A GRaphical Universal Modeler (https://gitlab.com/agrumery/aGrUM)
aGrUM is a C++ library for graphical models. It is designed for easily building applications using graphical models such as Bayesian networks, influence diagrams, decision trees, GAI networks or Markov decision processes.
aGrUM is written to provide the basic building blocks to perform the following tasks :designing graphical models,
learning graphical models,
elicitation of graphical models,
inference within graphical models,
The probabilistic graphical models currently present in the library are the following:Bayesian networks (first and main target),
O3PRM (Probabilistic Relational Models).
pyAgrum is a Python wrapper for the C++ aGrUM library (using SWIG interface generator). It provides a high-level interface to the part of aGrUM allowing to create, model, learn, use, calculate with and embed Bayesian Networks and other graphical models. Some specific (python and C++) codes are added in order to simplify and extend the aGrUM API.
Several topics have been added to pyAgrum (as pure python modules using pyAgrum) :
Scikit-learn-compliant probabilistic classifiers based on Bayesian networks,
Probabilistic causality (causal networks, do-calculus),
dynamic Bayesian network,
tools for explainability in Bayesian networks.
See the tutorials as jupyter notebooks for more details.
Installation : here
aGrUM/pyAgrum is released under the Gnu Lesser General Public License (LGPL v3.0), which means it can be freely copied and distributed, and costs nothing. Especially, aGrUM can be used and linked into both free software and proprietary software, provided that the code used under the LGPL is re-licensed under the LGPL (the other parts of the software are permitted have other licenses.). If you wish to integrate the aGrUM library into your product without being affected by the LGPL v.3, please contact us.