Merge remote-tracking branch 'upstream/main' into ref/index_equiv

Author: mroeschke

.circleci/config.yml

@@ -54,7 +54,7 @@ jobs:
             /opt/python/cp311-cp311/bin/python -m venv ~/virtualenvs/pandas-dev
             . ~/virtualenvs/pandas-dev/bin/activate
             python -m pip install --no-cache-dir -U pip wheel setuptools meson-python==0.13.1 meson[ninja]==1.2.1
-            python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytz pytest>=7.3.2 pytest-xdist>=2.2.0 hypothesis>=6.46.1
+            python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytz pytest>=7.3.2 pytest-xdist>=3.4.0 hypothesis>=6.84.0
             python -m pip install --no-cache-dir --no-build-isolation -e . --config-settings=setup-args="--werror"
             python -m pip list --no-cache-dir
             export PANDAS_CI=1

.github/workflows/unit-tests.yml

@@ -227,7 +227,7 @@ jobs:
           . ~/virtualenvs/pandas-dev/bin/activate
           python -m pip install --no-cache-dir -U pip wheel setuptools meson[ninja]==1.2.1 meson-python==0.13.1
           python -m pip install numpy --config-settings=setup-args="-Dallow-noblas=true"
-          python -m pip install --no-cache-dir versioneer[toml] cython python-dateutil pytz pytest>=7.3.2 pytest-xdist>=2.2.0 hypothesis>=6.46.1
+          python -m pip install --no-cache-dir versioneer[toml] cython python-dateutil pytz pytest>=7.3.2 pytest-xdist>=3.4.0 hypothesis>=6.84.0
           python -m pip install --no-cache-dir --no-build-isolation -e . --config-settings=setup-args="--werror"
           python -m pip list --no-cache-dir
           export PANDAS_CI=1
@@ -265,7 +265,7 @@ jobs:
           /opt/python/cp311-cp311/bin/python -m venv ~/virtualenvs/pandas-dev
           . ~/virtualenvs/pandas-dev/bin/activate
           python -m pip install --no-cache-dir -U pip wheel setuptools meson-python==0.13.1 meson[ninja]==1.2.1
-          python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytz pytest>=7.3.2 pytest-xdist>=2.2.0 hypothesis>=6.46.1
+          python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytz pytest>=7.3.2 pytest-xdist>=3.4.0 hypothesis>=6.84.0
           python -m pip install --no-cache-dir --no-build-isolation -e . --config-settings=setup-args="--werror"
           python -m pip list --no-cache-dir
 
@@ -339,7 +339,7 @@ jobs:
           python -m pip install --upgrade pip setuptools wheel meson[ninja]==1.2.1 meson-python==0.13.1
           python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy
           python -m pip install versioneer[toml]
-          python -m pip install python-dateutil pytz tzdata cython hypothesis>=6.46.1 pytest>=7.3.2 pytest-xdist>=2.2.0 pytest-cov
+          python -m pip install python-dateutil pytz tzdata cython hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
           python -m pip install -ve . --no-build-isolation --no-index --no-deps --config-settings=setup-args="--werror"
           python -m pip list
 
@@ -382,15 +382,14 @@ jobs:
           python -m pip install --upgrade pip setuptools wheel meson[ninja]==1.2.1 meson-python==0.13.1
           python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy cython
           python -m pip install versioneer[toml]
-          python -m pip install python-dateutil pytz tzdata hypothesis>=6.46.1 pytest>=7.3.2 pytest-xdist>=2.2.0 pytest-cov
+          python -m pip install python-dateutil pytz tzdata hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
           python -m pip install -ve . --no-build-isolation --no-index --no-deps --config-settings=setup-args="--werror"
           python -m pip list
 
       - name: Run Tests
         uses: ./.github/actions/run-tests
-        env:
-          PYTHON_GIL: 0
 
+  # NOTE: this job must be kept in sync with the Pyodide build job in wheels.yml
   emscripten:
     # Note: the Python version, Emscripten toolchain version are determined
     # by the Pyodide version. The appropriate versions can be found in the

.github/workflows/wheels.yml

@@ -100,6 +100,13 @@ jobs:
         - [windows-2022, win_amd64]
         # TODO: support PyPy?
         python: [["cp310", "3.10"], ["cp311", "3.11"], ["cp312", "3.12"]]
+
+        # Build Pyodide wheels and upload them to Anaconda.org
+        # NOTE: this job is similar to the one in unit-tests.yml except for the fact
+        # that it uses cibuildwheel instead of a standard Pyodide xbuildenv setup.
+        include:
+          - buildplat: [ubuntu-22.04, pyodide_wasm32]
+            python: ["cp312", "3.12"]
     env:
       IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
       IS_SCHEDULE_DISPATCH: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -140,12 +147,13 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/[email protected].1
+        uses: pypa/[email protected].2
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
           CIBW_PRERELEASE_PYTHONS: True
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
+          CIBW_PLATFORM: ${{ matrix.buildplat[1] == 'pyodide_wasm32' && 'pyodide' || 'auto' }}
 
       - name: Set up Python
         uses: mamba-org/setup-micromamba@v1
@@ -170,7 +178,7 @@ jobs:
         shell: pwsh
         run: |
           $TST_CMD = @"
-          python -m pip install hypothesis>=6.46.1 pytest>=7.3.2 pytest-xdist>=2.2.0;
+          python -m pip install hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0;
           python -m pip install `$(Get-Item pandas\wheelhouse\*.whl);
           python -c `'import pandas as pd; pd.test(extra_args=[`\"--no-strict-data-files`\", `\"-m not clipboard and not single_cpu and not slow and not network and not db`\"])`';
           "@

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.7
+    rev: v0.5.0
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -73,7 +73,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.15.2
+    rev: v3.16.0
     hooks:
     -   id: pyupgrade
         args: [--py310-plus]
@@ -93,7 +93,7 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v18.1.5
+    rev: v18.1.8
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

asv_bench/benchmarks/indexing.py

@@ -546,24 +546,17 @@ def time_chained_indexing(self, mode):
 
 
 class Block:
-    params = [
-        (True, "True"),
-        (np.array(True), "np.array(True)"),
-    ]
-
-    def setup(self, true_value, mode):
+    def setup(self):
         self.df = DataFrame(
             False,
             columns=np.arange(500).astype(str),
             index=date_range("2010-01-01", "2011-01-01"),
         )
 
-        self.true_value = true_value
-
-    def time_test(self, true_value, mode):
+    def time_test(self):
         start = datetime(2010, 5, 1)
         end = datetime(2010, 9, 1)
-        self.df.loc[start:end, :] = true_value
+        self.df.loc[start:end, :] = True
 
 
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

ci/code_checks.sh

@@ -70,15 +70,8 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
-        -i "pandas.DataFrame.max RT03" \
-        -i "pandas.DataFrame.mean RT03" \
-        -i "pandas.DataFrame.median RT03" \
-        -i "pandas.DataFrame.min RT03" \
-        -i "pandas.DataFrame.plot PR02" \
-        -i "pandas.Grouper PR02" \
         -i "pandas.MultiIndex.append PR07,SA01" \
         -i "pandas.MultiIndex.copy PR07,RT03,SA01" \
-        -i "pandas.MultiIndex.drop PR07,RT03,SA01" \
         -i "pandas.MultiIndex.get_level_values SA01" \
         -i "pandas.MultiIndex.get_loc PR07" \
         -i "pandas.MultiIndex.get_loc_level PR07" \
@@ -95,7 +88,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.freqstr SA01" \
         -i "pandas.Period.month SA01" \
-        -i "pandas.Period.now SA01" \
         -i "pandas.Period.ordinal GL08" \
         -i "pandas.Period.strftime PR01,SA01" \
         -i "pandas.Period.to_timestamp SA01" \
@@ -161,13 +153,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.lt SA01" \
         -i "pandas.Series.ne SA01" \
         -i "pandas.Series.pad PR01,SA01" \
-        -i "pandas.Series.plot PR02" \
         -i "pandas.Series.pop SA01" \
         -i "pandas.Series.prod RT03" \
         -i "pandas.Series.product RT03" \
         -i "pandas.Series.reorder_levels RT03,SA01" \
         -i "pandas.Series.sem PR01,RT03,SA01" \
-        -i "pandas.Series.skew RT03,SA01" \
         -i "pandas.Series.sparse PR01,SA01" \
         -i "pandas.Series.sparse.density SA01" \
         -i "pandas.Series.sparse.fill_value SA01" \
@@ -205,8 +195,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.str.wrap RT03,SA01" \
         -i "pandas.Series.str.zfill RT03" \
         -i "pandas.Series.struct.dtypes SA01" \
-        -i "pandas.Series.to_dict SA01" \
-        -i "pandas.Series.to_frame SA01" \
         -i "pandas.Series.to_markdown SA01" \
         -i "pandas.Series.update PR07,SA01" \
         -i "pandas.Timedelta.asm8 SA01" \
@@ -244,13 +232,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.month_name SA01" \
         -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.normalize SA01" \
-        -i "pandas.Timestamp.now SA01" \
         -i "pandas.Timestamp.quarter SA01" \
         -i "pandas.Timestamp.replace PR07,SA01" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.second GL08" \
         -i "pandas.Timestamp.strptime PR01,SA01" \
-        -i "pandas.Timestamp.time SA01" \
         -i "pandas.Timestamp.timestamp SA01" \
         -i "pandas.Timestamp.timetuple SA01" \
         -i "pandas.Timestamp.timetz SA01" \
@@ -317,11 +303,9 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.types.is_period_dtype SA01" \
         -i "pandas.api.types.is_re PR07,SA01" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
-        -i "pandas.api.types.is_signed_integer_dtype SA01" \
         -i "pandas.api.types.is_sparse SA01" \
         -i "pandas.api.types.is_string_dtype SA01" \
         -i "pandas.api.types.is_timedelta64_ns_dtype SA01" \
-        -i "pandas.api.types.is_unsigned_integer_dtype SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.api.types.union_categoricals RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \

ci/deps/actions-310-minimum_versions.yaml

@@ -15,9 +15,9 @@ dependencies:
   # test dependencies
   - pytest>=7.3.2
   - pytest-cov
-  - pytest-xdist>=2.2.0
-  - pytest-localserver>=0.7.1
-  - pytest-qt>=4.2.0
+  - pytest-xdist>=3.4.0
+  - pytest-localserver>=0.8.1
+  - pytest-qt>=4.4.0
   - boto3
 
   # required dependencies
@@ -32,7 +32,7 @@ dependencies:
   - fastparquet=2023.10.0
   - fsspec=2022.11.0
   - html5lib=1.1
-  - hypothesis=6.46.1
+  - hypothesis=6.84.0
   - gcsfs=2022.11.0
   - jinja2=3.1.2
   - lxml=4.9.2

ci/deps/actions-310.yaml

@@ -13,8 +13,9 @@ dependencies:
   # test dependencies
   - pytest>=7.3.2
   - pytest-cov
-  - pytest-xdist>=2.2.0
-  - pytest-qt>=4.2.0
+  - pytest-xdist>=3.4.0
+  - pytest-localserver>=0.8.1
+  - pytest-qt>=4.4.0
   - boto3
 
   # required dependencies
@@ -29,7 +30,7 @@ dependencies:
   - fastparquet>=2023.10.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
-  - hypothesis>=6.46.1
+  - hypothesis>=6.84.0
   - gcsfs>=2022.11.0
   - jinja2>=3.1.2
   - lxml>=4.9.2
@@ -60,4 +61,3 @@ dependencies:
     - adbc-driver-postgresql>=0.10.0
     - adbc-driver-sqlite>=0.8.0
     - tzdata>=2022.7
-    - pytest-localserver>=0.7.1

ci/deps/actions-311-downstream_compat.yaml

@@ -14,9 +14,9 @@ dependencies:
   # test dependencies
   - pytest>=7.3.2
   - pytest-cov
-  - pytest-xdist>=2.2.0
-  - pytest-localserver>=0.7.1
-  - pytest-qt>=4.2.0
+  - pytest-xdist>=3.4.0
+  - pytest-localserver>=0.8.1
+  - pytest-qt>=4.4.0
   - boto3
 
   # required dependencies
@@ -31,7 +31,7 @@ dependencies:
   - fastparquet>=2023.10.0
   - fsspec>=2022.11.0
   - html5lib>=1.1
-  - hypothesis>=6.46.1
+  - hypothesis>=6.84.0
   - gcsfs>=2022.11.0
   - jinja2>=3.1.2
   - lxml>=4.9.2

ci/deps/actions-311-numpydev.yaml

@@ -13,8 +13,8 @@ dependencies:
   # test dependencies
   - pytest>=7.3.2
   - pytest-cov
-  - pytest-xdist>=2.2.0
-  - hypothesis>=6.46.1
+  - pytest-xdist>=3.4.0
+  - hypothesis>=6.84.0
 
   # pandas dependencies
   - python-dateutil