George#

George is a fast and flexible Python library for Gaussian Process (GP) Regression. A full introduction to the theory of Gaussian Processes is beyond the scope of this documentation but the best resource is available for free online: Rasmussen & Williams (2006).

Unlike some other GP implementations, george is focused on efficiently evaluating the marginalized likelihood of a dataset under a GP prior, even as this dataset gets Big™. As you’ll see in these pages of documentation, the module exposes quite a few other features but it is designed to be used alongside your favorite non-linear optimization or posterior inference library for the best results.

George is being actively developed in a public repository on GitHub so if you have any trouble, open an issue there.

https://img.shields.io/badge/GitHub-dfm%2Fgeorge-blue.svg?style=flat http://img.shields.io/badge/license-MIT-blue.svg?style=flat https://github.com/dfm/george/workflows/Tests/badge.svg?style=flat https://coveralls.io/repos/github/dfm/george/badge.svg?branch=main&style=flat

Contributors#

George is being developed by Dan Foreman-Mackey (@dfm) with many contributions from:

License & Attribution#

Copyright 2012-2023 Daniel Foreman-Mackey and contributors.

George is being developed by Dan Foreman-Mackey in a public GitHub repository. The source code is made available under the terms of the MIT license.

If you make use of this code, please cite the paper which is in IEEE Transactions on Pattern Analysis and Machine Intelligence:

@ARTICLE{2015ITPAM..38..252A,
        author = {{Ambikasaran}, Sivaram and {Foreman-Mackey}, Daniel and {Greengard}, Leslie and {Hogg}, David W. and {O'Neil}, Michael},
         title = "{Fast Direct Methods for Gaussian Processes}",
       journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
      keywords = {Mathematics - Numerical Analysis, Astrophysics - Instrumentation and Methods for Astrophysics, Mathematics - Statistics Theory, Mathematics - Numerical Analysis, Astrophysics - Instrumentation and Methods for Astrophysics, Mathematics - Statistics Theory},
          year = 2015,
         month = jun,
        volume = {38},
         pages = {252},
           doi = {10.1109/TPAMI.2015.2448083},
 archivePrefix = {arXiv},
        eprint = {1403.6015},
  primaryClass = {math.NA},
        adsurl = {https://ui.adsabs.harvard.edu/abs/2015ITPAM..38..252A},
       adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}

Changelog#

0.4.0 (2021-02-15)#

  • Updated packaging and installation issues

  • Updated CI and Python version testing

0.3.1 (2018-01-08)#

  • Fixed issue where george would not compile with GCC<4.9 because of a compiler bug

  • Fixed bug when re-using HODLR factorizations

0.3.0 (2017-07-12)#

  • New modeling protocol for parameter fitting

  • Rewritten HODLR algorithm - more stable and better performance

  • New interface for “easily” implementing new kernel functions

pre-0.3#

  • This project has had a long and tumultuous history