azure-pipelines.yml

# Adapted from https://github.com/pandas-dev/pandas/blob/master/azure-pipelines.yml
schedules:
- cron: "30 2 * * *"
  displayName: Run nightly build
  branches:
    include:
    - main
  always: true

jobs:
- job: git_commit
  displayName: Get Git Commit
  pool:
    vmImage: ubuntu-20.04
  steps:
    - bash: python build_tools/azure/get_commit_message.py
      name: commit
      displayName: Get source version message

- job: linting
  dependsOn: [git_commit]
  condition: |
    and(
      succeeded(),
      not(contains(dependencies['git_commit']['outputs']['commit.message'], '[lint skip]')),
      not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]'))
    )
  displayName: Linting
  pool:
    vmImage: ubuntu-20.04
  steps:
    - task: UsePythonVersion@0
      inputs:
        versionSpec: '3.9'
    - bash: |
        source build_tools/shared.sh
        # Include pytest compatibility with mypy
        pip install pytest ruff $(get_dep mypy min) $(get_dep black min) cython-lint
      displayName: Install linters
    - bash: |
        ./build_tools/linting.sh
      displayName: Run linters

- template: build_tools/azure/posix.yml
  parameters:
    name: Linux_Nightly
    vmImage: ubuntu-20.04
    dependsOn: [git_commit, linting]
    condition: |
      and(
        succeeded(),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]')),
        or(eq(variables['Build.Reason'], 'Schedule'),
           contains(dependencies['git_commit']['outputs']['commit.message'], '[scipy-dev]'
          )
        )
      )
    matrix:
      pylatest_pip_scipy_dev:
        DISTRIB: 'conda-pip-scipy-dev'
        LOCK_FILE: './build_tools/azure/pylatest_pip_scipy_dev_linux-64_conda.lock'
        SKLEARN_WARNINGS_AS_ERRORS: '1'
        CHECK_PYTEST_SOFT_DEPENDENCY: 'true'
        # Tests that require large downloads over the networks are skipped in CI.
        # Here we make sure, that they are still run on a regular basis.
        SKLEARN_SKIP_NETWORK_TESTS: '0'

- template: build_tools/azure/posix-docker.yml
  # Experimental CPython branch without the Global Interpreter Lock:
  # https://github.com/colesbury/nogil/
  #
  # The nogil build relies on a dedicated PyPI-style index to install patched
  # versions of NumPy, SciPy and Cython maintained by @colesbury and that
  # include specific fixes to make them run correctly without relying on the GIL.
  #
  # The goal of this CI entry is to make sure that we do not introduce any
  # dependency on the GIL in scikit-learn itself. An auxiliary goal is to early
  # detect any regression in the patched build dependencies to report them
  # upstream. The long-term goal is to be able to stop having to maintain
  # multiprocessing based workaround / hacks in joblib / loky to make multi-CPU
  # computing in scikit-learn efficient by default using regular threads.
  #
  # If this experimental entry becomes too unstable, feel free to disable it.
  parameters:
    name: Linux_nogil
    vmImage: ubuntu-20.04
    dependsOn: [git_commit, linting]
    condition: |
      and(
        succeeded(),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]')),
        or(eq(variables['Build.Reason'], 'Schedule'),
           contains(dependencies['git_commit']['outputs']['commit.message'], '[nogil]'
          )
        )
      )
    matrix:
      pylatest_pip_nogil:
        DOCKER_CONTAINER: 'nogil/python'
        DISTRIB: 'pip-nogil'
        LOCK_FILE: './build_tools/azure/python_nogil_lock.txt'
        COVERAGE: 'false'

- template: build_tools/azure/posix-docker.yml
  parameters:
    name: Linux_Nightly_PyPy
    vmImage: ubuntu-20.04
    dependsOn: [linting, git_commit]
    condition: |
      and(
        succeeded(),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]')),
        or(
          eq(variables['Build.Reason'], 'Schedule'),
          contains(dependencies['git_commit']['outputs']['commit.message'], '[pypy]')
        )
      )
    matrix:
      pypy3:
        DOCKER_CONTAINER: 'condaforge/miniforge3:4.10.3-5'
        DISTRIB: 'conda-pypy3'
        LOCK_FILE: './build_tools/azure/pypy3_linux-64_conda.lock'


- job: Linux_Nightly_Pyodide
  pool:
    vmImage: ubuntu-22.04
  variables:
    # Need to match Python version and Emscripten version for the correct
    # Pyodide version. For example, for Pyodide version 0.24.1, see
    # https://github.com/pyodide/pyodide/blob/0.24.1/Makefile.envs
    PYODIDE_VERSION: '0.24.1'
    EMSCRIPTEN_VERSION: '3.1.45'
    PYTHON_VERSION: '3.11.3'

  dependsOn: [git_commit, linting]
  condition: |
    and(
      succeeded(),
      not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]')),
      or(eq(variables['Build.Reason'], 'Schedule'),
         contains(dependencies['git_commit']['outputs']['commit.message'], '[pyodide]'
        )
      )
    )
  steps:
    - task: UsePythonVersion@0
      inputs:
        versionSpec: $(PYTHON_VERSION)
        addToPath: true

    - bash: bash build_tools/azure/install_pyodide.sh
      displayName: Build Pyodide wheel

    - bash: bash build_tools/azure/test_script_pyodide.sh
      displayName: Test Pyodide wheel

# Will run all the time regardless of linting outcome.
- template: build_tools/azure/posix.yml
  parameters:
    name: Linux_Runs
    vmImage: ubuntu-20.04
    dependsOn: [git_commit]
    condition: |
      and(
        succeeded(),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]'))
      )
    matrix:
      pylatest_conda_forge_mkl:
        DISTRIB: 'conda'
        LOCK_FILE: './build_tools/azure/pylatest_conda_forge_mkl_linux-64_conda.lock'
        COVERAGE: 'true'
        BUILD_WITH_MESON: 'true'
        SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '42'  # default global random seed

# Check compilation with Ubuntu 22.04 LTS (Jammy Jellyfish) and scipy from conda-forge
# By default the CI is sequential, where `Ubuntu_Jammy_Jellyfish` runs first and
# the others jobs are run only if `Ubuntu_Jammy_Jellyfish` succeeds.
# When "[azure parallel]" is in the commit message, `Ubuntu_Jammy_Jellyfish` will
# run in parallel with the rest of the jobs. On Azure, the job's name will be
# `Ubuntu_Jammy_Jellyfish_Parallel`.
- template: build_tools/azure/posix-all-parallel.yml
  parameters:
    name: Ubuntu_Jammy_Jellyfish
    vmImage: ubuntu-22.04
    dependsOn: [git_commit, linting]
    condition: |
      and(
        succeeded(),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]'))
      )
    commitMessage: dependencies['git_commit']['outputs']['commit.message']
    matrix:
      pymin_conda_forge_openblas_ubuntu_2204:
        DISTRIB: 'conda'
        LOCK_FILE: './build_tools/azure/pymin_conda_forge_openblas_ubuntu_2204_linux-64_conda.lock'
        SKLEARN_WARNINGS_AS_ERRORS: '1'
        COVERAGE: 'false'
        SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '0'  # non-default seed

- template: build_tools/azure/posix.yml
  parameters:
    name: Ubuntu_Atlas
    vmImage: ubuntu-22.04
    dependsOn: [linting, git_commit, Ubuntu_Jammy_Jellyfish]
    # Runs when dependencies succeeded or skipped
    condition: |
      and(
        not(or(failed(), canceled())),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]'))
      )
    matrix:
      # Linux environment to test that scikit-learn can be built against
      # versions of numpy, scipy with ATLAS that comes with Ubuntu Jammy Jellyfish 22.04
      # i.e. numpy 1.21.5 and scipy 1.8.0
      ubuntu_atlas:
        DISTRIB: 'ubuntu'
        LOCK_FILE: './build_tools/azure/ubuntu_atlas_lock.txt'
        COVERAGE: 'false'
        SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '1'  # non-default seed

- template: build_tools/azure/posix.yml
  parameters:
    name: Linux
    vmImage: ubuntu-20.04
    dependsOn: [linting, git_commit, Ubuntu_Jammy_Jellyfish]
    # Runs when dependencies succeeded or skipped
    condition: |
      and(
        not(or(failed(), canceled())),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]'))
      )
    matrix:
      # Linux + Python 3.9 build with OpenBLAS and without pandas
      pymin_conda_defaults_openblas:
        DISTRIB: 'conda'
        LOCK_FILE: './build_tools/azure/pymin_conda_defaults_openblas_linux-64_conda.lock'
        # Enable debug Cython directives to capture IndexError exceptions in
        # combination with the -Werror::pytest.PytestUnraisableExceptionWarning
        # flag for pytest.
        # https://github.com/scikit-learn/scikit-learn/pull/24438
        SKLEARN_ENABLE_DEBUG_CYTHON_DIRECTIVES: '1'
        SKLEARN_RUN_FLOAT32_TESTS: '1'
        SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '2'  # non-default seed
      # Linux environment to test the latest available dependencies.
      # It runs tests requiring lightgbm, pandas and PyAMG.
      pylatest_pip_openblas_pandas:
        DISTRIB: 'conda-pip-latest'
        LOCK_FILE: './build_tools/azure/pylatest_pip_openblas_pandas_linux-64_conda.lock'
        CHECK_PYTEST_SOFT_DEPENDENCY: 'true'
        SKLEARN_WARNINGS_AS_ERRORS: '1'
        SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '3'  # non-default seed
        # disable pytest-xdist to have 1 job where OpenMP and BLAS are not single
        # threaded because by default the tests configuration (sklearn/conftest.py)
        # makes sure that they are single threaded in each xdist subprocess.
        PYTEST_XDIST_VERSION: 'none'

- template: build_tools/azure/posix-docker.yml
  parameters:
    name: Linux_Docker
    vmImage: ubuntu-20.04
    dependsOn: [linting, git_commit, Ubuntu_Jammy_Jellyfish]
    # Runs when dependencies succeeded or skipped
    condition: |
      and(
        not(or(failed(), canceled())),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]'))
      )
    matrix:
      debian_atlas_32bit:
        DOCKER_CONTAINER: 'i386/debian:11.2'
        DISTRIB: 'debian-32'
        COVERAGE: "true"
        LOCK_FILE: './build_tools/azure/debian_atlas_32bit_lock.txt'
        # disable pytest xdist due to unknown bug with 32-bit container
        PYTEST_XDIST_VERSION: 'none'
        SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '4'  # non-default seed

- template: build_tools/azure/posix.yml
  parameters:
    name: macOS
    vmImage: macOS-11
    dependsOn: [linting, git_commit, Ubuntu_Jammy_Jellyfish]
    # Runs when dependencies succeeded or skipped
    condition: |
      and(
        not(or(failed(), canceled())),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]'))
      )
    matrix:
      pylatest_conda_forge_mkl:
        DISTRIB: 'conda'
        LOCK_FILE: './build_tools/azure/pylatest_conda_forge_mkl_osx-64_conda.lock'
        SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '5'  # non-default seed
      pylatest_conda_mkl_no_openmp:
        DISTRIB: 'conda'
        LOCK_FILE: './build_tools/azure/pylatest_conda_mkl_no_openmp_osx-64_conda.lock'
        SKLEARN_TEST_NO_OPENMP: 'true'
        SKLEARN_SKIP_OPENMP_TEST: 'true'
        SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '6'  # non-default seed

- template: build_tools/azure/windows.yml
  parameters:
    name: Windows
    vmImage: windows-latest
    dependsOn: [linting, git_commit, Ubuntu_Jammy_Jellyfish]
    # Runs when dependencies succeeded or skipped
    condition: |
      and(
        not(or(failed(), canceled())),
        not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]'))
      )
    matrix:
      pymin_conda_forge_mkl:
        DISTRIB: 'conda'
        LOCK_FILE: ./build_tools/azure/pymin_conda_forge_mkl_win-64_conda.lock
        SKLEARN_WARNINGS_AS_ERRORS: '1'
        # The Azure Windows runner is typically much slower than other CI
        # runners due to the lack of compiler cache. Running the tests with
        # coverage enabled make them run extra slower. Since very few parts of
        # code should have windows-specific code branches, it should be enable
        # to restrict the code coverage collection to the non-windows runners.
        COVERAGE: 'false'
        # Enable debug Cython directives to capture IndexError exceptions in
        # combination with the -Werror::pytest.PytestUnraisableExceptionWarning
        # flag for pytest.
        # https://github.com/scikit-learn/scikit-learn/pull/24438
        SKLEARN_ENABLE_DEBUG_CYTHON_DIRECTIVES: '1'
        SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '7'  # non-default seed