[R] KMedians clustering in R

[Shubha Vishwanath Karanth]

Thanks all. But I was looking for "KMedian" algorithm and not the "KMedoids" algorithm. The wiki says, " Note that this algorithm is often confused with k-medoids, which finds the optimal medoid, not median, for each cluster. (A medoid is an actual point from the dataset; a median is the mathematical median calculated separately for each dimension.)"

Any package which does KMedian clustering algorthm? Many Thanks.
 
Regards,
Shubha.

-----Original Message-----
From: Christian Hennig [mailto:chrish at stats.ucl.ac.uk] 
Sent: Thursday, September 16, 2010 9:32 PM
To: Shubha Vishwanath Karanth
Cc: r-help at r-project.org; r-help at stat.math.ethz.ch
Subject: Re: [R] KMedians clustering in R

pam/clara in package cluster are probably as close to it as you can be.

There is no unique definition of a multivariate median and therefore there 
is no unique definition of "k-medians", but pam/clara is one possible 
version of it. (Of course if you think of k-medians as defined in a 
specific paper, it may still be something slightly different.)

Christian

On Thu, 16 Sep 2010, Shubha Vishwanath Karanth wrote:

> Hi R,
>
> Is there a package in R to perform KMedian clustering?
>
> Thanks.
> Shubha
> This e-mail may contain confidential and/or privileged i...{{dropped:10}}
>
> ______________________________________________
> 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.
>

*** --- ***
Christian Hennig
University College London, Department of Statistical Science
Gower St., London WC1E 6BT, phone +44 207 679 1698
chrish at stats.ucl.ac.uk, www.homepages.ucl.ac.uk/~ucakche
This e-mail may contain confidential and/or privileged i...{{dropped:10}}