build: Rebase dev onto main

.github/workflows/dist.yaml

@@ -1,19 +1,37 @@
 name: dist-check
 
-on: [push, pull_request]
+on:
+  workflow_dispatch:
+
+  push:
+    branches:
+      - main
+      - develop
+    tags:
+      - "v*.*.*"
+
+  pull_request:
+    branches:
+      - main
+      - develop
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
 
 jobs:
   dist:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Setup Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.8
     - name: Build dist
       run: |
-        python setup.py sdist
+        pip install build
+        python -m build --sdist
     - name: Twine check
       run: |
         pip install twine

.github/workflows/docs.yaml

@@ -1,13 +1,30 @@
 name: Docs
-on: [pull_request, push]
+on:
+  workflow_dispatch:
+
+  push:
+    branches:
+      - main
+      - develop
+    tags:
+      - "v*.*.*"
+
+  pull_request:
+    branches:
+      - main
+      - develop
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
 
 jobs:
   build-and-deploy:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Setup Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.8
     - name: Install dependencies

.github/workflows/pre-commit.yaml

@@ -1,14 +1,31 @@
 name: pre-commit
 
-on: [push]
+on:
+  workflow_dispatch:
+
+  push:
+    branches:
+      - main
+      - develop
+    tags:
+      - "v*.*.*"
+
+  pull_request:
+    branches:
+      - main
+      - develop
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
 
 jobs:
   run-all-files:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Setup Python 3.8
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.8
     - name: Install pre-commit

.github/workflows/release_docker.yaml

@@ -1,11 +1,20 @@
 name: release-docker
 
 on:
+  workflow_dispatch:
   push:
     branches:
-      - 'main'
       - 'develop'
       - 'docker'
+    tags:
+      - 'v*'
+  pull_request:
+    branches:
+      - 'develop'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
 
 jobs:
 
@@ -15,34 +24,46 @@ jobs:
 
     steps:
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
 
       - name: Login to DockerHub
-        uses: docker/login-action@v2
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Check out the repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Extract metadata (tags, labels) for Docker Hub
         id: meta_dockerhub
-        uses: docker/metadata-action@v4
+        uses: docker/metadata-action@v5
         with:
           images: "openml/openml-python"
 
       - name: Build and push
         id: docker_build
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v5
         with:
           context: ./docker/
-          push: true
           tags: ${{ steps.meta_dockerhub.outputs.tags }}
           labels: ${{ steps.meta_dockerhub.outputs.labels }}
+          platforms: linux/amd64,linux/arm64
+          push: ${{ github.event_name == 'push' }}
+
+      - name: Update repo description
+        if: ${{ startsWith(github.ref, 'refs/tags/v') }}
+        uses: peter-evans/dockerhub-description@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          repository: openml/openml-python
+          short-description: "pre-installed openml-python environment"
+          readme-filepath: ./docker/readme.md
 
       - name: Image digest
         run: echo ${{ steps.docker_build.outputs.digest }}

.github/workflows/test.yml

@@ -1,69 +1,66 @@
 name: Tests
 
-on: [push, pull_request]
+on:
+  workflow_dispatch:
+
+  push:
+    branches:
+      - main
+      - develop
+    tags:
+      - "v*.*.*"
+
+  pull_request:
+    branches:
+      - main
+      - develop
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
 
 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]
+        python-version: ["3.8"]
+        # TODO(eddiebergman): We should consider testing against newer version I guess...
+        # We probably consider just having a `"1"` version to always test against latest
+        scikit-learn: ["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
+        sklearn-only: ["true"]
+        exclude:  # no scikit-learn 0.23 release for Python 3.9
+          - python-version: "3.9"
+            scikit-learn: "0.23.1"
         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
+          - os: ubuntu-latest
+            python-version: "3.9"
+            scikit-learn: "0.24"
+            scipy: "1.10.0"
+            sklearn-only: "true"
+          # Include a code cov version
+          - code-cov: true
+            os: ubuntu-latest
+            python-version: "3.8"
             scikit-learn: 0.23.1
-            code-cov: true
             sklearn-only: 'false'
-            os: ubuntu-latest
+          # Include a windows test, for some reason on a later version of scikit-learn
           - os: windows-latest
-            sklearn-only: 'false'
+            python-version: "3.8"
             scikit-learn: 0.24.*
-            scipy: 1.10.0
+            scipy: "1.10.0"  # not sure why the explicit scipy version?
+            sklearn-only: 'false'
       fail-fast:  false
-      max-parallel: 4
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
       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
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install test dependencies

.gitignore

@@ -17,6 +17,14 @@ doc/auto_examples/
 doc/modules/generated/
 doc/datasets/generated/
 
+# Some stuff from testing?
+tests/files/org/openml/test/datasets/1/
+tests/files/org/openml/test/datasets/2/features.xml.pkl
+tests/files/org/openml/test/datasets/2/qualities.xml.pkl
+tests/files/org/openml/test/locks/
+tests/files/org/openml/test/tasks/1/datasplits.pkl.py3
+tests/files/org/openml/test/tasks/1882/datasplits.pkl.py3
+
 # Distribution / packaging
 
 .Python