Initial work toward PyTorch data loaders

.github/workflows/python-tiledbsoma-ml.yml

@@ -1,10 +1,72 @@
-name: python-tiledbsoma-ml
+name: python-tiledbsoma-ml CI
 
 on:
+  pull_request:
+    branches: ["*"]
+    paths-ignore:
+      - 'scripts/**'
+  push:
+    branches: [main]
+    paths-ignore:
+      - 'scripts/**'
+
   workflow_dispatch:
 
 jobs:
-  job:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Restore pre-commit cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pre-commit
+          key: pre-commit-${{ hashFiles('.pre-commit-config.yaml') }}
+
+      - name: Install pre-commit
+        run: pip -v install pre-commit
+
+      - name: Run pre-commit hooks on all files
+        run: pre-commit run -v -a
+
+  tests:
     runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
     steps:
-    # Empty job; placeholder GHA
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+
+      - name: Install prereqs
+        run: |
+          pip install --upgrade pip wheel pytest pytest-cov setuptools
+          pip install .
+
+      - name: Run tests
+        run: pytest -v --cov=src --cov-report=xml tests
+
+  build:
+    # for now, just do a test build to ensure that it works
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Do build
+        run: |
+          pip install --upgrade build pip wheel setuptools setuptools-scm
+          python -m build .

.github/workflows/python-tilledbsoma-ml-compat.yml

@@ -0,0 +1,46 @@
+name: python-tiledbsoma-ml past tiledbsoma compat # Latest tiledbsoma version covered by another workflow
+
+on:
+  pull_request:
+    branches: ["*"]
+    paths-ignore:
+      - "scripts/**"
+      - "notebooks/**"
+  push:
+    branches: [main]
+    paths-ignore:
+      - "scripts/**"
+      - "notebooks/**"
+
+jobs:
+  unit_tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        os: ["ubuntu-latest"]  # could add 'macos-latest', but the matrix is already huge...
+        python-version: ["3.9", "3.10", "3.11"]  # TODO: add 3.12 when tiledbsoma releases wheels for it.
+        pkg-version:
+          - "tiledbsoma~=1.9.0 'numpy<2.0.0'"
+          - "tiledbsoma~=1.10.0 'numpy<2.0.0'"
+          - "tiledbsoma~=1.11.0"
+          - "tiledbsoma~=1.12.0"
+          - "tiledbsoma~=1.13.0"
+          - "tiledbsoma~=1.14.0"
+
+    runs-on: ${{ matrix.os }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+
+      - name: Install prereqs
+        run: |
+          pip install --upgrade pip pytest setuptools
+          pip install ${{ matrix.pkg-version }} .
+
+      - name: Run tests
+        run: pytest -v tests

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.pre-commit-config.yaml

@@ -0,0 +1,23 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: "24.8.0"
+    hooks:
+      - id: black
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.6.5
+    hooks:
+      - id: ruff
+        name: "ruff for tiledbsoma_ml"
+        args: ["--config=pyproject.toml"]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.11.2
+    hooks:
+      - id: mypy
+        pass_filenames: false
+        args: ["--config-file=pyproject.toml", "src"]
+        additional_dependencies:
+          - attrs
+          - numpy
+          - pandas-stubs>=2

CHANGELOG.md

@@ -0,0 +1,24 @@
+
+# Change Log
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](http://keepachangelog.com/)
+and this project adheres to [Semantic Versioning](http://semver.org/).
+
+## [Unreleased] - yyyy-mm-dd
+
+Port and enhance contribution from the Chan Zuckerberg Initiative Foundation
+[CELLxGENE](https://cellxgene.cziscience.com/) project.
+
+This is not a one-for-one migration of the contributed code. Substantial changes have
+been made to the package utility (e.g., multi-GPU support), improve API usability, etc.
+
+### Added
+
+- Initial commits via [PR #1](https://github.com/single-cell-data/TileDB-SOMA-ML/pull/1)
+- Refine package dependency pins and compatibility tests via [PR #2](https://github.com/single-cell-data/TileDB-SOMA-ML/pull/2)
+
+### Changed
+
+### Fixed

README.md

@@ -0,0 +1,45 @@
+
+# tiledbsoma_ml
+
+A Python package containing ML tools for use with `tiledbsoma`.
+
+## Description
+
+The package currently contains a prototype PyTorch `IterableDataset` for use with the
+[`torch.utils.data.DataLoader`](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader)
+API.
+
+## Getting Started
+
+### Installing
+
+Install using your favorite package installer.  For exapmle, with pip:
+
+> pip install tiledbsoma-ml
+
+Developers may install editable, from source, in the usual manner:
+
+> pip install -e .
+
+### Documentation
+
+TBD
+
+## Builds
+
+This is a pure Python package. To build a wheel, ensure you have the `build` package installed, and then:
+
+> python -m build .
+
+## Version History
+
+See the [CHANGELOG.md](CHANGELOG.md) file.
+
+## License
+
+This project is licensed under the MIT License.
+
+## Acknowledgements
+
+The SOMA team is grateful to the Chan Zuckerberg Initiative Foundation [CELLxGENE Census](https://cellxgene.cziscience.com)
+team for their initial contribution.