perf: Use two-pass algorithm for csv to ensure correctness and SIMDiz… #20233
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Test Python | |
| on: | |
| pull_request: | |
| paths: | |
| - Cargo.lock | |
| - py-polars/** | |
| - docs/source/src/python/** | |
| - crates/** | |
| - .github/workflows/test-python.yml | |
| push: | |
| branches: | |
| - main | |
| paths: | |
| - Cargo.lock | |
| - crates/** | |
| - docs/source/src/python/** | |
| - py-polars/** | |
| - .github/workflows/test-python.yml | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| env: | |
| RUSTFLAGS: -C debuginfo=0 # Do not produce debug symbols to keep memory usage down | |
| RUST_BACKTRACE: 1 | |
| PYTHONUTF8: 1 | |
| defaults: | |
| run: | |
| working-directory: py-polars | |
| shell: bash | |
| jobs: | |
| test-python: | |
| runs-on: ${{ matrix.os }} | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| os: [ubuntu-latest] | |
| python-version: ['3.9', '3.12'] | |
| include: | |
| - os: windows-latest | |
| python-version: '3.12' | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Set up Graphviz | |
| uses: ts-graphviz/setup-graphviz@v2 | |
| - name: Create virtual environment | |
| env: | |
| BIN: ${{ matrix.os == 'windows-latest' && 'Scripts' || 'bin' }} | |
| run: | | |
| python -m venv .venv | |
| echo "$GITHUB_WORKSPACE/py-polars/.venv/$BIN" >> $GITHUB_PATH | |
| echo "VIRTUAL_ENV=$GITHUB_WORKSPACE/py-polars/.venv" >> $GITHUB_ENV | |
| - name: Install Python dependencies | |
| run: | | |
| pip install uv | |
| # Install typing-extensions separately whilst the `--extra-index-url` in `requirements-ci.txt` | |
| # doesn't have an up-to-date typing-extensions, see | |
| # https://github.com/astral-sh/uv/issues/6028#issuecomment-2287232150 | |
| uv pip install -U typing-extensions | |
| uv pip install --compile-bytecode -r requirements-dev.txt -r requirements-ci.txt --verbose | |
| - name: Set up Rust | |
| run: rustup show | |
| - name: Cache Rust | |
| uses: Swatinem/rust-cache@v2 | |
| with: | |
| workspaces: py-polars | |
| save-if: ${{ github.ref_name == 'main' }} | |
| - name: Install Polars | |
| run: maturin develop --features new_streaming | |
| - name: Run doctests | |
| if: github.ref_name != 'main' && matrix.python-version == '3.12' && matrix.os == 'ubuntu-latest' | |
| run: | | |
| python tests/docs/run_doctest.py | |
| pytest tests/docs/test_user_guide.py -m docs | |
| - name: Run tests | |
| if: github.ref_name != 'main' | |
| run: pytest -n auto --dist loadgroup -m "not release and not benchmark and not docs" | |
| - name: Run tests with new streaming engine | |
| if: github.ref_name != 'main' | |
| env: | |
| POLARS_AUTO_NEW_STREAMING: 1 | |
| run: pytest -n auto --dist loadgroup -m "not may_fail_auto_streaming and not slow and not write_disk and not release and not docs and not hypothesis and not benchmark and not ci_only" | |
| - name: Run tests async reader tests | |
| if: github.ref_name != 'main' && matrix.os != 'windows-latest' | |
| env: | |
| POLARS_FORCE_ASYNC: 1 | |
| run: pytest -m "not release and not benchmark and not docs" tests/unit/io/ | |
| - name: Check import without optional dependencies | |
| if: github.ref_name != 'main' && matrix.python-version == '3.12' && matrix.os == 'ubuntu-latest' | |
| run: | | |
| declare -a deps=("pandas" | |
| "pyarrow" | |
| "fsspec" | |
| "matplotlib" | |
| "backports.zoneinfo" | |
| "connectorx" | |
| "pyiceberg" | |
| "deltalake" | |
| "xlsx2csv" | |
| ) | |
| for d in "${deps[@]}" | |
| do | |
| echo "uninstall $i and check imports..." | |
| pip uninstall "$d" -y | |
| python -c 'import polars' | |
| done |