Merge branch 'main' into new-deprecation-policy

Aloqeely · Jun 6, 2024 · 235c6fe · 235c6fe
2 parents c96551c + 0e90f66
commit 235c6fe
Show file tree

Hide file tree

Showing 177 changed files with 2,389 additions and 1,489 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -1,46 +1,64 @@
 version: 2.1
 
 jobs:
-  test-arm:
+  test-linux-arm:
     machine:
       image: default
     resource_class: arm.large
     environment:
-      ENV_FILE: ci/deps/circle-310-arm64.yaml
+      ENV_FILE: ci/deps/circle-311-arm64.yaml
       PYTEST_WORKERS: auto
       PATTERN: "not single_cpu and not slow and not network and not clipboard and not arm_slow and not db"
       PYTEST_TARGET: "pandas"
       PANDAS_CI: "1"
     steps:
       - checkout
-      - run: .circleci/setup_env.sh
-      - run: >
-          PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH
-          LD_PRELOAD=$HOME/miniconda3/envs/pandas-dev/lib/libgomp.so.1:$LD_PRELOAD
-          ci/run_tests.sh
-  linux-musl:
+      - run:
+          name: Install Environment and Run Tests
+          shell: /bin/bash -exuo pipefail
+          command: |
+            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
+            wget -q $MAMBA_URL -O minimamba.sh
+            chmod +x minimamba.sh
+            MAMBA_DIR="$HOME/miniconda3"
+            rm -rf $MAMBA_DIR
+            ./minimamba.sh -b -p $MAMBA_DIR
+            export PATH=$MAMBA_DIR/bin:$PATH
+            conda info -a
+            conda env create -q -n pandas-dev -f $ENV_FILE
+            conda list -n pandas-dev
+            source activate pandas-dev
+            if pip show pandas 1>/dev/null; then
+                pip uninstall -y pandas
+            fi
+            python -m pip install --no-build-isolation -ve . --config-settings=setup-args="--werror"
+            PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH
+            ci/run_tests.sh
+  test-linux-musl:
     docker:
       - image: quay.io/pypa/musllinux_1_1_aarch64
     resource_class: arm.large
     steps:
       # Install pkgs first to have git in the image
       # (needed for checkout)
-      - run: |
-          apk update
-          apk add git
-          apk add musl-locales
+      - run:
+          name: Install System Packages
+          command: |
+            apk update
+            apk add git
+            apk add musl-locales
       - checkout
-      - run: |
-          /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 --no-build-isolation -e . --config-settings=setup-args="--werror"
-          python -m pip list --no-cache-dir
-      - run: |
-          . ~/virtualenvs/pandas-dev/bin/activate
-          export PANDAS_CI=1
-          python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
+      - run:
+          name: Install Environment and Run Tests
+          command: |
+            /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 --no-build-isolation -e . --config-settings=setup-args="--werror"
+            python -m pip list --no-cache-dir
+            export PANDAS_CI=1
+            python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
   build-aarch64:
     parameters:
       cibw-build:
@@ -71,7 +89,7 @@ jobs:
           name: Build aarch64 wheels
           no_output_timeout: 30m # Sometimes the tests won't generate any output, make sure the job doesn't get killed by that
           command: |
-            pip3 install cibuildwheel==2.15.0
+            pip3 install cibuildwheel==2.18.1
             cibuildwheel --prerelease-pythons --output-dir wheelhouse
 
           environment:
@@ -81,7 +99,7 @@ jobs:
           name: Install Anaconda Client & Upload Wheels
           command: |
             echo "Install Mambaforge"
-            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/23.1.0-0/Mambaforge-23.1.0-0-Linux-aarch64.sh"
+            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
             echo "Downloading $MAMBA_URL"
             wget -q $MAMBA_URL -O minimamba.sh
             chmod +x minimamba.sh
@@ -107,14 +125,14 @@ workflows:
       not:
         equal: [ scheduled_pipeline, << pipeline.trigger_source >> ]
     jobs:
-      - test-arm
+      - test-linux-arm
   test-musl:
     # Don't run trigger this one when scheduled pipeline runs
     when:
       not:
         equal: [ scheduled_pipeline, << pipeline.trigger_source >> ]
     jobs:
-      - linux-musl
+      - test-linux-musl
   build-wheels:
     jobs:
       - build-aarch64:

diff --git a/.circleci/setup_env.sh b/.circleci/setup_env.sh
diff --git a/.github/workflows/wheels.yml b/.github/workflows/wheels.yml
@@ -140,7 +140,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/[email protected].0
+        uses: pypa/[email protected].1
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.3
+    rev: v0.4.7
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -40,7 +40,7 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.3.0
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown, cython, c]
@@ -92,7 +92,7 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v18.1.4
+    rev: v18.1.5
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

diff --git a/asv_bench/benchmarks/tslibs/fields.py b/asv_bench/benchmarks/tslibs/fields.py
@@ -19,10 +19,15 @@ class TimeGetTimedeltaField:
     def setup(self, size, field):
         arr = np.random.randint(0, 10, size=size, dtype="i8")
         self.i8data = arr
+        arr = np.random.randint(-86400 * 1_000_000_000, 0, size=size, dtype="i8")
+        self.i8data_negative = arr
 
     def time_get_timedelta_field(self, size, field):
         get_timedelta_field(self.i8data, field)
 
+    def time_get_timedelta_field_negative_td(self, size, field):
+        get_timedelta_field(self.i8data_negative, field)
+
 
 class TimeGetDateField:
     params = [
@@ -72,3 +77,6 @@ def setup(self, size, side, period, freqstr, month_kw):
 
     def time_get_start_end_field(self, size, side, period, freqstr, month_kw):
         get_start_end_field(self.i8data, self.attrname, freqstr, month_kw=month_kw)
+
+
+from ..pandas_vb_common import setup  # noqa: F401 isort:skip
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -74,39 +74,31 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.DataFrame.mean RT03,SA01" \
         -i "pandas.DataFrame.median RT03,SA01" \
         -i "pandas.DataFrame.min RT03" \
-        -i "pandas.DataFrame.plot PR02,SA01" \
+        -i "pandas.DataFrame.plot PR02" \
         -i "pandas.Grouper PR02" \
-        -i "pandas.MultiIndex PR01" \
         -i "pandas.MultiIndex.append PR07,SA01" \
         -i "pandas.MultiIndex.copy PR07,RT03,SA01" \
         -i "pandas.MultiIndex.drop PR07,RT03,SA01" \
-        -i "pandas.MultiIndex.dtypes SA01" \
         -i "pandas.MultiIndex.get_level_values SA01" \
         -i "pandas.MultiIndex.get_loc PR07" \
         -i "pandas.MultiIndex.get_loc_level PR07" \
-        -i "pandas.MultiIndex.levels SA01" \
         -i "pandas.MultiIndex.levshape SA01" \
         -i "pandas.MultiIndex.names SA01" \
         -i "pandas.MultiIndex.nlevels SA01" \
         -i "pandas.MultiIndex.remove_unused_levels RT03,SA01" \
         -i "pandas.MultiIndex.reorder_levels RT03,SA01" \
-        -i "pandas.MultiIndex.set_codes SA01" \
         -i "pandas.MultiIndex.set_levels RT03,SA01" \
         -i "pandas.MultiIndex.sortlevel PR07,SA01" \
         -i "pandas.MultiIndex.to_frame RT03" \
-        -i "pandas.MultiIndex.truncate SA01" \
         -i "pandas.NA SA01" \
         -i "pandas.NaT SA01" \
         -i "pandas.NamedAgg SA01" \
-        -i "pandas.Period SA01" \
         -i "pandas.Period.asfreq SA01" \
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.freqstr SA01" \
-        -i "pandas.Period.is_leap_year SA01" \
         -i "pandas.Period.month SA01" \
         -i "pandas.Period.now SA01" \
         -i "pandas.Period.ordinal GL08" \
-        -i "pandas.Period.quarter SA01" \
         -i "pandas.Period.strftime PR01,SA01" \
         -i "pandas.Period.to_timestamp SA01" \
         -i "pandas.Period.year SA01" \
@@ -172,7 +164,7 @@ 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,SA01" \
+        -i "pandas.Series.plot PR02" \
         -i "pandas.Series.pop RT03,SA01" \
         -i "pandas.Series.prod RT03" \
         -i "pandas.Series.product RT03" \
@@ -351,7 +343,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.arrays.NumpyExtensionArray SA01" \
         -i "pandas.arrays.SparseArray PR07,SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
-        -i "pandas.bdate_range RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.agg RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.aggregate RT03" \
@@ -367,7 +358,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.nth PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.ohlc SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.plot PR02,SA01" \
+        -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.prod SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.sum SA01" \
@@ -385,7 +376,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.min SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.ohlc SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.plot PR02,SA01" \
+        -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.prod SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.sum SA01" \
@@ -412,7 +403,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.window.rolling.Window.std PR01" \
         -i "pandas.core.window.rolling.Window.var PR01" \
         -i "pandas.date_range RT03" \
-        -i "pandas.describe_option SA01" \
         -i "pandas.errors.AbstractMethodError PR01,SA01" \
         -i "pandas.errors.AttributeConflictWarning SA01" \
         -i "pandas.errors.CSSWarning SA01" \
@@ -441,7 +431,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.UnsupportedFunctionCall SA01" \
         -i "pandas.errors.ValueLabelTypeMismatch SA01" \
         -i "pandas.infer_freq SA01" \
-        -i "pandas.interval_range RT03" \
         -i "pandas.io.formats.style.Styler.apply RT03" \
         -i "pandas.io.formats.style.Styler.apply_index RT03" \
         -i "pandas.io.formats.style.Styler.background_gradient RT03" \
@@ -478,32 +467,13 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.json_normalize RT03,SA01" \
         -i "pandas.merge PR07" \
         -i "pandas.merge_asof PR07,RT03" \
-        -i "pandas.merge_ordered PR07" \
-        -i "pandas.option_context SA01" \
         -i "pandas.period_range RT03,SA01" \
-        -i "pandas.pivot PR07" \
-        -i "pandas.pivot_table PR07" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
-        -i "pandas.plotting.autocorrelation_plot RT03,SA01" \
         -i "pandas.plotting.lag_plot RT03,SA01" \
-        -i "pandas.plotting.parallel_coordinates PR07,RT03,SA01" \
-        -i "pandas.plotting.plot_params SA01" \
         -i "pandas.plotting.scatter_matrix PR07,SA01" \
-        -i "pandas.plotting.table PR07,RT03,SA01" \
         -i "pandas.qcut PR07,SA01" \
-        -i "pandas.read_feather SA01" \
-        -i "pandas.read_orc SA01" \
-        -i "pandas.read_sas SA01" \
-        -i "pandas.read_spss SA01" \
-        -i "pandas.reset_option SA01" \
         -i "pandas.set_eng_float_format RT03,SA01" \
-        -i "pandas.set_option SA01" \
-        -i "pandas.show_versions SA01" \
-        -i "pandas.test SA01" \
         -i "pandas.testing.assert_extension_array_equal SA01" \
-        -i "pandas.testing.assert_index_equal PR07,SA01" \
-        -i "pandas.testing.assert_series_equal PR07,SA01" \
-        -i "pandas.timedelta_range SA01" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
         -i "pandas.tseries.offsets.BQuarterBegin PR02" \
         -i "pandas.tseries.offsets.BQuarterBegin.freqstr SA01" \
@@ -788,16 +758,13 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.YearBegin.nanos GL08" \
         -i "pandas.tseries.offsets.YearBegin.normalize GL08" \
         -i "pandas.tseries.offsets.YearBegin.rule_code GL08" \
-        -i "pandas.tseries.offsets.YearEnd PR02" \
         -i "pandas.tseries.offsets.YearEnd.freqstr SA01" \
         -i "pandas.tseries.offsets.YearEnd.is_on_offset GL08" \
         -i "pandas.tseries.offsets.YearEnd.month GL08" \
         -i "pandas.tseries.offsets.YearEnd.n GL08" \
         -i "pandas.tseries.offsets.YearEnd.nanos GL08" \
         -i "pandas.tseries.offsets.YearEnd.normalize GL08" \
         -i "pandas.tseries.offsets.YearEnd.rule_code GL08" \
-        -i "pandas.unique PR07" \
-        -i "pandas.util.hash_array PR07,SA01" \
         -i "pandas.util.hash_pandas_object PR07,SA01" # There should be no backslash in the final line, please keep this comment in the last ignored function
 
     RET=$(($RET + $?)) ; echo $MSG "DONE"

diff --git a/ci/deps/circle-310-arm64.yaml → ci/deps/circle-311-arm64.yaml b/ci/deps/circle-310-arm64.yaml → ci/deps/circle-311-arm64.yaml
@@ -2,7 +2,7 @@ name: pandas-dev
 channels:
   - conda-forge
 dependencies:
-  - python=3.10
+  - python=3.11
 
   # build dependencies
   - versioneer[toml]