GPy

a Gaussian processes framework in python

This project is maintained by SheffieldML

GPy

GPy is a Gaussian Process (GP) framework written in python, from the Sheffield machine learning group.

Gaussian processes underpin range of modern machine learning algorithms. In GPy, we've used python to implement a range of machine learning algorithms based on GPs.

GPy is available under the BSD 3-clause license. We'd love to incorporate your changes, so fork us on github!

New release!

After a long series of changes, we're pleased to announce the GPy 1.0.7 is ready for use. Users can download the code from github (deploy branch) or install with pip.

. There are lots of changes, we've tried to highlight important ones in the changelog.

Installation

Installation instructions along side the source code can be found on the GPy project github page. The instructions vary slightly with the target OS but essentially revolve around installing from the python package index, PyPI

Tutorials

A series of tutorials on working with GPy can be found here:

These are in the ipython notebook format: the code, plots and text can be read online. If you wish to run the examples locally they can be downloaded and run with the ipython notebook.

Community / Discussions

Questions and community discussion about GPy happen on the GitHub repository Discussions page (the old Sheffield user mailing list is retired):

Documentation

You can read the online documentation for GPy here:

These documents are automatically compiled from the docstrings defined in the code: we recommend new users take a look at the tutorials first.

Tests