Merge branch 'pandas-dev:main' into fix_55490

Author: xiaohuanlin

.github/CODEOWNERS

@@ -9,7 +9,6 @@ doc/cheatsheet                    @Dr-Irv
 doc/source/development            @noatamir
 
 # pandas
-pandas/_libs/                     @WillAyd
 pandas/_typing.py                 @Dr-Irv
 pandas/core/groupby/*             @rhshadrach
 pandas/io/excel/*                 @rhshadrach

.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -31,7 +31,7 @@ body:
     attributes:
       label: Feature Description
       description: >
-        Please describe how the new feature would be implemented, using psudocode if relevant.
+        Please describe how the new feature would be implemented, using pseudocode if relevant.
       placeholder: >
         Add a new parameter to DataFrame, to_series, to return a Series if possible.
 

.github/workflows/unit-tests.yml

@@ -27,7 +27,7 @@ jobs:
     strategy:
       matrix:
         platform: [ubuntu-22.04, ubuntu-24.04-arm]
-        env_file: [actions-310.yaml, actions-311.yaml, actions-312.yaml]
+        env_file: [actions-310.yaml, actions-311.yaml, actions-312.yaml, actions-313.yaml]
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
         pandas_future_infer_string: ["0"]
@@ -188,7 +188,7 @@ jobs:
       matrix:
         # Note: Don't use macOS latest since macos 14 appears to be arm64 only
         os: [macos-13, macos-14, windows-latest]
-        env_file: [actions-310.yaml, actions-311.yaml, actions-312.yaml]
+        env_file: [actions-310.yaml, actions-311.yaml, actions-312.yaml, actions-313.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}
     name: ${{ format('{0} {1}', matrix.os, matrix.env_file) }}
@@ -316,7 +316,7 @@ jobs:
     #    To freeze this file, uncomment out the ``if: false`` condition, and migrate the jobs
     #    to the corresponding posix/windows-macos/sdist etc. workflows.
     # Feel free to modify this comment as necessary.
-    # if: false # Uncomment this to freeze the workflow, comment it to unfreeze
+    if: false
     defaults:
       run:
         shell: bash -eou pipefail {0}

.github/workflows/wheels.yml

@@ -153,7 +153,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/[email protected].1
+        uses: pypa/[email protected].3
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

.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):

asv_bench/benchmarks/indexing_engines.py

@@ -67,6 +67,14 @@ class NumericEngineIndexing:
     def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
 
+        if (
+            index_type == "non_monotonic"
+            and dtype in [np.int16, np.int8, np.uint8]
+            and unique
+        ):
+            # Values overflow
+            raise NotImplementedError
+
         if index_type == "monotonic_incr":
             if unique:
                 arr = np.arange(N * 3, dtype=dtype)
@@ -115,6 +123,14 @@ def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
         dtype = dtype.lower()
 
+        if (
+            index_type == "non_monotonic"
+            and dtype in ["int16", "int8", "uint8"]
+            and unique
+        ):
+            # Values overflow
+            raise NotImplementedError
+
         if index_type == "monotonic_incr":
             if unique:
                 arr = np.arange(N * 3, dtype=dtype)

ci/code_checks.sh

@@ -72,9 +72,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
-        -i "pandas.Timestamp.max PR02" \
-        -i "pandas.Timestamp.min PR02" \
-        -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.resample.Resampler.quantile PR01,PR07" \

ci/deps/actions-310-minimum_versions.yaml

@@ -25,39 +25,39 @@ dependencies:
   - numpy=1.23.5
 
   # optional dependencies
-  - beautifulsoup4=4.11.2
+  - beautifulsoup4=4.12.3
   - blosc=1.21.3
   - bottleneck=1.3.6
-  - fastparquet=2023.10.0
-  - fsspec=2022.11.0
+  - fastparquet=2024.2.0
+  - fsspec=2024.2.0
   - html5lib=1.1
   - hypothesis=6.84.0
-  - gcsfs=2022.11.0
-  - jinja2=3.1.2
+  - gcsfs=2024.2.0
+  - jinja2=3.1.3
   - lxml=4.9.2
-  - matplotlib=3.6.3
-  - numba=0.56.4
-  - numexpr=2.8.4
+  - matplotlib=3.8.3
+  - numba=0.59.0
+  - numexpr=2.9.0
   - odfpy=1.4.1
   - qtpy=2.3.0
-  - openpyxl=3.1.0
+  - openpyxl=3.1.2
   - psycopg2=2.9.6
   - pyarrow=10.0.1
-  - pymysql=1.0.2
+  - pymysql=1.1.0
   - pyqt=5.15.9
-  - pyreadstat=1.2.0
+  - pyreadstat=1.2.6
   - pytables=3.8.0
   - python-calamine=0.1.7
   - pytz=2023.4
   - pyxlsb=1.0.10
-  - s3fs=2022.11.0
-  - scipy=1.10.0
+  - s3fs=2024.2.0
+  - scipy=1.12.0
   - sqlalchemy=2.0.0
   - tabulate=0.9.0
-  - xarray=2022.12.0
+  - xarray=2024.1.1
   - xlrd=2.0.1
-  - xlsxwriter=3.0.5
-  - zstandard=0.19.0
+  - xlsxwriter=3.2.0
+  - zstandard=0.22.0
 
   - pip:
     - adbc-driver-postgresql==0.10.0

ci/deps/actions-310.yaml

@@ -23,39 +23,39 @@ dependencies:
   - numpy
 
   # optional dependencies
-  - beautifulsoup4>=4.11.2
+  - beautifulsoup4>=4.12.3
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2023.10.0
-  - fsspec>=2022.11.0
+  - fastparquet>=2024.2.0
+  - fsspec>=2024.2.0
   - html5lib>=1.1
   - hypothesis>=6.84.0
-  - gcsfs>=2022.11.0
-  - jinja2>=3.1.2
+  - gcsfs>=2024.2.0
+  - jinja2>=3.1.3
   - lxml>=4.9.2
-  - matplotlib>=3.6.3
-  - numba>=0.56.4
-  - numexpr>=2.8.4
+  - matplotlib>=3.8.3
+  - numba>=0.59.0
+  - numexpr>=2.9.0
   - odfpy>=1.4.1
   - qtpy>=2.3.0
-  - openpyxl>=3.1.0
+  - openpyxl>=3.1.2
   - psycopg2>=2.9.6
   - pyarrow>=10.0.1
-  - pymysql>=1.0.2
+  - pymysql>=1.1.0
   - pyqt>=5.15.9
-  - pyreadstat>=1.2.0
+  - pyreadstat>=1.2.6
   - pytables>=3.8.0
   - python-calamine>=0.1.7
   - pytz>=2023.4
   - pyxlsb>=1.0.10
-  - s3fs>=2022.11.0
-  - scipy>=1.10.0
+  - s3fs>=2024.2.0
+  - scipy>=1.12.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
-  - xarray>=2022.12.0, <=2024.9.0
+  - xarray>=2024.1.1, <=2024.9.0
   - xlrd>=2.0.1
-  - xlsxwriter>=3.0.5
-  - zstandard>=0.19.0
+  - xlsxwriter>=3.2.0
+  - zstandard>=0.22.0
 
   - pip:
     - adbc-driver-postgresql>=0.10.0

ci/deps/actions-311-downstream_compat.yaml

@@ -24,39 +24,39 @@ dependencies:
   - numpy
 
   # optional dependencies
-  - beautifulsoup4>=4.11.2
+  - beautifulsoup4>=4.12.3
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2023.10.0
-  - fsspec>=2022.11.0
+  - fastparquet>=2024.2.0
+  - fsspec>=2024.2.0
   - html5lib>=1.1
   - hypothesis>=6.84.0
-  - gcsfs>=2022.11.0
-  - jinja2>=3.1.2
+  - gcsfs>=2024.2.0
+  - jinja2>=3.1.3
   - lxml>=4.9.2
-  - matplotlib>=3.6.3
-  - numba>=0.56.4
-  - numexpr>=2.8.4
+  - matplotlib>=3.8.3
+  - numba>=0.59.0
+  - numexpr>=2.9.0
   - odfpy>=1.4.1
   - qtpy>=2.3.0
-  - openpyxl>=3.1.0
+  - openpyxl>=3.1.2
   - psycopg2>=2.9.6
   - pyarrow>=10.0.1
-  - pymysql>=1.0.2
+  - pymysql>=1.1.0
   - pyqt>=5.15.9
-  - pyreadstat>=1.2.0
+  - pyreadstat>=1.2.6
   - pytables>=3.8.0
   - python-calamine>=0.1.7
   - pytz>=2023.4
   - pyxlsb>=1.0.10
-  - s3fs>=2022.11.0
-  - scipy>=1.10.0
+  - s3fs>=2024.2.0
+  - scipy>=1.12.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
-  - xarray>=2022.12.0, <=2024.9.0
+  - xarray>=2024.1.1, <=2024.9.0
   - xlrd>=2.0.1
-  - xlsxwriter>=3.0.5
-  - zstandard>=0.19.0
+  - xlsxwriter>=3.2.0
+  - zstandard>=0.22.0
 
   # downstream packages
   - botocore

ci/deps/actions-311.yaml

@@ -23,39 +23,39 @@ dependencies:
   - numpy
 
   # optional dependencies
-  - beautifulsoup4>=4.11.2
+  - beautifulsoup4>=4.12.3
   - blosc>=1.21.3
   - bottleneck>=1.3.6
-  - fastparquet>=2023.10.0
-  - fsspec>=2022.11.0
+  - fastparquet>=2024.2.0
+  - fsspec>=2024.2.0
   - html5lib>=1.1
   - hypothesis>=6.84.0
-  - gcsfs>=2022.11.0
-  - jinja2>=3.1.2
+  - gcsfs>=2024.2.0
+  - jinja2>=3.1.3
   - lxml>=4.9.2
-  - matplotlib>=3.6.3
-  - numba>=0.56.4
-  - numexpr>=2.8.4
+  - matplotlib>=3.8.3
+  - numba>=0.59.0
+  - numexpr>=2.9.0
   - odfpy>=1.4.1
   - qtpy>=2.3.0
   - pyqt>=5.15.9
-  - openpyxl>=3.1.0
+  - openpyxl>=3.1.2
   - psycopg2>=2.9.6
   - pyarrow>=10.0.1
-  - pymysql>=1.0.2
-  - pyreadstat>=1.2.0
+  - pymysql>=1.1.0
+  - pyreadstat>=1.2.6
   - pytables>=3.8.0
   - python-calamine>=0.1.7
   - pytz>=2023.4
   - pyxlsb>=1.0.10
-  - s3fs>=2022.11.0
-  - scipy>=1.10.0
+  - s3fs>=2024.2.0
+  - scipy>=1.12.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
-  - xarray>=2022.12.0, <=2024.9.0
+  - xarray>=2024.1.1, <=2024.9.0
   - xlrd>=2.0.1
-  - xlsxwriter>=3.0.5
-  - zstandard>=0.19.0
+  - xlsxwriter>=3.2.0
+  - zstandard>=0.22.0
 
   - pip:
     - adbc-driver-postgresql>=0.10.0