[R] Using matrix as a response variable

sovboss e.sovetkin at gmail.com
Fri Jul 22 19:18:16 CEST 2011

Dear R users!

I have a problem using tune() from e1071 package. I need to to tune a neural
network where response variable is a vector. I've used this function as it
shown below and I got the error:

tune.netWhole <- tune("nnet", x, y, ranges = list(...), tunecontrol = ...)
# weights:  28
initial  value 10824.223491 
iter  10 value 8687.908464
final  value 8685.151182 
Error in crossprod(pred - true.y) : 
  dims [product 58] do not match the length of object [1218]

If someone has already handled with this problem, I'll be glad to read your
advices. Looking forward your answers.

View this message in context: http://r.789695.n4.nabble.com/Using-matrix-as-a-response-variable-tp3687296p3687296.html
Sent from the R help mailing list archive at Nabble.com.

More information about the R-help mailing list