Merge branch 'scikit-learn:main' into main

Author: jaffourt

.binder/postBuild

@@ -6,9 +6,9 @@ set -e
 # inside a git checkout of the scikit-learn/scikit-learn repo. This script is
 # generating notebooks from the scikit-learn python examples.
 
-if [[ ! -f /.dockerenv ]]; then
-    echo "This script was written for repo2docker and is supposed to run inside a docker container."
-    echo "Exiting because this script can delete data if run outside of a docker container."
+if [[ -z "${REPO_DIR}" ]]; then
+    echo "This script was written for repo2docker and the REPO_DIR environment variable is supposed to be set."
+    echo "Exiting because this script can delete data if run outside of a repo2docker context."
     exit 1
 fi
 
@@ -23,7 +23,7 @@ find . -delete
 GENERATED_NOTEBOOKS_DIR=.generated-notebooks
 cp -r $TMP_CONTENT_DIR/examples $GENERATED_NOTEBOOKS_DIR
 
-find $GENERATED_NOTEBOOKS_DIR -name '*.py' -exec sphx_glr_python_to_jupyter.py '{}' +
+find $GENERATED_NOTEBOOKS_DIR -name '*.py' -exec sphinx_gallery_py2jupyter '{}' +
 NON_NOTEBOOKS=$(find $GENERATED_NOTEBOOKS_DIR -type f | grep -v '\.ipynb')
 rm -f $NON_NOTEBOOKS
 

.binder/requirements.txt

@@ -1,8 +1,10 @@
---extra-index https://pypi.anaconda.org/scipy-wheels-nightly/simple scikit-learn
+--find-links https://pypi.anaconda.org/scientific-python-nightly-wheels/simple/scikit-learn
 --pre
 matplotlib
 scikit-image
 pandas
+seaborn
+Pillow
 sphinx-gallery
 scikit-learn
-
+polars

.binder/runtime.txt

@@ -0,0 +1 @@
+python-3.12

.circleci/artifact_path

@@ -1,29 +1,38 @@
-version: 2
+version: 2.1
 
 jobs:
+  lint:
+    docker:
+      - image: cimg/python:3.10.16
+    steps:
+      - checkout
+      - run:
+          name: dependencies
+          command: |
+            source build_tools/shared.sh
+            # Include pytest compatibility with mypy
+            pip install pytest $(get_dep ruff min) $(get_dep mypy min) cython-lint
+      - run:
+          name: linting
+          command: ./build_tools/linting.sh
+
   doc-min-dependencies:
     docker:
-      - image: circleci/python:3.7.3-stretch
+      - image: cimg/base:current-22.04
     environment:
-      - OMP_NUM_THREADS: 2
       - MKL_NUM_THREADS: 2
+      - OPENBLAS_NUM_THREADS: 2
       - CONDA_ENV_NAME: testenv
-      - PYTHON_VERSION: 3.6
-      - 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'
+      - LOCK_FILE: build_tools/circle/doc_min_dependencies_linux-64_conda.lock
+      # Do not fail if the documentation build generates warnings with minimum
+      # dependencies as long as we can avoid raising warnings with more recent
+      # versions of the same dependencies.
+      - SKLEARN_WARNINGS_AS_ERRORS: '0'
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh
       - restore_cache:
-          key: v1-datasets-{{ .Branch }}
+          key: v1-doc-min-deps-datasets-{{ .Branch }}
       - restore_cache:
           keys:
             - doc-min-deps-ccache-{{ .Branch }}
@@ -35,7 +44,7 @@ jobs:
             - ~/.ccache
             - ~/.cache/pip
       - save_cache:
-          key: v1-datasets-{{ .Branch }}
+          key: v1-doc-min-deps-datasets-{{ .Branch }}
           paths:
             - ~/scikit_learn_data
       - store_artifacts:
@@ -47,27 +56,20 @@ jobs:
 
   doc:
     docker:
-      - image: circleci/python:3.7.3-stretch
+      - image: cimg/base:current-22.04
     environment:
-      - OMP_NUM_THREADS: 2
       - MKL_NUM_THREADS: 2
+      - OPENBLAS_NUM_THREADS: 2
       - CONDA_ENV_NAME: testenv
-      - PYTHON_VERSION: 3
-      - NUMPY_VERSION: 'latest'
-      - SCIPY_VERSION: 'latest'
-      - MATPLOTLIB_VERSION: 'latest'
-      - CYTHON_VERSION: 'latest'
-      - SCIKIT_IMAGE_VERSION: 'latest'
-      - SPHINX_VERSION: 'min'
-      - PANDAS_VERSION: 'latest'
-      - SPHINX_GALLERY_VERSION: 'latest'
-      - NUMPYDOC_VERSION: 'latest'
-      - SPHINX_PROMPT_VERSION: 'latest'
+      - LOCK_FILE: build_tools/circle/doc_linux-64_conda.lock
+      # Make sure that we fail if the documentation build generates warnings with
+      # recent versions of the dependencies.
+      - SKLEARN_WARNINGS_AS_ERRORS: '1'
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh
       - restore_cache:
-          key: v1-datasets-{{ .Branch }}
+          key: v1-doc-datasets-{{ .Branch }}
       - restore_cache:
           keys:
             - doc-ccache-{{ .Branch }}
@@ -79,7 +81,7 @@ jobs:
             - ~/.ccache
             - ~/.cache/pip
       - save_cache:
-          key: v1-datasets-{{ .Branch }}
+          key: v1-doc-datasets-{{ .Branch }}
           paths:
             - ~/scikit_learn_data
       - store_artifacts:
@@ -94,43 +96,9 @@ jobs:
           root: doc/_build/html
           paths: .
 
-  lint:
-    docker:
-      - image: circleci/python:3.6
-    steps:
-      - checkout
-      - run: ./build_tools/circle/checkout_merge_commit.sh
-      - run:
-          name: dependencies
-          command: sudo pip install flake8
-      - run:
-          name: linting
-          command: ./build_tools/circle/linting.sh
-
-  pypy3:
-    docker:
-      - image: condaforge/miniforge3
-    environment:
-      # Avoid the interactive dialog when installing tzdata
-      - DEBIAN_FRONTEND: noninteractive
-    steps:
-      - restore_cache:
-          keys:
-            - pypy3-ccache-{{ .Branch }}
-            - pypy3-ccache
-      - run: apt-get -yq update && apt-get -yq install git ssh
-      - checkout
-      - run: conda init bash && source ~/.bashrc
-      - run: ./build_tools/circle/build_test_pypy.sh
-      - save_cache:
-          key: pypy3-ccache-{{ .Branch }}-{{ .BuildNum }}
-          paths:
-            - ~/.ccache
-            - ~/.cache/pip
-
   deploy:
     docker:
-      - image: circleci/python:3.6
+      - image: cimg/base:current-22.04
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh
@@ -139,7 +107,7 @@ jobs:
       - attach_workspace:
           at: doc/_build/html
       - run: ls -ltrh doc/_build/html/stable
-      - deploy:
+      - run:
           command: |
             if [[ "${CIRCLE_BRANCH}" =~ ^main$|^[0-9]+\.[0-9]+\.X$ ]]; then
               bash build_tools/circle/push_doc.sh doc/_build/html/stable
@@ -156,21 +124,6 @@ workflows:
       - doc-min-dependencies:
           requires:
             - lint
-      - pypy3:
-          filters:
-            branches:
-              only:
-                - 0.20.X
       - deploy:
           requires:
             - doc
-  pypy:
-    triggers:
-      - schedule:
-          cron: "0 0 * * *"
-          filters:
-            branches:
-              only:
-                - main
-    jobs:
-      - pypy3

.circleci/config.yml

@@ -19,13 +19,13 @@ coverage:
 
 codecov:
   notify:
-    # Prevent coverage status to upload multiple times for parallel and long
-    # running CI pipelines. This configuration is particularly useful on PRs
-    # to avoid confusion. Note that this value is set to the number of Azure
-    # Pipeline jobs uploading coverage reports.
-    after_n_builds: 6
+    # Prevent codecov from calculating the coverage results before all expected uploads
+    # are in. This value is set to the total number of jobs uploading coverage reports.
+    after_n_builds: 7
 
 ignore:
 - "sklearn/externals"
 - "sklearn/_build_utils"
-- "**/setup.py"
+- "sklearn/__check_build"
+- "sklearn/_min_dependencies.py"
+- "**/conftest.py"

.codecov.yml

@@ -1,9 +1,11 @@
 [run]
-branch = True
+# Use statement coverage rather than branch coverage because
+# COVERAGE_CORE=sysmon can make branch coverage slower rather than faster. See
+# https://github.com/nedbat/coveragepy/issues/1812 for more details.
+branch = False
 source = sklearn
 parallel = True
 omit =
     */sklearn/externals/*
     */sklearn/_build_utils/*
     */benchmarks/*
-    **/setup.py

.coveragerc

@@ -0,0 +1,17 @@
+{
+  // More info about Features: https://containers.dev/features
+  "image": "mcr.microsoft.com/devcontainers/base:ubuntu-24.04",
+  "features": {},
+
+  "onCreateCommand": ".devcontainer/setup.sh",
+  "postCreateCommand": "",
+
+  "customizations": {
+    "vscode": {
+      "extensions": [
+        "ms-python.python"
+      ],
+      "settings": {}
+    }
+  }
+}

.devcontainer/devcontainer.json

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+set -e
+
+"${SHELL}" <(curl -Ls micro.mamba.pm/install.sh) < /dev/null
+# .bashrc has been updated by the mamba install one-liner above.
+# 'source $HOME/.bashrc' sets up micromamba for later use
+source $HOME/.bashrc
+
+micromamba env create -f build_tools/circle/doc_environment.yml -n sklearn-dev --yes
+# Auto-activate sklearn-dev in terminal
+echo "micromamba activate sklearn-dev" >> $HOME/.bashrc

.devcontainer/setup.sh

@@ -0,0 +1,54 @@
+# Since git version 2.23, git-blame has a feature to ignore
+# certain commits.
+#
+# This file contains a list of commits that are not likely what
+# you are looking for in `git blame`. You can set this file as
+# a default ignore file for blame by running the following
+# command.
+#
+# $ git config blame.ignoreRevsFile .git-blame-ignore-revs
+
+# PR 18948: Migrate code style to Black
+82df48934eba1df9a1ed3be98aaace8eada59e6e
+
+# PR 20294: Use target_version >= 3.7 in Black
+351ace7935a4ea685171cc6d174890f08facd561
+
+# PR 20412: Use experimental_string_processing=true in Black
+3ae7c7615343bbd36acece57825d8b0d70fd9da4
+
+# PR 20502: Runs Black on examples
+70a185ae59b4362633d18b0d0083abb1b6f7370c
+
+# PR 22474: Update to Black 22.1.0
+1fc86b6aacd89da44a3b4e8abf7c3e2ba4336ffe
+
+# PR 22983: Update to Black 22.3.0
+d4aad64b1eb2e42e76f49db2ccfbe4b4660d092b
+
+# PR 26110: Update black to 23.3.0
+893d5accaf9d16f447645e704f85a216187564f7
+
+# PR 26649: Add isort and ruff rules
+42173fdb34b5aded79664e045cada719dfbe39dc
+
+# PR 28802: Update black to 24.3.0
+c4c546355667b070edd5c892b206aa4a97af9a0b
+
+# PR 30694: Enforce ruff rules (RUF)
+fe7c4176828af5231f526e76683fb9bdb9ea0367
+
+# PR 30695: Apply ruff/flake8-implicit-str-concat rules (ISC)
+5cdbbf15e3fade7cc2462ef66dc4ea0f37f390e3
+
+# PR 31015: black -> ruff format
+ff78e258ccf11068e2b3a433c51517ae56234f88
+
+# PR 31226: Enforce ruff/pygrep-hooks rules
+b98dc797c480b1b9495f918e201d45ee07f29feb
+
+# PR 31817: Consistently use relative imports
+4abf564cb4ac58d61fbbe83552c28f764284a69d
+
+# PR 31847 Switch to absolute imports enforced by ruff
+1fe659545c70d9f805c1c4097dd2fce9a6285a12