You are viewing a plain text version of this content. The canonical link for it is here.

Posted to user@mahout.apache.org by Zhongming cai <ca...@yahoo.co.uk> on 2010/08/19 16:40:26 UTC

Means-Shift clustering

Hi,

Does anyone know a Means-Shift clustering algorithm implementation (preferrable in Java) which is not hadoop based ?

Thanks,

Zhongming

Re: Means-Shift clustering

Posted by Jeff Eastman <jd...@windwardsolutions.com>.

  The Mahout implementation can be run sequentially, in memory, using 
the Java reference implementation by adding an execution method argument 
(-xm sequential) to the command line invocation. Look at the 
MeanShiftCanopyClusterer.clusterPoints() for a stand-alone Java 
reference implementation.

On 8/19/10 7:40 AM, Zhongming cai wrote:
> Hi,
>
> Does anyone know a Means-Shift clustering algorithm implementation (preferrable in Java) which is not hadoop based ?
>
> Thanks,
>
> Zhongming
>
>
>
>
>
>