2011/11/11 Mathieu Blondel <[email protected]>:
> GraphLasso seems really neat (and the associated CV object should
> prove very useful).
>
> I had a look at the stock market example but I am a bit confused by
> the fact that the clustering, graph structure and 2d-embedding seemed
> to be learned independently although they are clearly related
> problems. I see that the (dense) correlation matrix is used as input
> to affinity propagation. Wouldn't it be better if we used the partial
> correlations learned by GraphLasso directly? This way, the cluster
> centers and the edge structure would be more related. Likewise, the
> graph structure and the clustering are not used at all for learning
> the embedding, which seems like a pity.

Indeed I thought the same, but as the current result is already good /
interesting ...

> Also, I wonder if once we have
> the graph structure, couldn't we get away with just using a graph
> drawing algorithm?

Yes but that requires an external dependency on something like dot or
neato from GraphViz. It's better not to have such a dependency for
building the documentation. But we could ad a note and maybe a helper
python function to generate a ".dot" file from an adjacency matrix +
node labels.

-- 
Olivier
http://twitter.com/ogrisel - http://github.com/ogrisel

------------------------------------------------------------------------------
RSA(R) Conference 2012
Save $700 by Nov 18
Register now
http://p.sf.net/sfu/rsa-sfdev2dev1
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to