Specify the units for Mutual Information scores

.circleci/config.yml

@@ -3,19 +3,22 @@ version: 2
 jobs:
   doc-min-dependencies:
     docker:
-      - image: circleci/python:3.7.3-stretch
+      - image: circleci/python:3.7.7-buster
     environment:
       - OMP_NUM_THREADS: 2
       - MKL_NUM_THREADS: 2
       - CONDA_ENV_NAME: testenv
-      - PYTHON_VERSION: 3.6
+      - PYTHON_VERSION: 3.7
       - NUMPY_VERSION: 'min'
       - SCIPY_VERSION: 'min'
       - MATPLOTLIB_VERSION: 'min'
       - CYTHON_VERSION: 'min'
       - SCIKIT_IMAGE_VERSION: 'min'
       - SPHINX_VERSION: 'min'
       - PANDAS_VERSION: 'min'
+      - SPHINX_GALLERY_VERSION: 'min'
+      - NUMPYDOC_VERSION: 'min'
+      - SPHINX_PROMPT_VERSION: 'min'
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh
@@ -44,7 +47,7 @@ jobs:
 
   doc:
     docker:
-      - image: circleci/python:3.7.3-stretch
+      - image: circleci/python:3.7.7-buster
     environment:
       - OMP_NUM_THREADS: 2
       - MKL_NUM_THREADS: 2
@@ -57,6 +60,9 @@ jobs:
       - SCIKIT_IMAGE_VERSION: 'latest'
       - SPHINX_VERSION: 'min'
       - PANDAS_VERSION: 'latest'
+      - SPHINX_GALLERY_VERSION: 'latest'
+      - NUMPYDOC_VERSION: 'latest'
+      - SPHINX_PROMPT_VERSION: 'latest'
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh
@@ -90,7 +96,7 @@ jobs:
 
   lint:
     docker:
-      - image: circleci/python:3.6
+      - image: circleci/python:3.7
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh
@@ -104,6 +110,9 @@ jobs:
   pypy3:
     docker:
       - image: condaforge/miniforge3
+    environment:
+      # Avoid the interactive dialog when installing tzdata
+      - DEBIAN_FRONTEND: noninteractive
     steps:
       - restore_cache:
           keys:
@@ -121,7 +130,7 @@ jobs:
 
   deploy:
     docker:
-      - image: circleci/python:3.6
+      - image: circleci/python:3.7
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh
@@ -132,7 +141,7 @@ jobs:
       - run: ls -ltrh doc/_build/html/stable
       - deploy:
           command: |
-            if [[ "${CIRCLE_BRANCH}" =~ ^master$|^[0-9]+\.[0-9]+\.X$ ]]; then
+            if [[ "${CIRCLE_BRANCH}" =~ ^main$|^[0-9]+\.[0-9]+\.X$ ]]; then
               bash build_tools/circle/push_doc.sh doc/_build/html/stable
             fi
 
@@ -162,6 +171,6 @@ workflows:
           filters:
             branches:
               only:
-                - master
+                - main
     jobs:
       - pypy3

.codecov.yml

@@ -4,7 +4,7 @@ coverage:
   status:
     project:
       default:
-        # Commits pushed to master should not make the overall
+        # Commits pushed to main should not make the overall
         # project coverage decrease by more than 1%:
         target: auto
         threshold: 1%

.github/ISSUE_TEMPLATE/config.yml

@@ -1,11 +1,17 @@
 blank_issues_enabled: false
 contact_links:
-  - name: Stack overflow
+  - name: Discussions
+    url: https://github.com/scikit-learn/scikit-learn/discussions/new
+    about: Ask questions and discuss with other scikit-learn community members
+  - name: Stack Overflow
     url: https://stackoverflow.com/questions/tagged/scikit-learn
-    about: Please ask and answer usage questions on stackoverflow
+    about: Please ask and answer usage questions on Stack Overflow
   - name: Mailing list 
     url: https://mail.python.org/mailman/listinfo/scikit-learn
     about: General discussions and announcements on the mailing list
   - name: Gitter
     url: https://gitter.im/scikit-learn/scikit-learn
     about: Users and developers can sometimes be found on the gitter channel
+  - name: Blank issue
+    url: https://github.com/scikit-learn/scikit-learn/issues/new
+    about: Please note that Github Discussions should be used in most cases instead

.github/labeler-file-extensions.yml

@@ -0,0 +1,8 @@
+cython:
+- sklearn/**/*.pyx
+- sklearn/**/*.pxd
+- sklearn/**/*.pxi
+# Tempita templates
+- sklearn/**/*.pyx.tp
+- sklearn/**/*.pxd.tp
+- sklearn/**/*.pxi.tp

.github/scripts/label_title_regex.py

@@ -0,0 +1,25 @@
+"""Labels PRs based on title. Must be run in a github action with the
+pull_request_target event."""
+from ghapi.all import context_github
+from ghapi.all import GhApi
+from ghapi.all import user_repo
+from ghapi.all import github_token
+import re
+
+owner, repo = user_repo()
+pull_request = context_github.event.pull_request
+title = pull_request.title
+
+regex_to_labels = [
+    (r"\bDOC\b", "Documentation"),
+    (r"\bCI\b", "Build / CI")
+]
+
+labels_to_add = [
+    label for regex, label in regex_to_labels
+    if re.search(regex, title)
+]
+
+if labels_to_add:
+    api = GhApi(owner=owner, repo=repo, token=github_token())
+    api.issues.add_labels(pull_request.number, labels=labels_to_add)

.github/workflows/check-changelog.yml

@@ -0,0 +1,54 @@
+name: Check Changelog
+# This check makes sure that the changelog is properly updated
+# when a PR introduces a change in a test file.
+# To bypass this check, label the PR with "No Changelog Needed".
+on:
+  pull_request:
+    types: [opened, edited, labeled, unlabeled, synchronize]
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    if: ${{ contains(github.event.pull_request.labels.*.name, 'No Changelog Needed') == 0 }}
+    steps:
+      - name: Get PR number and milestone
+        run: |
+          echo "PR_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+          echo "TAGGED_MILESTONE=${{ github.event.pull_request.milestone.title }}" >> $GITHUB_ENV
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: '0'
+      - name: Check the changelog
+        run: |
+          set -xe
+          changed_files=$(git diff --name-only origin/main)
+          # Changelog should be updated only if tests have been modified
+          if [[ ! "$changed_files" =~ tests ]]
+          then
+            exit 0
+          fi
+          all_changelogs=$(cat ./doc/whats_new/v*.rst)
+          if [[ "$all_changelogs" =~ :pr:\`$PR_NUMBER\` ]]
+          then
+            echo "Changelog has been updated."
+            # If the pull request is milestoned check the correspondent changelog
+            if exist -f ./doc/whats_new/v${TAGGED_MILESTONE:0:4}.rst
+            then
+              expected_changelog=$(cat ./doc/whats_new/v${TAGGED_MILESTONE:0:4}.rst)
+              if [[ "$expected_changelog" =~ :pr:\`$PR_NUMBER\` ]]
+              then
+                echo "Changelog and milestone correspond."
+              else
+                echo "Changelog and milestone do not correspond."
+                echo "If you see this error make sure that the tagged milestone for the PR"
+                echo "and the changelog name properly match."
+                exit 1
+              fi
+            fi
+          else
+            echo "Changelog entry is missing."
+            echo "If you see this error and there is already a changelog entry then make sure that"
+            echo "the PR number is correct. If no changelog entry is required for this PR,"
+            echo "label the PR with 'No Changelog Needed' to bypass this check."
+            exit 1
+          fi

.github/workflows/labeler-module.yml

@@ -12,3 +12,13 @@ jobs:
         repo-token: "${{ secrets.GITHUB_TOKEN }}"
         max-labels: "3"
         configuration-path: ".github/labeler-module.yml"
+
+  triage_file_extensions:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: thomasjpfan/labeler@v2.5.0
+      continue-on-error: true
+      if: github.repository == 'scikit-learn/scikit-learn'
+      with:
+        repo-token: "${{ secrets.GITHUB_TOKEN }}"
+        configuration-path: ".github/labeler-file-extensions.yml"

.github/workflows/labeler-title-regex.yml

@@ -1,16 +1,20 @@
 name: Pull Request Regex Title Labeler
 on:
   pull_request_target:
-    types: [opened]
+    types: [opened, edited]
 
 jobs:
 
   labeler:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
     steps:
-    - name: Check Labels
-      id: labeler
-      continue-on-error: true
-      uses: jimschubert/labeler-action@v2
+    - uses: actions/checkout@v2
+    - uses: actions/setup-python@v2
       with:
-        GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}}
+        python-version: '3.9'
+    - name: Install ghapi
+      run: pip install -Uq ghapi
+    - name: Label pull request
+      run: python .github/scripts/label_title_regex.py
+      env:
+        CONTEXT_GITHUB: ${{ toJson(github) }}

.github/workflows/publish_pypi.yml

@@ -40,10 +40,10 @@ jobs:
         user: __token__
         password: ${{ secrets.TEST_PYPI_TOKEN }}
         repository_url: https://test.pypi.org/legacy/
-      if: ${{ github.event.inputs.pypi_repo }} == 'testpypi'
+      if: ${{ github.event.inputs.pypi_repo == 'testpypi' }}
     - name: Publish package to PyPI
       uses: pypa/gh-action-pypi-publish@v1.4.1
       with:
         user: __token__
         password: ${{ secrets.PYPI_TOKEN }}
-      if: ${{ github.event.inputs.pypi_repo }} == 'pypi'
+      if: ${{ github.event.inputs.pypi_repo == 'pypi' }}

.github/workflows/twitter.yml

@@ -1,12 +1,12 @@
 # Tweet the URL of a commit on @sklearn_commits whenever a push event
-# happens on the master branch
+# happens on the main branch
 name: Twitter Push Notification
 
 
 on:
   push:
     branches:
-      - master
+      - main
 
 
 jobs:
@@ -16,7 +16,7 @@ jobs:
     steps:
       - name: Tweet URL of last commit as @sklearn_commits
         if: github.repository == 'scikit-learn/scikit-learn'
-        uses: xorilog/twitter-action@0.1
+        uses: docker://thomasjpfan/twitter-action:0.3
         with:
           args: "-message \"https://github.com/scikit-learn/scikit-learn/commit/${{ github.sha }}\""
         env:

.github/workflows/wheels.yml

@@ -7,12 +7,12 @@ on:
     - cron: "42 3 */1 * *"
   push:
     branches:
-      - master
+      - main
       # Release branches
       - "[0-9]+.[0-9]+.X"
   pull_request:
     branches:
-      - master
+      - main
       - "[0-9]+.[0-9]+.X"
   # Manual run
   workflow_dispatch:
@@ -22,6 +22,7 @@ jobs:
   check_build_trigger:
     name: Check build trigger
     runs-on: ubuntu-latest
+    if: github.repository == 'scikit-learn/scikit-learn'
     outputs:
       build: ${{ steps.check_build_trigger.outputs.build }}
 
@@ -35,9 +36,9 @@ jobs:
         name: Check build trigger
         run: bash build_tools/github/check_build_trigger.sh
 
-  # Build the wheels for Linux, Windows and macOS for Python 3.6 and newer
+  # Build the wheels for Linux, Windows and macOS for Python 3.7 and newer
   build_wheels:
-    name: Build wheel for cp${{ matrix.python }}-${{ matrix.platform_id }}
+    name: Build wheel for cp${{ matrix.python }}-${{ matrix.platform_id }}-${{ matrix.manylinux_image }}
     runs-on: ${{ matrix.os }}
     needs: check_build_trigger
     if: needs.check_build_trigger.outputs.build
@@ -47,8 +48,9 @@ jobs:
       fail-fast: false
       matrix:
         os: [windows-latest, ubuntu-latest, macos-latest]
-        python: [36, 37, 38, 39]
+        python: [37, 38, 39]
         bitness: [32, 64]
+        manylinux_image: [manylinux1, manylinux2010]
         include:
           # Run 32 and 64 bit version in parallel for Linux and Windows
           - os: windows-latest
@@ -69,6 +71,12 @@ jobs:
         exclude:
           - os: macos-latest
             bitness: 32
+          # Remove manylinux1 from the windows and osx build matrix since
+          # manylinux_image is not used for these platforms
+          - os: windows-latest
+            manylinux_image: manylinux1
+          - os: macos-latest
+            manylinux_image: manylinux1
 
     steps:
       - name: Checkout scikit-learn
@@ -85,12 +93,16 @@ jobs:
                             OPENBLAS_NUM_THREADS=2
                             SKLEARN_SKIP_NETWORK_TESTS=1
                             SKLEARN_BUILD_PARALLEL=3
+                            MACOSX_DEPLOYMENT_TARGET=10.13
           CIBW_BUILD: cp${{ matrix.python }}-${{ matrix.platform_id }}
-          CIBW_REPAIR_WHEEL_COMMAND_WINDOWS: bash build_tools/github/repair_windows_wheels.sh {wheel} {dest_dir} ${{ matrix.bitness }} 
+          CIBW_MANYLINUX_X86_64_IMAGE: ${{ matrix.manylinux_image }}
+          CIBW_MANYLINUX_I686_IMAGE: ${{ matrix.manylinux_image }}
+          CIBW_REPAIR_WHEEL_COMMAND_WINDOWS: bash build_tools/github/repair_windows_wheels.sh {wheel} {dest_dir} ${{ matrix.bitness }}
           CIBW_BEFORE_TEST_WINDOWS: bash build_tools/github/build_minimal_windows_image.sh ${{ matrix.python }} ${{ matrix.bitness }}
           CIBW_TEST_REQUIRES: pytest pandas threadpoolctl
           CIBW_TEST_COMMAND: bash {project}/build_tools/github/test_wheels.sh
           CIBW_TEST_COMMAND_WINDOWS: bash {project}/build_tools/github/test_windows_wheels.sh ${{ matrix.python }} ${{ matrix.bitness }}
+          CIBW_BUILD_VERBOSITY: 1
 
         run: bash build_tools/github/build_wheels.sh