Merge pull request #1232 from openml/develop

Release 0.13.1

.flake8

@@ -5,7 +5,7 @@ select = C,E,F,W,B,T
 ignore = E203, E402, W503
 per-file-ignores =
     *__init__.py:F401
-    *cli.py:T001
+    *cli.py:T201
 exclude =
     venv
     examples

.github/dependabot.yml

@@ -0,0 +1,9 @@
+version: 2
+
+updates:
+  # This will check for updates to github actions every day
+  # https://docs.github.com/en/[email protected]/code-security/dependabot/working-with-dependabot/keeping-your-actions-up-to-date-with-dependabot
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"

.github/workflows/dist.yaml

@@ -6,9 +6,9 @@ jobs:
   dist:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Setup Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: 3.8
     - name: Build dist

.github/workflows/docs.yaml

@@ -5,14 +5,17 @@ jobs:
   build-and-deploy:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Setup Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: 3.8
     - name: Install dependencies
       run: |
         pip install -e .[docs,examples,examples_unix]
+        # dependency "fanova" does not work with numpy 1.24 or later
+        # https://github.com/automl/fanova/issues/108
+        pip install numpy==1.23.5
     - name: Make docs
       run: |
         cd doc

.github/workflows/pre-commit.yaml

@@ -6,9 +6,9 @@ jobs:
   run-all-files:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Setup Python 3.7
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: 3.7
     - name: Install pre-commit

.github/workflows/release_docker.yaml

@@ -3,29 +3,46 @@ name: release-docker
 on:
   push:
     branches:
+      - 'main'
       - 'develop'
       - 'docker'
 
 jobs:
+
   docker:
+
     runs-on: ubuntu-latest
+
     steps:
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
+        uses: docker/setup-qemu-action@v2
+
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
+        uses: docker/setup-buildx-action@v2
+
       - name: Login to DockerHub
-        uses: docker/login-action@v1
+        uses: docker/login-action@v2
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
-      - uses: actions/checkout@v2
+
+      - name: Check out the repo
+        uses: actions/checkout@v3
+
+      - name: Extract metadata (tags, labels) for Docker Hub
+        id: meta_dockerhub
+        uses: docker/metadata-action@v4
+        with:
+          images: "openml/openml-python"
+
       - name: Build and push
         id: docker_build
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v4
         with:
           context: ./docker/
           push: true
-          tags: openml/openml-python:latest
+          tags: ${{ steps.meta_dockerhub.outputs.tags }}
+          labels: ${{ steps.meta_dockerhub.outputs.labels }}
+
       - name: Image digest
         run: echo ${{ steps.docker_build.outputs.digest }}

.github/workflows/test.yml

@@ -0,0 +1,117 @@
+name: Tests
+
+on: [push, pull_request]
+
+jobs:
+  test:
+    name: (${{ matrix.os }}, Py${{ matrix.python-version }}, sk${{ matrix.scikit-learn }}, sk-only:${{ matrix.sklearn-only }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        python-version: [3.7, 3.8]
+        scikit-learn: [0.21.2, 0.22.2, 0.23.1, 0.24]
+        os: [ubuntu-latest]
+        sklearn-only: ['true']
+        exclude:  # no scikit-learn 0.21.2 release for Python 3.8
+          - python-version: 3.8
+            scikit-learn: 0.21.2
+        include:
+          - python-version: 3.6
+            scikit-learn: 0.18.2
+            scipy: 1.2.0
+            os: ubuntu-20.04 
+            sklearn-only: 'true'
+          - python-version: 3.6
+            scikit-learn: 0.19.2
+            os: ubuntu-20.04 
+            sklearn-only: 'true'
+          - python-version: 3.6
+            scikit-learn: 0.20.2
+            os: ubuntu-20.04 
+            sklearn-only: 'true'
+          - python-version: 3.6
+            scikit-learn: 0.21.2
+            os: ubuntu-20.04 
+            sklearn-only: 'true'
+          - python-version: 3.6
+            scikit-learn: 0.22.2
+            os: ubuntu-20.04 
+            sklearn-only: 'true'
+          - python-version: 3.6
+            scikit-learn: 0.23.1
+            os: ubuntu-20.04 
+            sklearn-only: 'true'
+          - python-version: 3.6
+            scikit-learn: 0.24
+            os: ubuntu-20.04 
+            sklearn-only: 'true'
+          - python-version: 3.8
+            scikit-learn: 0.23.1
+            code-cov: true
+            sklearn-only: 'false'
+            os: ubuntu-latest
+          - os: windows-latest
+            sklearn-only: 'false'
+            scikit-learn: 0.24.*
+      fail-fast:  false
+      max-parallel: 4
+
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+    - name: Setup Python ${{ matrix.python-version }}
+      if: matrix.os != 'windows-latest'  # windows-latest only uses preinstalled Python (3.7.9)
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install test dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -e .[test]
+    - name: Install scikit-learn ${{ matrix.scikit-learn }}
+      run: |
+        pip install scikit-learn==${{ matrix.scikit-learn }}
+    - name: Install numpy for Python 3.8
+      # Python 3.8 & scikit-learn<0.24 requires numpy<=1.23.5
+      if: ${{ matrix.python-version == '3.8' && contains(fromJSON('["0.23.1", "0.22.2", "0.21.2"]'), matrix.scikit-learn) }}
+      run: |
+        pip install numpy==1.23.5
+    - name: Install scipy ${{ matrix.scipy }}
+      if: ${{ matrix.scipy }}
+      run: |
+        pip install scipy==${{ matrix.scipy }}
+    - name: Store repository status
+      id: status-before
+      run: |
+        echo "::set-output name=BEFORE::$(git status --porcelain -b)"
+    - name: Run tests on Ubuntu
+      if: matrix.os == 'ubuntu-latest'
+      run: |
+        if [ ${{ matrix.code-cov }} ]; then codecov='--cov=openml --long  --cov-report=xml'; fi
+        # Most of the time, running only the scikit-learn tests is sufficient
+        if [ ${{ matrix.sklearn-only }} = 'true' ]; then sklearn='-m sklearn'; fi
+        echo pytest -n 4 --durations=20 --timeout=600 --timeout-method=thread --dist load -sv $codecov $sklearn --reruns 5 --reruns-delay 1 -o log_cli=true
+        pytest -n 4 --durations=20 --timeout=600 --timeout-method=thread --dist load -sv $codecov $sklearn --reruns 5 --reruns-delay 1 -o log_cli=true
+    - name: Run tests on Windows
+      if: matrix.os == 'windows-latest'
+      run: |  # we need a separate step because of the bash-specific if-statement in the previous one.
+        pytest -n 4 --durations=20 --timeout=600 --timeout-method=thread --dist load -sv --reruns 5 --reruns-delay 1
+    - name: Check for files left behind by test
+      if: matrix.os != 'windows-latest' && always()
+      run: |
+        before="${{ steps.status-before.outputs.BEFORE }}"
+        after="$(git status --porcelain -b)"
+        if [[ "$before" != "$after" ]]; then
+            echo "git status from before: $before"
+            echo "git status from after: $after"
+            echo "Not all generated files have been deleted!"
+            exit 1
+        fi
+    - name: Upload coverage
+      if: matrix.code-cov && always()
+      uses: codecov/codecov-action@v3
+      with:
+        files: coverage.xml
+        fail_ci_if_error: true
+        verbose: true

.gitignore

@@ -1,6 +1,8 @@
 *~
 doc/generated
 examples/.ipynb_checkpoints
+venv
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -75,6 +77,7 @@ target/
 # IDE
 .idea
 *.swp
+.vscode
 
 # MYPY
 .mypy_cache

.pre-commit-config.yaml

@@ -1,28 +1,34 @@
 repos:
   - repo: https://github.com/psf/black
-    rev: 19.10b0
+    rev: 22.6.0
     hooks:
       - id: black
         args: [--line-length=100]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.761
+    rev: v0.961
     hooks:
       - id: mypy
         name: mypy openml
-        files: openml/*
+        files: openml/.*
+        additional_dependencies:
+          - types-requests
+          - types-python-dateutil
       - id: mypy
         name: mypy tests
-        files: tests/*
-  - repo: https://gitlab.com/pycqa/flake8
-    rev: 3.8.3
+        files: tests/.*
+        additional_dependencies:
+          - types-requests
+          - types-python-dateutil
+  - repo: https://github.com/pycqa/flake8
+    rev: 4.0.1
     hooks:
       - id: flake8
         name: flake8 openml
-        files: openml/*
+        files: openml/.*
         additional_dependencies:
-          - flake8-print==3.1.4
+          - flake8-print==5.0.0
       - id: flake8
         name: flake8 tests
-        files: tests/*
+        files: tests/.*
         additional_dependencies:
-          - flake8-print==3.1.4
+          - flake8-print==5.0.0