It looks like Weka has an underflow issue with large graphs…
http://weka.8497.n7.nabble.com/NaN-in-margins-of-an-editableBayesNet-td44721.html
So I’d like to try PyMC. Is it possible to learn a Bayesian network from data like the network shown in the first post here:
https://discourse.pymc.io/t/making-a-query-for-a-simple-bn-made-in-pymc3/2663/16
It sounds like I could then set my observation to a specific value in my class and then get the most influential attributes, is that correct? Is there a good tutorial for this? What are the right terms to use when talking about PyMC?