initial scaffolding for project

.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 +1,26 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: "24.8.0"
+    hooks:
+      - id: black
+        exclude: 'apis/'
+
+  - 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"]
+        exclude: 'apis/'
+
+  - 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
+        exclude: 'apis/'

CHANGELOG.md

@@ -0,0 +1,21 @@
+
+# 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
+
+### Changed
+
+### Fixed

pyproject.toml

@@ -0,0 +1,76 @@
+[build-system]
+requires = ["setuptools >= 61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tiledbsoma-ml"
+dynamic = ["version"]
+dependencies = [
+    "attrs>=22.2",
+    "tiledbsoma>=1.9.0",
+    "torch>=2.0",
+    "torchdata<=0.9",
+    "numpy",
+    "numba",
+    "pandas",
+    "pyarrow",
+    "scipy"
+]
+requires-python = ">= 3.9"
+description = "Machine learning tools for use with tiledbsoma"
+readme = "README.md"
+authors = [
+    {name = "TileDB, Inc.", email = "[email protected]"},
+    {name = "The Chan Zuckerberg Initiative Foundation", email = "[email protected]" },
+]
+maintainers = [
+    {name = "TileDB, Inc.", email="[email protected]"},
+]
+
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Information Technology",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Operating System :: Unix",
+    "Operating System :: POSIX :: Linux",
+    "Operating System :: MacOS :: MacOS X",
+    "Operating System :: Microsoft :: Windows",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+
+[project.urls]
+Repository = "https://github.com/TileDB-Inc/TileDB-SOMA-ML.git"
+Issues = "https://github.com/TileDB-Inc/TileDB-SOMA-ML/issues"
+Changelog = "https://github.com/TileDB-Inc/TileDB-SOMA-ML/blob/main/CHANGELOG.md"
+
+[tool.setuptools.dynamic]
+version = {attr = "tiledbsoma_ml.__version__"}
+
+[tool.setuptools.package-data]
+"tiledbsoma_ml" = ["py.typed"]
+
+[tool.setuptools_scm]
+root = "../../.."
+
+[tool.mypy]
+show_error_codes = true
+ignore_missing_imports = true
+warn_unreachable = true
+strict = true
+python_version = 3.9
+plugins = "numpy.typing.mypy_plugin"
+
+[tool.ruff]
+lint.select = ["E", "F", "B", "I"]
+lint.ignore = ["E501"]  # line too long
+lint.extend-select = ["I001"]  # unsorted-imports
+fix = true
+target-version = "py39"
+line-length = 120

src/tiledbsoma_ml/__init__.py

@@ -0,0 +1,8 @@
+# Copyright (c) 2021-2024 The Chan Zuckerberg Initiative Foundation
+# Copyright (c) 2021-2024 TileDB, Inc.
+#
+# Licensed under the MIT License.
+
+"""An API to support machine learning applications built on SOMA."""
+
+__version__ = "0.1.0-dev"

src/tiledbsoma_ml/py.typed

@@ -0,0 +1,2 @@
+# Marker file to indicate that this package contains Python typing information,
+# and that mypy can use it to typecheck client code.