R help - Apr 2009 - fclustindex, e1071 package

Hi,
 
I'm using e1071 package to do fuzzy cluster analysis. My dataset (ra) has
5237 observations and 2 variables - depth and velocity. I used fuzzy cmeans
to create 6 fuzzy classes.
 
>ra.flcust6<-cmeans(ra,6,iter.max=100,verbose=F,dist="euclidean",method="cmea
ns",m=1.7,rate.par=NULL,weights=1)

 

I would like to calculate the value of all the fuzzy validity measures using
the flcustIndex function. However it returned the following error:

 
> fclustIndex(ra.flcust6,ra,index="all")
Error in solve.default(scatter[, , i]) : 
  Lapack routine dgesv: system is exactly singular


 

Please could anyone explain what this means and what I have done wrong?

 

thanks

Caroline Wallis

 


	[[alternative HTML version deleted]]

Caroline Wallis wrote:
> Hi,
>  
> I'm using e1071 package to do fuzzy cluster analysis. My dataset (ra)
has
> 5237 observations and 2 variables - depth and velocity. I used fuzzy cmeans
> to create 6 fuzzy classes.
>  
> 
>>
ra.flcust6<-cmeans(ra,6,iter.max=100,verbose=F,dist="euclidean",method="cmea
> ns",m=1.7,rate.par=NULL,weights=1)
> 
>  
> 
> I would like to calculate the value of all the fuzzy validity measures
using
> the flcustIndex function. However it returned the following error:
> 
>  
> 
>> fclustIndex(ra.flcust6,ra,index="all")
> Error in solve.default(scatter[, , i]) : 
>   Lapack routine dgesv: system is exactly singular
> 
> 
>  
> 
> Please could anyone explain what this means and what I have done wrong?

Well, it tells you that the matrix is exatcly singular. At first I'd 
check your data if this is plausible.

Uwe Ligges




>  
> 
> thanks
> 
> Caroline Wallis
> 
>  
> 
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.