search

FenTechSolutions / CausalDiscoveryToolbox

Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.
https://fentechsolutions.github.io/CausalDiscoveryToolbox/html/index.html
MIT License
1.12k stars 197 forks source link

GIES: intervention targets #96

Open bvarici opened 3 years ago

bvarici commented 3 years ago

I may be missing something but I think GIES algorithm may not work properly. It takes a “score” input, that has “targets” in pcalg R implementation, i.e., intervened nodes.

Only difference between GES and GIES implementation in this package seems to be the “score”, obs and int, as it should be. However, https://github.com/FenTechSolutions/CausalDiscoveryToolbox/blob/master/cdt/causality/graph/GIES.py doesn’t seem to have “target” for 'int' score. Could you elaborate whether something is missing in GIES implementation, or I am missing something. Thanks.

diviyank commented 3 years ago

Hello @bvarici, thanks for noting this point, I'll be fixing ths in the next release !

manonromain commented 3 years ago

Hi Diviyan, was this fixed? I don't think so, but I might be missing something.

Have a good day!