[R] Re: [R--gR] smooth="periodic.lowess"???

Achim Zeileis Achim.Zeileis at wu-wien.ac.at
Thu Oct 21 12:11:25 CEST 2004


Moved to R-help from R-SIG-gR.

On Thu, 21 Oct 2004 17:44:27 +0800 XP Sun wrote:

> hi, everyone,
> 
> this is the first time for me to use R,
> would you like to tell me how to use this command? thank you in
> advance.
> 
> fit <- principal.curve(y, plot = TRUE, smooth="periodic.lowess",
> iter=0)
> 
> when i uesd the parameter 
> 
>    smooth="periodic.lowess", 
> 
> i met a error. the message is:
> 
>    Error in cbind(...) : number of rows of matrices must match (see
>    arg 2)
> 
> any help is appreciated.

Several comments:
  1. Why did you send this request to R-SIG-gR?
     This is a SIG (special interest group) on gR (graphical models
     in R) and your request does not seem to be related to that!
  2. A better place to ask questions like the above is R-help.
     But one should read the posting guide before doing so.
       http://www.R-project.org/posting-guide.html
  3. If you read the posting guide, it will tell you that:
     If you have problems with some function, please do give a 
     reproducible example (including your version of R and OS,
     indicate add-on packages you use, etc.).

For your request above, there is nothing much that we could do. After I
had found out that this is about a function in the package princurve (do
note that there is a second CRAN package pcurve for the same task), all
I can say is that

  R> library(princurve)
  R> example(principal.curve)
  R> fit <- principal.curve(x, plot = TRUE, smooth="periodic.lowess",
       iter= 0)

gives some warnings but does not throw an error as you indicated above.
This is on Linux with today's R-devel (2.1.0 to be) with the current
CRAN version of princurve.
Z


> best, 
> 
> ¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡Sun
> ¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡xpsun at ict.ac.cn
> ¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡2004-10-21
> 
> _______________________________________________
> R-sig-gR mailing list
> R-sig-gR at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-gr
>




More information about the R-help mailing list