Merge branch 'main' into tst-string-xfails

Author: jbrockmendel

.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)
 

ci/deps/actions-310-minimum_versions.yaml

@@ -41,7 +41,7 @@ dependencies:
   - qtpy=2.3.0
   - openpyxl=3.1.2
   - psycopg2=2.9.6
-  - pyarrow=10.0.1
+  - pyarrow=12.0.1
   - pyiceberg=0.7.1
   - pymysql=1.1.0
   - pyqt=5.15.9

ci/deps/actions-310.yaml

@@ -39,7 +39,7 @@ dependencies:
   - qtpy>=2.3.0
   - openpyxl>=3.1.2
   - psycopg2>=2.9.6
-  - pyarrow>=10.0.1
+  - pyarrow>=12.0.1
   - pyiceberg>=0.7.1
   - pymysql>=1.1.0
   - pyqt>=5.15.9

ci/deps/actions-311-downstream_compat.yaml

@@ -40,7 +40,7 @@ dependencies:
   - qtpy>=2.3.0
   - openpyxl>=3.1.2
   - psycopg2>=2.9.6
-  - pyarrow>=10.0.1
+  - pyarrow>=12.0.1
   - pyiceberg>=0.7.1
   - pymysql>=1.1.0
   - pyqt>=5.15.9

ci/deps/actions-311.yaml

@@ -40,7 +40,7 @@ dependencies:
   - pyqt>=5.15.9
   - openpyxl>=3.1.2
   - psycopg2>=2.9.6
-  - pyarrow>=10.0.1
+  - pyarrow>=12.0.1
   - pyiceberg>=0.7.1
   - pymysql>=1.1.0
   - pyreadstat>=1.2.6

ci/deps/actions-312.yaml

@@ -40,7 +40,7 @@ dependencies:
   - pyqt>=5.15.9
   - openpyxl>=3.1.2
   - psycopg2>=2.9.6
-  - pyarrow>=10.0.1
+  - pyarrow>=12.0.1
   - pyiceberg>=0.7.1
   - pymysql>=1.1.0
   - pyreadstat>=1.2.6

ci/deps/actions-313.yaml

@@ -41,7 +41,7 @@ dependencies:
   - pyqt>=5.15.9
   - openpyxl>=3.1.2
   - psycopg2>=2.9.6
-  - pyarrow>=10.0.1
+  - pyarrow>=12.0.1
   - pymysql>=1.1.0
   - pyreadstat>=1.2.6
   - pytables>=3.8.0

doc/source/getting_started/install.rst

@@ -307,7 +307,7 @@ Dependency                                             Minimum Version    pip ex
 `PyTables <https://github.com/PyTables/PyTables>`__    3.8.0              hdf5             HDF5-based reading / writing
 `zlib <https://github.com/madler/zlib>`__                                 hdf5             Compression for HDF5
 `fastparquet <https://github.com/dask/fastparquet>`__  2024.2.0           -                Parquet reading / writing (pyarrow is default)
-`pyarrow <https://github.com/apache/arrow>`__          10.0.1             parquet, feather Parquet, ORC, and feather reading / writing
+`pyarrow <https://github.com/apache/arrow>`__          12.0.1             parquet, feather Parquet, ORC, and feather reading / writing
 `PyIceberg <https://py.iceberg.apache.org/>`__         0.7.1              iceberg          Apache Iceberg reading / writing
 `pyreadstat <https://github.com/Roche/pyreadstat>`__   1.2.6              spss             SPSS files (.sav) reading
 `odfpy <https://github.com/eea/odfpy>`__               1.4.1              excel            Open document format (.odf, .ods, .odt) reading / writing

doc/source/user_guide/index.rst

@@ -87,5 +87,6 @@ Guides
     enhancingperf
     scale
     sparse
+    migration-3-strings
     gotchas
     cookbook