Re: [R] the number of cluster

2005-04-06 Thread msck9
Are there any package that is using v-fold cross-validation algorithm
to test the number the clusters? 

Thanks,
Ming
On Sat, Mar 19, 2005 at 12:44:42PM +0100, Uwe Ligges wrote:
 XP Sun wrote:
 
  hi, all,
  
  how to decide the number of cluster before you use kmeans and hclust? 
  thank you in advance!
 
 Depends on your criterion. Best idea is always to use the brain and
 think about how many clusters are sensible for the particular
 task/problem/data.
 For hclust, you can also look at the dendrogram's height and distances
 of dissimilarities in order to cut.
 
 Uwe Ligges
 
 
  best
  -xpsun
  
  __
  R-help@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
 
 __
 R-help@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

__
R-help@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


Re: [R] the number of cluster

2005-03-19 Thread Uwe Ligges
XP Sun wrote:

 hi, all,
 
   how to decide the number of cluster before you use kmeans and hclust? 
   thank you in advance!

Depends on your criterion. Best idea is always to use the brain and
think about how many clusters are sensible for the particular
task/problem/data.
For hclust, you can also look at the dendrogram's height and distances
of dissimilarities in order to cut.

Uwe Ligges


 best
 -xpsun
 
 __
 R-help@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

__
R-help@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


[R] the number of cluster

2005-03-18 Thread XP Sun
hi, all,

how to decide the number of cluster before you use kmeans and hclust? 
thank you in advance!

best
-xpsun

__
R-help@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