_kth_smallest(arr):
             algos.kth_smallest(arr, k)
 
@@ -180,42 +180,42 @@ def setup(self):
         self.period = self.dti.to_period("D")
 
     def time_datetime_field_year(self):
-        @test_parallel(num_threads=2)
+        @run_parallel(num_threads=2)
         def run(dti):
             dti.year
 
         run(self.dti)
 
     def time_datetime_field_day(self):
-        @test_parallel(num_threads=2)
+        @run_parallel(num_threads=2)
         def run(dti):
             dti.day
 
         run(self.dti)
 
     def time_datetime_field_daysinmonth(self):
-        @test_parallel(num_threads=2)
+        @run_parallel(num_threads=2)
         def run(dti):
             dti.days_in_month
 
         run(self.dti)
 
     def time_datetime_field_normalize(self):
-        @test_parallel(num_threads=2)
+        @run_parallel(num_threads=2)
         def run(dti):
             dti.normalize()
 
         run(self.dti)
 
     def time_datetime_to_period(self):
-        @test_parallel(num_threads=2)
+        @run_parallel(num_threads=2)
         def run(dti):
             dti.to_period("s")
 
         run(self.dti)
 
     def time_period_to_datetime(self):
-        @test_parallel(num_threads=2)
+        @run_parallel(num_threads=2)
         def run(period):
             period.to_timestamp()
 
@@ -232,7 +232,7 @@ def setup(self, method):
         if hasattr(DataFrame, "rolling"):
             df = DataFrame(arr).rolling(win)
 
-            @test_parallel(num_threads=2)
+            @run_parallel(num_threads=2)
             def parallel_rolling():
                 getattr(df, method)()
 
@@ -249,7 +249,7 @@ def parallel_rolling():
                 "std": rolling_std,
             }
 
-            @test_parallel(num_threads=2)
+            @run_parallel(num_threads=2)
             def parallel_rolling():
                 rolling[method](arr, win)
 
@@ -286,7 +286,7 @@ def setup(self, dtype):
         self.fname = f"__test_{dtype}__.csv"
         df.to_csv(self.fname)
 
-        @test_parallel(num_threads=2)
+        @run_parallel(num_threads=2)
         def parallel_read_csv():
             read_csv(self.fname)
 
@@ -305,7 +305,7 @@ class ParallelFactorize:
     def setup(self, threads):
         strings = Index([f"i-{i}" for i in range(100000)], dtype=object)
 
-        @test_parallel(num_threads=threads)
+        @run_parallel(num_threads=threads)
         def parallel():
             factorize(strings)
 

pandas/core/frame.py

@@ -7235,7 +7235,7 @@ def sort_values(
             indexer = lexsort_indexer(
                 keys_data, orders=ascending, na_position=na_position, key=key
             )
-        elif len(by):
+        elif by:
             # len(by) == 1
 
             k = self._get_label_or_level_values(by[0], axis=axis)

pandas/core/indexes/base.py

@@ -7635,7 +7635,7 @@ def ensure_index(index_like: Axes, copy: bool = False) -> Index:
             # check in clean_index_list
             index_like = list(index_like)
 
-        if len(index_like) and lib.is_all_arraylike(index_like):
+        if index_like and lib.is_all_arraylike(index_like):
             from pandas.core.indexes.multi import MultiIndex
 
             return MultiIndex.from_arrays(index_like)

pandas/io/parsers/base_parser.py

@@ -243,7 +243,7 @@ def extract(r):
             names.insert(single_ic, single_ic)
 
         # Clean the column names (if we have an index_col).
-        if len(ic):
+        if ic:
             col_names = [
                 r[ic[0]]
                 if ((r[ic[0]] is not None) and r[ic[0]] not in self.unnamed_cols)

pandas/io/parsers/python_parser.py

@@ -281,7 +281,7 @@ def read(
 
         index: Index | None
         columns: Sequence[Hashable] = list(self.orig_names)
-        if not len(content):  # pragma: no cover
+        if not content:  # pragma: no cover
             # DataFrame with the right metadata, even though it's length 0
             # error: Cannot determine type of 'index_col'
             names = dedup_names(

pandas/tests/arithmetic/test_datetime64.py

@@ -9,7 +9,6 @@
 )
 from itertools import (
     product,
-    starmap,
 )
 import operator
 
@@ -2211,7 +2210,7 @@ def test_timedelta64_equal_timedelta_supported_ops(self, op, box_with_array):
 
         def timedelta64(*args):
             # see casting notes in NumPy gh-12927
-            return np.sum(list(starmap(np.timedelta64, zip(args, intervals))))
+            return np.sum(list(map(np.timedelta64, args, intervals)))
 
         for d, h, m, s, us in product(*([range(2)] * 5)):
             nptd = timedelta64(d, h, m, s, us)

pandas/util/_tester.py

@@ -12,7 +12,7 @@
 PKG = os.path.dirname(os.path.dirname(__file__))
 
 
-def test(extra_args: list[str] | None = None, run_doctests: bool = False) -> None:
+def test(extra_args: list[str] | None = None, run_doctests: bool = False) -> None:  # noqa: PT028
     """
     Run the pandas test suite using pytest.
 

pyproject.toml

@@ -318,6 +318,8 @@ ignore = [
   "ISC001",
   # if-stmt-min-max
   "PLR1730",
+  # nan-comparison
+  "PLW0177",
 
   ### TODO: Enable gradually
   # Useless statement