how can i fix this problem ? I tried to train a simple linear VSM classifier

Question

library(kernlab)
 letter_classifier <- ksvm(letter ~ ., data = letters_train,
                       kernel = "vanilladot")

>  Setting default kernel parameters   Error in .local(x, ...) :    No
> Support Vectors found. You may want to change your parameters In
> addition: Warning message: In .local(x, ...) : NAs introduced by
> coercion

Opeyemi Olomola · Answer

Check the structure of letters_train.
SVM is for continuous and categorical variable analysis, and surely one of your variables (letter) is likely still a character variable. Change it to factor and try again.

how can i fix this problem ? I tried to train a simple linear VSM classifier

One Answer

Add your own answers!

Ask a Question