On Wed, Oct 13, 2010 at 12:07 PM, Samuel GARCIA <sgarcia@olfac.univ-lyon1.fr> wrote:

I will use automatic clustering. I am just trying AffinityPropagation. I
will need GMM too. But I will test others.

Cool. I am currently working on the GMM module. It can be a bit slow right now if you are using tied or full diagonals, but this will hopefully be fixed in the next release. Also, don't hesitate to report bugs of feature requests, it is very valuable for us to have feedback from people with different backgrounds :-)



I am absolutely not an expert in this domain and having a good python
package for entering in the clustering-learning word is just like
paradise for a beginner, thank you.

For NDViewer, here at the steps 5:
you have an old screenshot of the object.

But seeing a screenshot have not many sense because hight dimension can
be seen  in mouvement!
In the original RGGOBI package you have a movie to make an idea.


On 13/10/2010 11:30, Olivier Grisel wrote:
> 2010/10/13 Samuel GARCIA<sgarcia@olfac.univ-lyon1.fr>:
>> Hi list,
>> good news.
>> I was waiting this release for integrating new stuff in my project
>> (OpenElectrophy), in which I need your package for spikesorting.
>> Congratulation for this workfor all dev.
> Thanks for the feedback. Which algos / features of scikit-learn are
> you using in particular?

Samuel Garcia
Laboratoire de Neurosciences Sensorielles, Comportement, Cognition.
CNRS - UMR5020 - Universite Claude Bernard LYON 1
Equipe logistique et technique
50, avenue Tony Garnier
69366 LYON Cedex 07
Tél : 04 37 28 74 24
Fax : 04 37 28 76 01

Beautiful is writing same markup. Internet Explorer 9 supports
standards for HTML5, CSS3, SVG 1.1,  ECMAScript5, and DOM L2 & L3.
Spend less time writing and  rewriting code and more time creating great
experiences on the web. Be a part of the beta today.
Scikit-learn-general mailing list