Daft

Summary

Daft is a Python package that uses matplotlib to render pixel-perfect probabilistic graphical models for publication in a journal or on the internet. With a short Python script and an intuitive model-building syntax you can design directed (Bayesian Networks, directed acyclic graphs) and undirected (Markov random fields) models and save them in any formats that matplotlib supports (including PDF, PNG, EPS and SVG).

Installation

Installing the most recent stable version of Daft should be pretty easy if you use pip:

pip install daft

Otherwise, you can download the source (tar, zip) and run:

python setup.py install

in the root directory.

Daft only depends on matplotlib and numpy. These are standard components of the scientific Python stack but if you don’t already have them installed pip will try to install them for you but sometimes it’s easier to do that part yourself.

Issues

If you have any problems or questions, open an “issue” on Github.

Authors & Contributions

Daft is being developed and supported by Dan Foreman-Mackey and David W. Hogg.

For the hackers in the house, development happens on Github and we welcome pull requests. In particular, we’d love to see examples of how you’re using Daft in your work.

License

Copyright 2012 Dan Foreman-Mackey, David W. Hogg, and contributors.

Daft is free software made available under the MIT License. For details see the LICENSE file.

If you use Daft in academic projects, acknowledgements are greatly appreciated.

Fork me on GitHub