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

Posted to dev@mahout.apache.org by Kevin <ke...@gmail.com> on 2013/07/19 00:56:09 UTC

Speedup Mean Shift Clustering

Hello,

I've started to use the mean shift clustering algorithm and I am wondering
if it would be beneficial to include the functionality of
MeanShiftCanopyMapper.map(...) in the
MeanShiftCanopyCreatorMapper.map(...). This way the MapReduce job used to
create canopies from vector would not only transform all the vectors to
canopies, but also, in the same job, start merging canopies. The first
iteration of building the clusters would be done inside the
MeanShiftCanopyMapper instead of just transforming vectors to canopies.

Any inputs about this?

Thanks,
-Kevin

Re: Speedup Mean Shift Clustering

Posted by Ted Dunning <te...@gmail.com>.

Coz the streaming k-means is better and waay faster.



On Thu, Jul 18, 2013 at 4:19 PM, Kevin <ke...@gmail.com> wrote:

> Thanks for the update. Can you point me to or tell me why the mean shift
> clustering algorithm will be removed from upcoming releases?
>
>
> On Thu, Jul 18, 2013 at 7:14 PM, Sebastian Schelter <ss...@apache.org>
> wrote:
>
> > Hi Kevin,
> >
> > unfortunately, we have decided to remove the mean shift clustering in
> > upcoming releases.
> >
> >
> > 2013/7/18 Kevin <ke...@gmail.com>
> >
> > > Hello,
> > >
> > > I've started to use the mean shift clustering algorithm and I am
> > wondering
> > > if it would be beneficial to include the functionality of
> > > MeanShiftCanopyMapper.map(...) in the
> > > MeanShiftCanopyCreatorMapper.map(...). This way the MapReduce job used
> to
> > > create canopies from vector would not only transform all the vectors to
> > > canopies, but also, in the same job, start merging canopies. The first
> > > iteration of building the clusters would be done inside the
> > > MeanShiftCanopyMapper instead of just transforming vectors to canopies.
> > >
> > > Any inputs about this?
> > >
> > > Thanks,
> > > -Kevin
> > >
> >
>

Re: Speedup Mean Shift Clustering

Posted by Kevin <ke...@gmail.com>.

Thanks for the update. Can you point me to or tell me why the mean shift
clustering algorithm will be removed from upcoming releases?


On Thu, Jul 18, 2013 at 7:14 PM, Sebastian Schelter <ss...@apache.org> wrote:

> Hi Kevin,
>
> unfortunately, we have decided to remove the mean shift clustering in
> upcoming releases.
>
>
> 2013/7/18 Kevin <ke...@gmail.com>
>
> > Hello,
> >
> > I've started to use the mean shift clustering algorithm and I am
> wondering
> > if it would be beneficial to include the functionality of
> > MeanShiftCanopyMapper.map(...) in the
> > MeanShiftCanopyCreatorMapper.map(...). This way the MapReduce job used to
> > create canopies from vector would not only transform all the vectors to
> > canopies, but also, in the same job, start merging canopies. The first
> > iteration of building the clusters would be done inside the
> > MeanShiftCanopyMapper instead of just transforming vectors to canopies.
> >
> > Any inputs about this?
> >
> > Thanks,
> > -Kevin
> >
>

Re: Speedup Mean Shift Clustering

Posted by Sebastian Schelter <ss...@apache.org>.

Hi Kevin,

unfortunately, we have decided to remove the mean shift clustering in
upcoming releases.


2013/7/18 Kevin <ke...@gmail.com>

> Hello,
>
> I've started to use the mean shift clustering algorithm and I am wondering
> if it would be beneficial to include the functionality of
> MeanShiftCanopyMapper.map(...) in the
> MeanShiftCanopyCreatorMapper.map(...). This way the MapReduce job used to
> create canopies from vector would not only transform all the vectors to
> canopies, but also, in the same job, start merging canopies. The first
> iteration of building the clusters would be done inside the
> MeanShiftCanopyMapper instead of just transforming vectors to canopies.
>
> Any inputs about this?
>
> Thanks,
> -Kevin
>