This library defines the connectors needed for the integration and deployment of BigML models using MLFlow.

All the resources generated by the BigML API-first platform, including models, are totally white-box, and they can be downloaded as JSON and used to predict anywhere. The bigmlflow library uses BigML's Python bindings to integrate with MLFlow tracking and deploying capacities.

The examples/README.md file shows a few use cases that cover some of the Supervised Models available in BigML and a full training example to demo the logging and tracking of BigML's models using MLFlow.

This library is available as a PyPI package. To install it, just run:

    pip install bigmlflow

The tests directory contains some tests for the logging of models. We use Pytest to run the tests, so you can install it separately

    pip install pytest

or as an extra for development and testing purposes

    pip install -e .[tests]

Please follow the next steps:

1. Fork the project on github.com.
2. Create a new branch.
3. Commit changes to the new branch.
4. Send a pull request.