eBay/bayesian-belief-networks

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

1142 stars · 256 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python framework for defining Bayesian Belief Networks and other graphical models as pure Python functions, with support for discrete and Gaussian continuous variables. It provides multiple exact and approximate inference engines including junction tree message passing, sum product, and MCMC sampling.

Use cases

• build a bayesian belief network in python
• run exact inference on a probabilistic graphical model
• convert a bayesian network to a junction tree or factor graph
• do approximate inference with MCMC sampling on a belief network
• model gaussian bayesian networks with continuous variables
• export a probabilistic graph to graphviz dot format

When to choose

• you want to define Bayesian networks declaratively in pure Python with minimal dependencies
• you need exact inference (junction tree, sum product) on small-to-medium discrete or Gaussian networks
• you want MCMC sampling as a fallback for approximate inference
• you need GraphViz export for visualizing model structure

When to avoid

• you need large-scale or scalable inference on massive networks
• you want modern deep-learning-based probabilistic programming (e.g., Pyro, PyMC)
• you need active maintenance or recent releases - the project has seen limited updates since 2021
• you require hybrid networks mixing discrete and continuous variables with full support

Facets

library · maturity maintenance

machine-learning math data-science machine-learning data-science python cross-platform bayesian-networks probabilistic-graphical-models exact-inference junction-tree mcmc factor-graphs graphviz-export algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="eBay/bayesian-belief-networks")