Skip to content

michaelnowotny/pyjags

 
 

Repository files navigation

PyJAGS: The Python Interface to JAGS

PyJAGS provides a Python interface to JAGS, a program for analysis of Bayesian hierarchical models using Markov Chain Monte Carlo (MCMC) simulation.

PyJAGS adds the following features on top of JAGS:

  • Multicore support for parallel simulation of multiple Markov chains (See Jupyter Notebook Advanced Functionality
  • Saving sample MCMC chains to and restoring from HDF5 files
  • Functionality to merge samples along iterations or across chains so that sampling can be resumed in consecutive chunks until convergence criteria are satisfied
  • Connectivity to the Bayesian analysis and visualization package Arviz

License: GPLv2

Supported Platforms

PyJAGS works on MacOS and Linux. Windows is not currently supported.

Installation

A working JAGS installation is required.

    pip install pyjags

Useful Links

Acknowledgements

  • JAGS was created by Martyn Plummer
  • PyJAGS was originally created by Tomasz Miasko
  • As of May 2020, PyJAGS is developed by Michael Nowotny

About

PyJAGS: The Python Interface to JAGS

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 94.7%
  • Python 4.8%
  • C++ 0.5%