Skip to content
conftrace_
2020 PGM PGM 2020

PGM_PyLib: A Toolkit for Probabilistic Graphical Models in Python

Abstract

PGM{_}PyLib is a toolkit that contains a wide range of Probabilistic Graphical Models algorithms implemented in Python, and serves as a companion of the book Probabilistic Graphical Models: Principles and Applications. Currently, the algorithms implemented include: Bayesian classifiers, hidden Markov models, Markov random fields, and Bayesian networks; as well as some general functions. The toolkit is open source, can be downloaded from: https://github.com/jona2510/PGM{_}PyLib .

Authors

Jonathan Serrano-Pérez, L. Enrique Sucar

Topics

Artificial Intelligence > Bayesian & Probabilistic > Probabilistic Modeling Machine Learning > Bayesian & Probabilistic > Probabilistic Modeling Artificial Intelligence > Bayesian & Probabilistic > Bayesian Networks

Keywords

hidden markov model markov random field bayesian network probabilistic graphical model bayesian classifier python toolkit
Download PDF

More from PGM 2020

All PGM 2020 papers →
CREDICI: A Java Library for Causal Inference by Credal Networks
Probabilistic Graphical Models with Neural Networks in InferPy
GOBNILP: Learning Bayesian network structure with integer programming
CREMA: A Java Library for Credal Network Inference
A Software System for Predicting Patient Flow at the Emergency Department of Aalborg University Hospital
MeDIL: A Python Package for Causal Modelling