Graph_Sampler
Graph_Sampler is a graph or network inference and simulation package. Graph_Sampler allows you to generate structured random graphs and perform fully Bayesian inference on Bayesian networks' or dynamic Bayesian networks' structure. Markov chain Monte Carlo algorithms are used to those effects. The code is standard C. It uses flex and bison for development, and optionally libgsl at run-time.
News
Aug 29th, 2018 - Release of version 3.0.0!
(see Downloading Graph_Sampler, below).
Version 3.0.0 proposes a new hypergraph-type of model and many
improvements.
Check the User's Manual.
Jan 7th, 2018 - Help request and bug reporting mailing lists are available (see Mailing lists, below).
Downloading Graph_Sampler code
You can download Graph_Sampler C code via HTTP at http://ftp.nongnu.org/gnu/graphsampler/.
The gzipped tar archive contains:
- A User's Manual (in Texinfo, pdf and HTML formats)
- The ASCII source code of the Graph_Sampler routines (to link with your models)
- Examples of simulation scripts
Older versions can also be obtained on the same servers.
Graph_Sampler development is hosted on savannah.gnu.org. See the Graph_Sampler project page on Savannah, where the latest development sources are publicly available.
Documentation
The User's manual for Graph_Sampler is available online.
The pdf version of the manual can be found here here
Installation
To install Graph_Sampler, you will need a C compiler and linker to compile the sources and obtain executables. For any machine we recommend the GNU gcc compiler, but standard C compilers should also work.
Installation of the GNU Scientific Library (gsl, and its companion gslcblas) is optional but strongly recommended.
The user's manual provides detailed instructions (online here) for installation on major platforms.
Mailing lists
Graph_Sampler has the following mailing lists:
- graphsampler-bug is used for bugs reporting, as well as development and enhancement requests.
- help-graphsampler-help is for general user help and discussion.
Announcements about Graph_Sampler are made on info-nongnu (archive).
Contributed material and related links
Getting involved
Development of Graph_Sampler, is a volunteer effort, and you can contribute:
- Development
- For development sources, issue trackers, and other information, please see the Graph_Sampler project page at savannah.nongnu.org.
- Maintainer
- Graph_Sampler is currently being maintained by Frederic Y. Bois. Please use the mailing lists for contact.
Licensing
Graph_Sampler is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 3 of the License, or (at your option) any later version.