Treat your machine learning models like any other software asset: properly test them and fail builds if they don't meet your desired performance.
- Documentation: https://test-ml.readthedocs.io/en/latest/ (not live yet). For now, you can build the docs locally:
$ cd docs && make clean && make htmlOpen then index.html in the newly created docs/_build folder and you're good to go.
This library enables you to easily test machine learning artifacts. Specify a set of target metric, and the rest is taken care of.
Note
Status: alpha. Active development, but breaking changes may come.
- Rich CLI capabilities that enable you to configure metrics, input data, performance cut-offs, and more
- Small, statically typed codebase, and extensive docstrings
- Public API enabling embedding this library in any build process
- Easily extensible with custom loaders, runners, and metrics
This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.