r - H2O Random Forest Hangs on Completion -
i'm training random forest using h2o , r on large (~6 million) row dataset , ~50 output levels. despite progress bar hitting 100% console (and processor!) still busy , hangs on hour (so far!). not resource limitations, have 120gb of ram , couple of dozen cores.
hard give reproducible example given nature of issue there 35 variables, half of factors, i'm running model training through r following options:
rforest <- h2o.randomforest(y = y.var , x = x.vars , training_frame = traindata.h2o , validation_frame = testdata.h2o , ntrees = 100 , stopping_rounds = 3 , seed = 42 , model_id = modcode , mtries = -1)
has encountered similar issue/has explanation/knows workaround, please?
Comments
Post a Comment