[R] r kernlab find best cost parameter automatically

Luigi Marongiu m@rong|u@|u|g| @end|ng |rom gm@||@com
Thu May 23 09:19:34 CEST 2019


Dear all,
I am using kernlab to implement an SVM analysis. The model I am
building has the syntax:

`ksvm(<y> ~ <x>, data = <dataframe>, type = "C-svc", kernel =
"rbfdot", kpar = "automatic", C = <k>, prob.model = TRUE)`

Here, I can use different values of `k` to give different costs to the
model. Each time I give a different k, the results obviously change.
Would be possible to automate the selection of the best <k> value?
Thank you

-- 
Best regards,
Luigi



More information about the R-help mailing list