[R] kernlab sigest

[Achim Zeileis]

Bjoern,

thanks for your mail. But when reporting problems with a contributed
package, please contact the maintainer first or at least Cc him when
writing to R-help.

The problem below is in the formula method of sigest because the frac
argument gets passed on to model.frame which causes the error. I'll
commit a fix, but you can do it also easily locally if you add the 
second line of
  m$scaled <- NULL
  m$frac <- NULL
in the formula method of sigest.

Best,
Z

On Thu, 17 Mar 2005 10:39:23 +0100 (CET) bjoern h menze wrote:

> hello,
> 
> I have the following problem setting parameter 'frac' in the sigest
> function of the kernlab package.
> 
> ## executing the ?sigest example:
> library(kernlab)
> data(spam)
> srange <- sigest(type~.,data = spam)
> 
> ## works fine...
> 
> ## setting 'frac' explicitly
> ## (in this case even to the default of .25)
> options(error=recover)
> srange <- sigest(type~.,data = spam, frac = .25)
> 
> ## fails..
> 
> Error in model.frame(formula, rownames, variables, varnames, extras,
> extranames,  :
>         variable lengths differ
> 
> Enter a frame number, or 0 to exit
> 1:sigest(type ~ ., data = spam, frac = 0.25)
> 2:sigest(type ~ ., data = spam, frac = 0.25)
> 3:.local(x, ...)
> 4:eval(m, parent.frame())
> 5:eval(expr, envir, enclos)
> 6:model.frame(data = ..1, frac = 0.25, formula = x)
> 7:model.frame
> 
> any ideas?
> 
> thank you,
> Bjoern
> 
> 
> ---
> 
> bjoern menze
> menze @ uni-hd de
> # 0170 5894150 (mobil)
> # 06221 548829 (institut)
> # 06221 470787 (heidelberg)
> bergstrasse 42  69120 heidelberg
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
> http://www.R-project.org/posting-guide.html
>