[R] heatmap

Liaw, Andy andy_liaw at merck.com
Mon Oct 8 16:22:16 CEST 2007


From: michael watson 
> 
> If you just want a coloured representation of your distance 
> matrix, use image()
>  
> ?image()

W/o the parens...

  
> If you want to cluster your original data and show the 
> original data (not the distances) as a heatmap then use 
> heatmap(), but you should use something like hclust() to 
> cluster the data first.

heatmap() will do the clustering for you by default (via hclust() and
dist()).  If you already have the distance matrix, then use something
like distfun=function(x) x (i.e., do-nothing) and remember to specify
symm=TRUE in the call to heatmap.

Andy
 
> ________________________________
> 
> From: r-help-bounces at r-project.org on behalf of Andreas Gruber
> Sent: Mon 08/10/2007 12:28 PM
> To: r-help at r-project.org
> Subject: [R] heatmap
> 
> 
> 
> Hi,
> 
> I am having troubles with heatmap(). I have a matrix 
> containing pairwise
> distance values and I want to plot this matrix with heatmap. I wonder
> now what distfun is for. Is a distance matrix computed from my initial
> matrix again and then plotted?
> 
> cheers,
> andreas
> 
> ______________________________________________
> 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.
> 
> ______________________________________________
> 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.
> 
> 
> 


------------------------------------------------------------------------------
Notice:  This e-mail message, together with any attachme...{{dropped:15}}



More information about the R-help mailing list