Merge branch 'pandas-dev:main' into master

.circleci/config.yml

@@ -4,7 +4,7 @@ jobs:
   test-arm:
     machine:
       image: ubuntu-2004:202101-01
-    resource_class: arm.medium
+    resource_class: arm.large
     environment:
       ENV_FILE: ci/deps/circle-38-arm64.yaml
       PYTEST_WORKERS: auto
@@ -14,9 +14,82 @@ jobs:
     steps:
       - checkout
       - run: .circleci/setup_env.sh
-      - run: PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH ci/run_tests.sh
+      - run: >
+          PATH=$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
+  build-aarch64:
+    parameters:
+      cibw-build:
+        type: string
+    machine:
+      image: ubuntu-2004:202101-01
+    resource_class: arm.large
+    environment:
+      ENV_FILE: ci/deps/circle-38-arm64.yaml
+      TRIGGER_SOURCE: << pipeline.trigger_source >>
+    steps:
+      - checkout
+      - run:
+          name: Check if build is necessary
+          command: |
+            # Check if tag is defined or TRIGGER_SOURCE is scheduled
+            if [[ -n "$CIRCLE_TAG" ]]; then
+                echo 'export IS_PUSH="true"' >> "$BASH_ENV"
+            elif [[ $TRIGGER_SOURCE == "scheduled_pipeline" ]]; then
+                echo 'export IS_SCHEDULE_DISPATCH="true"' >> "$BASH_ENV"
+            # Look for the build label/[wheel build] in commit
+            # grep takes a regex, so need to escape brackets
+            elif (git log --format=oneline -n 1 $CIRCLE_SHA1) | grep -q '\[wheel build\]'; then
+                : # Do nothing
+            elif ! (curl https://api.github.com/repos/pandas-dev/pandas/issues/$CIRCLE_PR_NUMBER | jq '.labels' | grep -q 'Build'); then
+                circleci-agent step halt
+            fi
+      - run:
+          name: Build aarch64 wheels
+          command: |
+            pip3 install cibuildwheel==2.9.0
+            cibuildwheel --output-dir wheelhouse
+          environment:
+            CIBW_BUILD: << parameters.cibw-build >>
+
+      - run:
+          name: Install Anaconda Client & Upload Wheels
+          command: |
+            echo "Install Mambaforge"
+            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/4.14.0-0/Mambaforge-4.14.0-0-Linux-aarch64.sh"
+            echo "Downloading $MAMBA_URL"
+            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
+
+            mamba install -y -c conda-forge anaconda-client
+
+            source ci/upload_wheels.sh
+            set_upload_vars
+            upload_wheels
+      - store_artifacts:
+          path: wheelhouse/
 
 workflows:
   test:
+    # Don't run trigger this one when scheduled pipeline runs
+    when:
+      not:
+        equal: [ scheduled_pipeline, << pipeline.trigger_source >> ]
     jobs:
       - test-arm
+  build-wheels:
+    jobs:
+      - build-aarch64:
+          filters:
+            tags:
+              only: /^v.*/
+          matrix:
+            parameters:
+              cibw-build: ["cp38-manylinux_aarch64", "cp39-manylinux_aarch64", "cp310-manylinux_aarch64", "cp311-manylinux_aarch64"]

.circleci/setup_env.sh

@@ -1,47 +1,16 @@
 #!/bin/bash -e
 
-# edit the locale file if needed
-if [[ "$(uname)" == "Linux" && -n "$LC_ALL" ]]; then
-    echo "Adding locale to the first line of pandas/__init__.py"
-    rm -f pandas/__init__.pyc
-    SEDC="3iimport locale\nlocale.setlocale(locale.LC_ALL, '$LC_ALL')\n"
-    sed -i "$SEDC" pandas/__init__.py
-
-    echo "[head -4 pandas/__init__.py]"
-    head -4 pandas/__init__.py
-    echo
-fi
+echo "Install Mambaforge"
+MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/4.14.0-0/Mambaforge-4.14.0-0-Linux-aarch64.sh"
+echo "Downloading $MAMBA_URL"
+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
 
-MINICONDA_DIR=/usr/local/miniconda
-if [ -e $MINICONDA_DIR ] && [ "$BITS32" != yes ]; then
-    echo "Found Miniconda installation at $MINICONDA_DIR"
-else
-    echo "Install Miniconda"
-    DEFAULT_CONDA_URL="https://repo.continuum.io/miniconda/Miniconda3-latest"
-    if [[ "$(uname -m)" == 'aarch64' ]]; then
-        CONDA_URL="https://github.com/conda-forge/miniforge/releases/download/4.10.1-4/Miniforge3-4.10.1-4-Linux-aarch64.sh"
-    elif [[ "$(uname)" == 'Linux' ]]; then
-        if [[ "$BITS32" == "yes" ]]; then
-            CONDA_URL="$DEFAULT_CONDA_URL-Linux-x86.sh"
-        else
-            CONDA_URL="$DEFAULT_CONDA_URL-Linux-x86_64.sh"
-        fi
-    elif [[ "$(uname)" == 'Darwin' ]]; then
-        CONDA_URL="$DEFAULT_CONDA_URL-MacOSX-x86_64.sh"
-    else
-      echo "OS $(uname) not supported"
-      exit 1
-    fi
-    echo "Downloading $CONDA_URL"
-    wget -q $CONDA_URL -O miniconda.sh
-    chmod +x miniconda.sh
-
-    MINICONDA_DIR="$HOME/miniconda3"
-    rm -rf $MINICONDA_DIR
-    ./miniconda.sh -b -p $MINICONDA_DIR
-fi
-export PATH=$MINICONDA_DIR/bin:$PATH
+export PATH=$MAMBA_DIR/bin:$PATH
 
 echo
 echo "which conda"
@@ -51,7 +20,7 @@ echo
 echo "update conda"
 conda config --set ssl_verify false
 conda config --set quiet true --set always_yes true --set changeps1 false
-conda install -y -c conda-forge -n base 'mamba>=0.21.2' pip setuptools
+mamba install -y -c conda-forge -n base pip setuptools
 
 echo "conda info -a"
 conda info -a
@@ -70,11 +39,6 @@ time mamba env update -n pandas-dev --file="${ENV_FILE}"
 echo "conda list -n pandas-dev"
 conda list -n pandas-dev
 
-if [[ "$BITS32" == "yes" ]]; then
-    # activate 32-bit compiler
-    export CONDA_BUILD=1
-fi
-
 echo "activate pandas-dev"
 source activate pandas-dev
 
@@ -90,15 +54,9 @@ if pip list | grep -q ^pandas; then
     pip uninstall -y pandas || true
 fi
 
-if [ "$(conda list -f qt --json)" != [] ]; then
-    echo
-    echo "remove qt"
-    echo "causes problems with the clipboard, we use xsel for that"
-    conda remove qt -y --force || true
-fi
-
 echo "Build extensions"
-python setup.py build_ext -q -j3
+# GH 47305: Parallel build can causes flaky ImportError from pandas/_libs/tslibs
+python setup.py build_ext -q -j1
 
 echo "Install pandas"
 python -m pip install --no-build-isolation --no-use-pep517 -e .

.devcontainer.json

@@ -9,8 +9,7 @@
 	// You can edit these settings after create using File > Preferences > Settings > Remote.
 	"settings": {
 		"terminal.integrated.shell.linux": "/bin/bash",
-		"python.condaPath": "/opt/conda/bin/conda",
-		"python.pythonPath": "/opt/conda/bin/python",
+		"python.pythonPath": "/usr/local/bin/python",
 		"python.formatting.provider": "black",
 		"python.linting.enabled": true,
 		"python.linting.flake8Enabled": true,

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -17,7 +17,9 @@ body:
             [latest version](https://pandas.pydata.org/docs/whatsnew/index.html) of pandas.
           required: true
         - label: >
-            I have confirmed this bug exists on the main branch of pandas.
+            I have confirmed this bug exists on the
+            [main branch](https://pandas.pydata.org/docs/dev/getting_started/install.html#installing-the-development-version-of-pandas)
+            of pandas.
   - type: textarea
     id: example
     attributes:

.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -0,0 +1,72 @@
+name: Feature Request
+description: Suggest an idea for pandas
+title: "ENH: "
+labels: [Enhancement, Needs Triage]
+
+body:
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: Feature Type
+      description: Please check what type of feature request you would like to propose.
+      options:
+        - label: >
+            Adding new functionality to pandas
+        - label: >
+            Changing existing functionality in pandas
+        - label: >
+            Removing existing functionality in pandas
+  - type: textarea
+    id: description
+    attributes:
+      label: Problem Description
+      description: >
+        Please describe what problem the feature would solve, e.g. "I wish I could use pandas to ..."
+      placeholder: >
+        I wish I could use pandas to return a Series from a DataFrame when possible.
+    validations:
+      required: true
+  - type: textarea
+    id: feature
+    attributes:
+      label: Feature Description
+      description: >
+        Please describe how the new feature would be implemented, using psudocode if relevant.
+      placeholder: >
+        Add a new parameter to DataFrame, to_series, to return a Series if possible.
+
+        def __init__(self, ..., to_series: bool=False):
+            """
+            Parameters
+            ----------
+            ...
+
+            to_series : bool, default False
+                Return a Series if possible
+            """
+            if to_series:
+                return Series(data)
+    validations:
+      required: true
+  - type: textarea
+    id: alternative
+    attributes:
+      label: Alternative Solutions
+      description: >
+        Please describe any alternative solution (existing functionality, 3rd party package, etc.)
+        that would satisfy the feature request.
+      placeholder: >
+        Write a custom function to return a Series when possible.
+
+        def to_series(...)
+           result = pd.DataFrame(...)
+           ...
+    validations:
+      required: true
+  - type: textarea
+    id: context
+    attributes:
+      label: Additional Context
+      description: >
+        Please provide any relevant GitHub issues, code examples or references that help describe and support
+        the feature request.

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,4 +1,4 @@
-- [ ] closes #xxxx (Replace xxxx with the Github issue number)
+- [ ] closes #xxxx (Replace xxxx with the GitHub issue number)
 - [ ] [Tests added and passed](https://pandas.pydata.org/pandas-docs/dev/development/contributing_codebase.html#writing-tests) if fixing a bug or adding a new feature
 - [ ] All [code checks passed](https://pandas.pydata.org/pandas-docs/dev/development/contributing_codebase.html#pre-commit).
 - [ ] Added [type annotations](https://pandas.pydata.org/pandas-docs/dev/development/contributing_codebase.html#type-hints) to new arguments/methods/functions.

.github/workflows/32-bit-linux.yml

@@ -4,11 +4,13 @@ on:
   push:
     branches:
       - main
-      - 1.4.x
+      - 2.0.x
+      - 1.5.x
   pull_request:
     branches:
       - main
-      - 1.4.x
+      - 2.0.x
+      - 1.5.x
     paths-ignore:
       - "doc/**"
 
@@ -17,7 +19,7 @@ permissions:
 
 jobs:
   pytest:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -38,9 +40,11 @@ jobs:
           /opt/python/cp38-cp38/bin/python -m venv ~/virtualenvs/pandas-dev && \
           . ~/virtualenvs/pandas-dev/bin/activate && \
           python -m pip install --no-deps -U pip wheel 'setuptools<60.0.0' && \
-          pip install cython numpy python-dateutil pytz pytest pytest-xdist pytest-asyncio>=0.17 hypothesis && \
-          python setup.py build_ext -q -j2 && \
+          python -m pip install versioneer[toml] && \
+          python -m pip install cython numpy python-dateutil pytz pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17 hypothesis>=6.34.2 && \
+          python setup.py build_ext -q -j1 && \
           python -m pip install --no-build-isolation --no-use-pep517 -e . && \
+          python -m pip list && \
           export PANDAS_CI=1 && \
           pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml"
 
@@ -50,3 +54,7 @@ jobs:
           name: Test results
           path: test-data.xml
         if: failure()
+    concurrency:
+      # https://github.community/t/concurrecy-not-work-for-push/183068/7
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-32bit
+      cancel-in-progress: true

.github/workflows/assign.yml

@@ -11,7 +11,7 @@ jobs:
     permissions:
       issues: write
       pull-requests: write
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
     - if: github.event.comment.body == 'take'
       run: |

.github/workflows/asv-bot.yml

@@ -21,7 +21,7 @@ jobs:
     name: "Run benchmarks"
     # TODO: Support more benchmarking options later, against different branches, against self, etc
     if: startsWith(github.event.comment.body, '@github-actions benchmark')
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     defaults:
       run:
         shell: bash -el {0}