Skip to content

This library is a Python implementation of the algorithms GenESeSS and xGenESeSS published and described by I. Chattopadhyay et al. They can highlight the eventual causality connexions (in the sense of Granger) between discrete time series.

License

Notifications You must be signed in to change notification settings

jbdelfau/Causality-networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Causality networks

Author

Jean-Baptiste Delfau

Description

This library is a Python implementation of the algorithms GenESeSS and xGenESeSS published and described by I. Chattopadhyay et al in the following articles:

  • Causality networks, Chattopadhyay, arXiv, 2014.
  • Abductive learning of quantized stochastic processes with probabilistic finite automata, Chattopadhyay et al, Phil Trans R Soc A, 2016
  • Event-level prediction of urban crime reveals a signature of enforcement bias in US cities, Rotaru et al, Nature human Behaviour, 2022

Its main purpose is to infer a Probabilistic Finite State Automaton (PFSA) or Crossed Probabilistic Finite State Automaton (XPFSA) from discrete time series. The analysis of these automata can then bring into light the existence of causal dependence - in the sense of Granger - between the events of the time series.

Usage

Examples can be found in file test_algo.py of the tests folder. In short, one needs to call the function granger_network() with the following arguments:

  • a dictionary of time series likely to be correlated
  • a dictionary of hyperparameters
  • the maximum length of the sequences computed by the algorithm
  • the title of the experiment

About

This library is a Python implementation of the algorithms GenESeSS and xGenESeSS published and described by I. Chattopadhyay et al. They can highlight the eventual causality connexions (in the sense of Granger) between discrete time series.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages