Merge remote-tracking branch 'upstream/main' into wooseogchoi-59095

merged from upstream/main

Author: wooseogchoi

.github/actions/build_pandas/action.yml

@@ -4,12 +4,6 @@ inputs:
   editable:
     description: Whether to build pandas in editable mode (default true)
     default: true
-  meson_args:
-    description: Extra flags to pass to meson
-    required: false
-  cflags_adds:
-    description: Items to append to the CFLAGS variable
-    required: false
 runs:
   using: composite
   steps:
@@ -30,12 +24,11 @@ runs:
 
     - name: Build Pandas
       run: |
-        export CFLAGS="$CFLAGS ${{ inputs.cflags_adds }}"
         if [[ ${{ inputs.editable }} == "true" ]]; then
-          pip install -e . --no-build-isolation -v --no-deps ${{ inputs.meson_args }} \
+          pip install -e . --no-build-isolation -v --no-deps \
             --config-settings=setup-args="--werror"
         else
-          pip install . --no-build-isolation -v --no-deps ${{ inputs.meson_args }} \
+          pip install . --no-build-isolation -v --no-deps \
             --config-settings=setup-args="--werror"
         fi
       shell: bash -el {0}

.github/actions/run-tests/action.yml

@@ -7,14 +7,14 @@ runs:
       shell: bash -el {0}
 
     - name: Publish test results
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: Test results
         path: test-data.xml
       if: failure()
 
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v3
+      uses: codecov/codecov-action@v4
       with:
         flags: unittests
         name: codecov-pandas

.github/workflows/unit-tests.yml

@@ -74,9 +74,9 @@ jobs:
       PATTERN: ${{ matrix.pattern }}
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
-      PANDAS_CI: ${{ matrix.pandas_ci || '1' }}
+      PANDAS_CI: '1'
       TEST_ARGS: ${{ matrix.test_args || '' }}
-      PYTEST_WORKERS: ${{ matrix.pytest_workers || 'auto' }}
+      PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}
       NPY_PROMOTION_STATE: ${{ matrix.env_file == 'actions-311-numpydev.yaml' && 'weak' || 'legacy' }}
       # Clipboard tests
@@ -88,7 +88,7 @@ jobs:
 
     services:
       mysql:
-        image: mysql:8.0.33
+        image: mysql:8
         env:
           MYSQL_ALLOW_EMPTY_PASSWORD: yes
           MYSQL_DATABASE: pandas
@@ -101,7 +101,7 @@ jobs:
           - 3306:3306
 
       postgres:
-        image: postgres:13
+        image: postgres:16
         env:
           PGUSER: postgres
           POSTGRES_USER: postgres
@@ -116,7 +116,7 @@ jobs:
           - 5432:5432
 
       moto:
-        image: motoserver/moto:4.1.13
+        image: motoserver/moto:5.0.0
         env:
           AWS_ACCESS_KEY_ID: foobar_key
           AWS_SECRET_ACCESS_KEY: foobar_secret
@@ -148,9 +148,6 @@ jobs:
       uses: ./.github/actions/build_pandas
       # TODO: Re-enable once Pypy has Pypy 3.10 on conda-forge
       if: ${{ matrix.name != 'Pypy' }}
-      with:
-        meson_args: ${{ matrix.meson_args }}
-        cflags_adds: ${{ matrix.cflags_adds }}
 
     - name: Test (not single_cpu)
       uses: ./.github/actions/run-tests
@@ -302,7 +299,7 @@ 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 # Uncomment this to freeze the workflow, comment it to unfreeze
     defaults:
       run:
         shell: bash -eou pipefail {0}
@@ -317,7 +314,7 @@ jobs:
 
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-${{ matrix.pytest_target }}-dev
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-python-dev
       cancel-in-progress: true
 
     env:
@@ -334,7 +331,7 @@ jobs:
       - name: Set up Python Dev Version
         uses: actions/setup-python@v5
         with:
-          python-version: '3.12-dev'
+          python-version: '3.13-dev'
 
       - name: Build Environment
         run: |
@@ -349,6 +346,51 @@ jobs:
       - name: Run Tests
         uses: ./.github/actions/run-tests
 
+  python-freethreading:
+    defaults:
+      run:
+        shell: bash -eou pipefail {0}
+    runs-on: ubuntu-22.04
+
+    timeout-minutes: 90
+
+    concurrency:
+      # https://github.community/t/concurrecy-not-work-for-push/183068/7
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-python-freethreading-dev
+      cancel-in-progress: true
+
+    env:
+      PYTEST_WORKERS: "auto"
+      PANDAS_CI: 1
+      PATTERN: "not slow and not network and not clipboard and not single_cpu"
+      PYTEST_TARGET: pandas
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python Free-threading Version
+        uses: deadsnakes/[email protected]
+        with:
+          python-version: 3.13-dev
+          nogil: true
+
+      - name: Build Environment
+        run: |
+          python --version
+          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 -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
+
   emscripten:
     # Note: the Python version, Emscripten toolchain version are determined
     # by the Pyodide version. The appropriate versions can be found in the

.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]
@@ -67,12 +67,13 @@ repos:
     -   id: fix-encoding-pragma
         args: [--remove]
     -   id: trailing-whitespace
+        args: [--markdown-linebreak-ext=md]
 -   repo: https://github.com/PyCQA/isort
     rev: 5.13.2
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.15.2
+    rev: v3.16.0
     hooks:
     -   id: pyupgrade
         args: [--py310-plus]
@@ -92,7 +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/tslibs/timedelta.py

@@ -20,7 +20,7 @@ def time_from_int(self):
         Timedelta(123456789)
 
     def time_from_unit(self):
-        Timedelta(1, unit="d")
+        Timedelta(1, unit="D")
 
     def time_from_components(self):
         Timedelta(

asv_bench/benchmarks/tslibs/timestamp.py

@@ -1,7 +1,10 @@
-from datetime import datetime
+from datetime import (
+    datetime,
+    timezone,
+)
+import zoneinfo
 
 import numpy as np
-import pytz
 
 from pandas import Timestamp
 
@@ -12,7 +15,7 @@ class TimestampConstruction:
     def setup(self):
         self.npdatetime64 = np.datetime64("2020-01-01 00:00:00")
         self.dttime_unaware = datetime(2020, 1, 1, 0, 0, 0)
-        self.dttime_aware = datetime(2020, 1, 1, 0, 0, 0, 0, pytz.UTC)
+        self.dttime_aware = datetime(2020, 1, 1, 0, 0, 0, 0, timezone.utc)
         self.ts = Timestamp("2020-01-01 00:00:00")
 
     def time_parse_iso8601_no_tz(self):
@@ -113,7 +116,7 @@ def setup(self, tz):
         self.ts = Timestamp("2017-08-25 08:16:14", tz=tz)
 
     def time_replace_tz(self, tz):
-        self.ts.replace(tzinfo=pytz.timezone("US/Eastern"))
+        self.ts.replace(tzinfo=zoneinfo.ZoneInfo("US/Eastern"))
 
     def time_replace_None(self, tz):
         self.ts.replace(tzinfo=None)
@@ -144,8 +147,8 @@ def time_ceil(self, tz):
 
 class TimestampAcrossDst:
     def setup(self):
-        dt = datetime(2016, 3, 27, 1)
-        self.tzinfo = pytz.timezone("CET").localize(dt, is_dst=False).tzinfo
+        dt = datetime(2016, 3, 27, 1, fold=0)
+        self.tzinfo = dt.astimezone(zoneinfo.ZoneInfo("Europe/Berlin")).tzinfo
         self.ts2 = Timestamp(dt)
 
     def time_replace_across_dst(self):

asv_bench/benchmarks/tslibs/tslib.py

@@ -20,13 +20,13 @@
     timedelta,
     timezone,
 )
+import zoneinfo
 
 from dateutil.tz import (
     gettz,
     tzlocal,
 )
 import numpy as np
-import pytz
 
 try:
     from pandas._libs.tslibs import ints_to_pydatetime
@@ -38,7 +38,7 @@
     None,
     timezone.utc,
     timezone(timedelta(minutes=60)),
-    pytz.timezone("US/Pacific"),
+    zoneinfo.ZoneInfo("US/Pacific"),
     gettz("Asia/Tokyo"),
     tzlocal_obj,
 ]

asv_bench/benchmarks/tslibs/tz_convert.py

@@ -1,5 +1,6 @@
+from datetime import timezone
+
 import numpy as np
-from pytz import UTC
 
 from pandas._libs.tslibs.tzconversion import tz_localize_to_utc
 
@@ -41,7 +42,7 @@ def time_tz_convert_from_utc(self, size, tz):
         #  dti = DatetimeIndex(self.i8data, tz=tz)
         #  dti.tz_localize(None)
         if old_sig:
-            tz_convert_from_utc(self.i8data, UTC, tz)
+            tz_convert_from_utc(self.i8data, timezone.utc, tz)
         else:
             tz_convert_from_utc(self.i8data, tz)
 

ci/code_checks.sh

@@ -162,7 +162,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.ne SA01" \
         -i "pandas.Series.pad PR01,SA01" \
         -i "pandas.Series.plot PR02" \
-        -i "pandas.Series.pop RT03,SA01" \
+        -i "pandas.Series.pop SA01" \
         -i "pandas.Series.prod RT03" \
         -i "pandas.Series.product RT03" \
         -i "pandas.Series.reorder_levels RT03,SA01" \
@@ -231,7 +231,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.ctime SA01" \
         -i "pandas.Timestamp.date SA01" \
         -i "pandas.Timestamp.day GL08" \
-        -i "pandas.Timestamp.floor SA01" \
         -i "pandas.Timestamp.fold GL08" \
         -i "pandas.Timestamp.fromordinal SA01" \
         -i "pandas.Timestamp.fromtimestamp PR01,SA01" \
@@ -245,13 +244,11 @@ 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" \
@@ -261,7 +258,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.to_period PR01,SA01" \
         -i "pandas.Timestamp.today SA01" \
         -i "pandas.Timestamp.toordinal SA01" \
-        -i "pandas.Timestamp.tz SA01" \
         -i "pandas.Timestamp.tz_localize SA01" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.tzname SA01" \

ci/deps/actions-311-pyarrownightly.yaml

@@ -18,7 +18,7 @@ dependencies:
 
   # required dependencies
   - python-dateutil
-  - numpy
+  - numpy<2
   - pytz
   - pip