Metadata-Version: 2.2
Name: tiledbsoma-ml
Version: 0.1.0a3
Summary: Machine learning tools for use with tiledbsoma
Author-email: "TileDB, Inc." <help@tiledb.io>, The Chan Zuckerberg Initiative Foundation <soma@chanzuckerberg.com>
Maintainer-email: "TileDB, Inc." <help@tiledb.io>
Project-URL: Repository, https://github.com/TileDB-Inc/TileDB-SOMA-ML.git
Project-URL: Issues, https://github.com/TileDB-Inc/TileDB-SOMA-ML/issues
Project-URL: Changelog, https://github.com/TileDB-Inc/TileDB-SOMA-ML/blob/main/CHANGELOG.md
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Information Technology
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Operating System :: Unix
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: Microsoft :: Windows
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: attrs>=22.2
Requires-Dist: tiledbsoma>=1.9.0
Requires-Dist: torch>=2.0
Requires-Dist: numpy
Requires-Dist: numba
Requires-Dist: pandas
Requires-Dist: pyarrow
Requires-Dist: scipy

# TileDB-SOMA-ML

A Python package containing ML tools for use with [TileDB-SOMA].

**NOTE:** this is a _pre-release_ package, and may be subject to breaking API changes prior to first release.

## Description

The package contains a prototype PyTorch [`IterableDataset`] for use with the
[`torch.utils.data.DataLoader`]
API. For a general introduction to PyTorch data loading,
[see this tutorial][torch data tutorial].
Additional information on the DataLoader/Dataset pattern
[can be found here][`torch.data`].

Defects and feature requests should be filed as a GitHub issue in this repo. Please include a reproducible test case in all bug reports.

## Getting Started

### Installing

Prior to the first release, installation is most easily accomplished by installing directly from GitHub:

```bash
pip install git+https://github.com/single-cell-data/TileDB-SOMA-ML
```

Developers may install editable, from source, in the usual manner -- clone the repo and execute:

```bash
pip install -e .
```

### Documentation

Documentation is pending. Preliminary documentation can be found at [single-cell-data.github.io/TileDB-SOMA-ML], and in
the [notebooks] directory.

## Builds

This is a pure Python package. To build a wheel, ensure you have the `build` package installed, and then:

```bash
python -m build .
```

## Version History

See the [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.

[TileDB-SOMA]: https://github.com/single-cell-data/TileDB-SOMA
[`IterableDataset`]: https://pytorch.org/docs/stable/data.html#torch.utils.data.IterableDataset
[`torch.utils.data.DataLoader`]: https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader
[torch data tutorial]: https://pytorch.org/tutorials/beginner/data_loading_tutorial.html
[`torch.data`]: https://pytorch.org/docs/stable/data.html
[single-cell-data.github.io/TileDB-SOMA-ML]: https://single-cell-data.github.io/TileDB-SOMA-ML/
[notebooks]: notebooks
[CHANGELOG.md]: CHANGELOG.md
