[R] memory issue trying to solve too large a problem using hclust

[David Smith]

> Sorrowly, I did not have time to try it, but it seems that I would
> have to start using more R and less S-Plus, since "as.dist()" does
> not exist in S-Plus (maybe it works with dist, I have to try)

With S-PLUS's hclust, you can just pass in the correlation matrix:

  d <- 1-cor(x)^2
  hc <- hclust(d)

You could always do as.dist <- I in S-PLUS if you want a cross-system
script.

# David

--
David M Smith <dsmith at insightful.com>
S-PLUS Product Marketing Manager, Insightful Corp, Seattle WA
Tel: +1 (206) 283 8802 x360
Fax: +1 (206) 283 0347

Insightful Corporation provides analytical solutions leveraging
S-PLUS, StatServer, S-PLUS Analytic Server and consulting services.
See www.insightful.com for details.

> -----Original Message-----
> From: owner-r-help at stat.math.ethz.ch
> [mailto:owner-r-help at stat.math.ethz.ch]On Behalf Of cstrato at EUnet.at
> Sent: Wednesday, December 05, 2001 10:37
> To: carlos.ortega at minorplanet.com; 'Aboubakar Maitournam';
> r-help at stat.math.ethz.ch
> Subject: Re: [R] memory issue trying to solve too large a problem using
> hclust
>
>
> Dear all
>
> I would like to thank all people who have responded (Carlos Ortega,
> Aboubakar Maitournam, Ron Wherens, Christian Henning and Andy Liaw).
> Some have sent their answers to my mail-address only, so I am never
> quite sure if they want me to foreward their answers to r-help or
> not. In contrast to S-news, at R most people respond to r-help,
> which I find preferable.
>
> I am especially greatful to Andy Liaw ,who mentioned the following
> possibility to use correlation in hclust:
>   d <- 1-cor(x)^2
>   hc <- hclust(as.dist(d))
> Sorrowly, I did not have time to try it, but it seems that I would
> have to start using more R and less S-Plus, since "as.dist()" does
> not exist in S-Plus (maybe it works with dist, I have to try)
>
> Best regards
> Christian Stratowa
>
> Carlos Ortega wrote:
>
> > Hello,
> >
> > I am wondering if the "dna library 0.2" that Proffesor Jim Landsey made
> > available on March 2000 (www.luc.ac.be/~jlindsey/rcode.html )
> as well as his
> > papers ("An Introduction to Markov Models in Molecular Biology. (2000)
> > available at http://alpha.luc.ac.be/~lucp0753/manuscripts.html
> ) are useful
> > for your purposes.
> >
> > Thanks,
> > Carlos Ortega.
> >
> > -----Mensaje original-----
> > De: owner-r-help at stat.math.ethz.ch
> > [mailto:owner-r-help at stat.math.ethz.ch]En nombre de Aboubakar Maitournam
> > Enviado el: miercoles, 05 de diciembre de 2001 11:15
> > Para: cstrato at EUnet.at; r-help at stat.math.ethz.ch
> > Asunto: Re: [R] memory issue trying to solve too large a problem using
> > hclust
>
> -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.
> -.-.-.-.-.-.-
> r-help mailing list -- Read
http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._.
_._

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._