multinet `nparams()` - Githubissues

bmihaljevic / bnclassify

Learning Discrete Bayesian Network Classifiers from Data

18 stars 10 forks source link

multinet `nparams()` #57

Open bmihaljevic opened 3 years ago

bmihaljevic commented 3 years ago

nparams() currently not implemented. The number of parameters should be divided by r, where r is the number of classes, since each local model has r-1 dummy classes. This should be updated locally (for each model) as it may effect BIC and AIC scores. See test-multinet.r