search

trappmartin / BayesianSumProductNetworks

Implementation of Bayesian Sum-Product Networks
MIT License
12 stars 6 forks source link

Continuous Variables made discrete #3

Open crinders opened 3 years ago

crinders commented 3 years ago

@trappmartin I generated a small continuous synthetic dataset for familiarizing myself with your package and the following issue occurred: All my continuous values are replaced with integers in run_abda_rg.jl. I believe the culprit is 

 dids = filter(d -> length(filter(x -> !isnan(x), unique(x_train[:,d]))) < args["maxcategories"], 1:D)

which really should read

 dids = filter(d -> length(filter(x -> !isnan(x), unique(x_train[:,d]))) < args["maxcategories"], dids)
trappmartin commented 3 years ago

Uh, that shouldn't be the case. Yes, that definitely looks like a bug. I haven't had time to bring this repo to life again, so there might be some other tiny issues here and there. Feel free to ping me via e-mail (see my Aalto University email address) if you have any questions about the code. GitHub notifications sometimes got over my head.

crinders commented 3 years ago

I have some interest in applying BSPNs in a number of scenarios. So you may hear from me more often ;-)