Merge branch 'main' into tst-str-2

Author: jbrockmendel

.circleci/config.yml

@@ -56,7 +56,7 @@ 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>=3.4.0 hypothesis>=6.84.0
+            python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil 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

.devcontainer.json

@@ -8,7 +8,6 @@
 	// Use 'settings' to set *default* container specific settings.json values on container create.
 	// You can edit these settings after create using File > Preferences > Settings > Remote.
 	"settings": {
-		"terminal.integrated.shell.linux": "/bin/bash",
 		"python.pythonPath": "/usr/local/bin/python",
 		"python.formatting.provider": "black",
 		"python.linting.enabled": true,

.github/actions/setup-conda/action.yml

@@ -14,3 +14,9 @@ runs:
         condarc-file: ci/.condarc
         cache-environment: true
         cache-downloads: true
+
+    - name: Uninstall pyarrow
+      if: ${{ env.REMOVE_PYARROW == '1' }}
+      run: |
+        micromamba remove -y pyarrow
+      shell: bash -el {0}

.github/workflows/unit-tests.yml

@@ -29,6 +29,7 @@ jobs:
         env_file: [actions-310.yaml, actions-311.yaml, actions-312.yaml]
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
+        pandas_future_infer_string: ["0"]
         include:
           - name: "Downstream Compat"
             env_file: actions-311-downstream_compat.yaml
@@ -58,6 +59,9 @@ jobs:
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "zh_CN"
           - name: "Future infer strings"
+            env_file: actions-312.yaml
+            pandas_future_infer_string: "1"
+          - name: "Future infer strings (without pyarrow)"
             env_file: actions-311.yaml
             pandas_future_infer_string: "1"
           - name: "Pypy"
@@ -85,9 +89,10 @@ jobs:
       NPY_PROMOTION_STATE: ${{ matrix.env_file == 'actions-311-numpydev.yaml' && 'weak' || 'legacy' }}
       # Clipboard tests
       QT_QPA_PLATFORM: offscreen
+      REMOVE_PYARROW: ${{ matrix.name == 'Future infer strings (without pyarrow)' && '1' || '0' }}
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_future_infer_string }}
       cancel-in-progress: true
 
     services:
@@ -231,7 +236,7 @@ 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>=3.4.0 hypothesis>=6.84.0
+          python -m pip install --no-cache-dir versioneer[toml] cython python-dateutil 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
@@ -269,7 +274,7 @@ 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>=3.4.0 hypothesis>=6.84.0
+          python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil 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
 
@@ -290,7 +295,7 @@ jobs:
     # In general, this will remain frozen(present, but not running) until:
     #    - The next unreleased Python version has released beta 1
     #      - This version should be available on GitHub Actions.
-    #    - Our required build/runtime dependencies(numpy, pytz, Cython, python-dateutil)
+    #    - Our required build/runtime dependencies(numpy, Cython, python-dateutil)
     #      support that unreleased Python version.
     #    To unfreeze, comment out the ``if: false`` condition, and make sure you update
     #    the name of the workflow and Python version in actions/setup-python ``python-version:``
@@ -343,7 +348,7 @@ 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>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
+          python -m pip install python-dateutil 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
 

.gitpod.yml

@@ -14,7 +14,7 @@ tasks:
       cp gitpod/settings.json .vscode/settings.json
       git fetch --tags
       python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true
-      pre-commit install
+      pre-commit install --install-hooks
     command: |
       python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true
       echo "✨ Pre-build complete! You can close this terminal ✨ "

Dockerfile

@@ -2,7 +2,7 @@ FROM python:3.10.8
 WORKDIR /home/pandas
 
 RUN apt-get update && apt-get -y upgrade
-RUN apt-get install -y build-essential
+RUN apt-get install -y build-essential bash-completion
 
 # hdf5 needed for pytables installation
 # libgles2-mesa needed for pytest-qt
@@ -12,4 +12,6 @@ RUN python -m pip install --upgrade pip
 COPY requirements-dev.txt /tmp
 RUN python -m pip install -r /tmp/requirements-dev.txt
 RUN git config --global --add safe.directory /home/pandas
+
+ENV SHELL "/bin/bash"
 CMD ["/bin/bash"]

ci/code_checks.sh

@@ -70,7 +70,6 @@ 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.MultiIndex.get_loc_level PR07" \
         -i "pandas.MultiIndex.names SA01" \
         -i "pandas.MultiIndex.reorder_levels RT03,SA01" \
         -i "pandas.MultiIndex.sortlevel PR07,SA01" \
@@ -159,28 +158,15 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.sparse.sp_values SA01" \
         -i "pandas.Series.sparse.to_coo PR07,RT03,SA01" \
         -i "pandas.Series.std PR01,RT03,SA01" \
-        -i "pandas.Series.str.capitalize RT03" \
-        -i "pandas.Series.str.casefold RT03" \
-        -i "pandas.Series.str.center RT03,SA01" \
-        -i "pandas.Series.str.decode PR07,RT03,SA01" \
-        -i "pandas.Series.str.encode PR07,RT03,SA01" \
-        -i "pandas.Series.str.index RT03" \
-        -i "pandas.Series.str.ljust RT03,SA01" \
-        -i "pandas.Series.str.lower RT03" \
         -i "pandas.Series.str.lstrip RT03" \
         -i "pandas.Series.str.match RT03" \
         -i "pandas.Series.str.normalize RT03,SA01" \
         -i "pandas.Series.str.partition RT03" \
         -i "pandas.Series.str.repeat SA01" \
         -i "pandas.Series.str.replace SA01" \
-        -i "pandas.Series.str.rindex RT03" \
-        -i "pandas.Series.str.rjust RT03,SA01" \
         -i "pandas.Series.str.rpartition RT03" \
         -i "pandas.Series.str.rstrip RT03" \
         -i "pandas.Series.str.strip RT03" \
-        -i "pandas.Series.str.swapcase RT03" \
-        -i "pandas.Series.str.title RT03" \
-        -i "pandas.Series.str.upper RT03" \
         -i "pandas.Series.str.wrap RT03,SA01" \
         -i "pandas.Series.str.zfill RT03" \
         -i "pandas.Series.struct.dtypes SA01" \
@@ -234,11 +220,8 @@ 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_localize SA01" \
         -i "pandas.Timestamp.tzinfo GL08" \
-        -i "pandas.Timestamp.tzname SA01" \
         -i "pandas.Timestamp.unit SA01" \
-        -i "pandas.Timestamp.utcfromtimestamp PR01,SA01" \
         -i "pandas.Timestamp.utcoffset SA01" \
         -i "pandas.Timestamp.utctimetuple SA01" \
         -i "pandas.Timestamp.value GL08" \
@@ -284,12 +267,9 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.types.is_iterator PR07,SA01" \
         -i "pandas.api.types.is_list_like SA01" \
         -i "pandas.api.types.is_named_tuple PR07,SA01" \
-        -i "pandas.api.types.is_numeric_dtype SA01" \
         -i "pandas.api.types.is_object_dtype SA01" \
-        -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_timedelta64_ns_dtype SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.BooleanArray SA01" \

ci/deps/actions-310-minimum_versions.yaml

@@ -23,7 +23,6 @@ dependencies:
   # required dependencies
   - python-dateutil=2.8.2
   - numpy=1.23.5
-  - pytz=2020.1
 
   # optional dependencies
   - beautifulsoup4=4.11.2
@@ -49,6 +48,7 @@ dependencies:
   - pyreadstat=1.2.0
   - pytables=3.8.0
   - python-calamine=0.1.7
+  - pytz=2023.4
   - pyxlsb=1.0.10
   - s3fs=2022.11.0
   - scipy=1.10.0

ci/deps/actions-310.yaml

@@ -21,7 +21,6 @@ dependencies:
   # required dependencies
   - python-dateutil
   - numpy
-  - pytz
 
   # optional dependencies
   - beautifulsoup4>=4.11.2
@@ -47,6 +46,7 @@ dependencies:
   - pyreadstat>=1.2.0
   - pytables>=3.8.0
   - python-calamine>=0.1.7
+  - pytz>=2023.4
   - pyxlsb>=1.0.10
   - s3fs>=2022.11.0
   - scipy>=1.10.0

ci/deps/actions-311-downstream_compat.yaml

@@ -22,7 +22,6 @@ dependencies:
   # required dependencies
   - python-dateutil
   - numpy
-  - pytz
 
   # optional dependencies
   - beautifulsoup4>=4.11.2
@@ -48,6 +47,7 @@ dependencies:
   - pyreadstat>=1.2.0
   - pytables>=3.8.0
   - python-calamine>=0.1.7
+  - pytz>=2023.4
   - pyxlsb>=1.0.10
   - s3fs>=2022.11.0
   - scipy>=1.10.0