[R] kernlab - laplacedot kernel error

Rincy Feng 362205285 at qq.com
Thu Jan 7 09:50:02 CET 2016

  I am using R's "kernlab" package. I am doing classification  using ksvm().
  My train data is 2455obs 5397variables and no NA data in there.

  And my code is:
  train$tag <- as.factor(train$tag)

  But it returns the following error: 
  Error in votematrix[i, ret < 0] <- votematrix[i, ret < 0] + 1 : 
  NAs are not allowed in subscripted assignments
  In addition: Warning messages:
  1: In sqrt(-round(2 * x[lowerl:upperl, ] %*% t(y) - dotbb - dota[lowerl:upperl] %*%  :
  NaNs produced
  2: ...(the same as 1)

 But when I choose another kernel, such as rbfdot, vanilladot, polydot and tanhdot, it returns the ksvm model to me.
 So can you tell me where is wrong?
 Thank you very much for your time and attention.
	[[alternative HTML version deleted]]

More information about the R-help mailing list