gbm - R - Caret - Using ROC instead of accuracy in model training -



gbm - R - Caret - Using ROC instead of accuracy in model training -

hi name abhi , using caret build gbm trees based model. instead of accuracy utilize roc metric

here code have far

mytunegrid <- expand.grid(n.trees = 500,interaction.depth = 11,shrinkage = 0.1) fitcontrol <- traincontrol(method = "repeatedcv", number = 7,repeats = 1, verboseiter = false,returnresamp = "all",classprobs = true) mymodel <- train(cover_type ~ .,data = modeldata,method = "gbm",trcontrol = fitcontrol,tunegrid = mytunegrid,metric='roc')

however when run code warning

warning message: in train.default(x, y, weights = w, ...) : metric "roc" not in result set. accuracy used instead.

how forcefulness model utilize roc instead of accuracy. doing wrong here?

here link github project source code? https://github.com/rseiter/practicalmlproject/blob/master/multiclasssummary.r

r gbm

Comments

Popular posts from this blog

Delphi change the assembly code of a running process -

json - Hibernate and Jackson (java.lang.IllegalStateException: Cannot call sendError() after the response has been committed) -

C++ 11 "class" keyword -