Merge branch 'main' into submodulev2

Author: adam2392

.github/workflows/labeler-module.yml

@@ -14,7 +14,7 @@ jobs:
   triage:
     runs-on: ubuntu-latest
     steps:
-    - uses: thomasjpfan/labeler@v2.5.0
+    - uses: thomasjpfan/labeler@v2.5.1
       continue-on-error: true
       if: github.repository == 'neurodata/scikit-learn'
       with:
@@ -25,7 +25,7 @@ jobs:
   triage_file_extensions:
     runs-on: ubuntu-latest
     steps:
-    - uses: thomasjpfan/labeler@v2.5.0
+    - uses: thomasjpfan/labeler@v2.5.1
       continue-on-error: true
       if: github.repository == 'neurodata/scikit-learn'
       with:

.github/workflows/twitter.yml

@@ -41,8 +41,8 @@
 .. |Scikit-ImageMinVersion| replace:: 0.16.2
 .. |PandasMinVersion| replace:: 1.0.5
 .. |SeabornMinVersion| replace:: 0.9.0
-.. |PytestMinVersion| replace:: 5.3.1
-.. |PlotlyMinVersion| replace:: 5.10.0
+.. |PytestMinVersion| replace:: 7.1.2
+.. |PlotlyMinVersion| replace:: 5.14.0
 
 =================
 Scikit-learn-tree
@@ -160,8 +160,6 @@ The scikit-learn community goals are to be helpful, welcoming, and effective. Th
 has detailed information about contributing code, documentation, tests, and
 more. We've included some basic information in this README.
 
-=========================
-
 .. _fork_changelog:
 
 Major Changes of the Fork
@@ -284,4 +282,4 @@ that may, or may not eventually be PRed into ``scikit-learn``. For example,
 
 If you are developing tree models, we encourage you to take a look at that package, or
 if you have suggestions to make the tree submodule of our fork, ``scikit-learn-tree``
-more 
+more 

README.rst

@@ -71,7 +71,7 @@ jobs:
   #
   # 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 specifc fixes to make them run correctly without relying on the GIL.
+  # 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
@@ -121,6 +121,40 @@ jobs:
         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 Pyodide version 0.23.2, see
+    # https://github.com/pyodide/pyodide/blob/0.23.2/Makefile.envs
+    PYODIDE_VERSION: '0.23.2'
+    EMSCRIPTEN_VERSION: '3.1.32'
+    PYTHON_VERSION: '3.11.2'
+
+  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 and install it in a Pyodide venv
+
+    - 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:

azure-pipelines.yml

@@ -86,10 +86,10 @@ def load_data(dtype=np.float32, order="F"):
     "ExtraTrees": ExtraTreesClassifier(),
     "RandomForest": RandomForestClassifier(),
     "Nystroem-SVM": make_pipeline(
-        Nystroem(gamma=0.015, n_components=1000), LinearSVC(C=100)
+        Nystroem(gamma=0.015, n_components=1000), LinearSVC(C=100, dual="auto")
     ),
     "SampledRBF-SVM": make_pipeline(
-        RBFSampler(gamma=0.015, n_components=1000), LinearSVC(C=100)
+        RBFSampler(gamma=0.015, n_components=1000), LinearSVC(C=100, dual="auto")
     ),
     "LogisticRegression-SAG": LogisticRegression(solver="sag", tol=1e-1, C=1e4),
     "LogisticRegression-SAGA": LogisticRegression(solver="saga", tol=1e-1, C=1e4),

benchmarks/bench_mnist.py

@@ -4,29 +4,29 @@
 #
 #    pip-compile --output-file=build_tools/azure/debian_atlas_32bit_lock.txt build_tools/azure/debian_atlas_32bit_requirements.txt
 #
-attrs==22.2.0
+attrs==23.1.0
     # via pytest
-coverage==7.2.2
+coverage==7.2.7
     # via pytest-cov
-cython==0.29.33
+cython==0.29.35
     # via -r build_tools/azure/debian_atlas_32bit_requirements.txt
+iniconfig==2.0.0
+    # via pytest
 joblib==1.1.1
     # via -r build_tools/azure/debian_atlas_32bit_requirements.txt
-more-itertools==9.1.0
-    # via pytest
-packaging==23.0
+packaging==23.1
     # via pytest
-pluggy==0.13.1
+pluggy==1.0.0
     # via pytest
 py==1.11.0
     # via pytest
-pytest==5.3.1
+pytest==7.1.2
     # via
     #   -r build_tools/azure/debian_atlas_32bit_requirements.txt
     #   pytest-cov
 pytest-cov==2.9.0
     # via -r build_tools/azure/debian_atlas_32bit_requirements.txt
 threadpoolctl==2.2.0
     # via -r build_tools/azure/debian_atlas_32bit_requirements.txt
-wcwidth==0.2.6
+tomli==2.0.1
     # via pytest

build_tools/azure/debian_atlas_32bit_lock.txt

@@ -4,5 +4,5 @@
 cython
 joblib==1.1.1  # min
 threadpoolctl==2.2.0
-pytest==5.3.1  # min
+pytest==7.1.2  # min
 pytest-cov==2.9.0  # min

build_tools/azure/debian_atlas_32bit_requirements.txt

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+set -e
+
+git clone https://github.com/emscripten-core/emsdk.git
+cd emsdk
+./emsdk install $EMSCRIPTEN_VERSION
+./emsdk activate $EMSCRIPTEN_VERSION
+source emsdk_env.sh
+cd -
+
+pip install pyodide-build==$PYODIDE_VERSION pyodide-cli
+
+pyodide build
+
+ls -ltrh dist
+
+pyodide venv pyodide-venv
+source pyodide-venv/bin/activate
+
+pip install dist/*.whl
+pip list

build_tools/azure/install_pyodide.sh

@@ -129,5 +129,6 @@ jobs:
       condition: and(succeeded(), eq(variables['COVERAGE'], 'true'),
                      eq(variables['SELECTED_TESTS'], ''))
       displayName: 'Upload To Codecov'
+      retryCountOnTaskFailure: 5
       env:
         CODECOV_TOKEN: $(CODECOV_TOKEN)

build_tools/azure/posix-docker.yml

@@ -107,5 +107,6 @@ jobs:
       condition: and(succeeded(), eq(variables['COVERAGE'], 'true'),
                      eq(variables['SELECTED_TESTS'], ''))
       displayName: 'Upload To Codecov'
+      retryCountOnTaskFailure: 5
       env:
         CODECOV_TOKEN: $(CODECOV_TOKEN)