Skip to main content

approximate bayesian computing with population monte carlo

Project description

https://badge.fury.io/py/abcpmc.png https://travis-ci.org/jakeret/abcpmc.png?branch=master https://coveralls.io/repos/jakeret/abcpmc/badge.png?branch=master http://img.shields.io/badge/arXiv-1504.07245-orange.svg?style=flat

A Python Approximate Bayesian Computing (ABC) Population Monte Carlo (PMC) implementation based on Sequential Monte Carlo (SMC) with Particle Filtering techniques.

approximated 2d posterior (created with triangle.py).

The abcpmc package has been developed at ETH Zurich in the Software Lab of the Cosmology Research Group of the ETH Institute of Astronomy.

The development is coordinated on GitHub and contributions are welcome. The documentation of abcpmc is available at readthedocs.org and the package is distributed over PyPI.

Features

  • Entirely implemented in Python and easy to extend

  • Follows Beaumont et al. 2009 PMC algorithm

  • Parallelized with muliprocessing or message passing interface (MPI)

  • Extendable with k-nearest neighbour (KNN) or optimal local covariance matrix (OLCM) pertubation kernels (Fillipi et al. 2012)

  • Detailed examples in IPython notebooks

    • A 2D gauss case study
    • A toy model including a comparison to theoretical predictions

Documentation

The full documentation can be generated with Sphinx

History

0.1.1 (2015-05-03)

  • Python 3 support
  • Minor fixes
  • Improved documentation

0.1.0 (2015-04-28)

  • First release

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
abcpmc-0.1.1.tar.gz (700.6 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page