On Wed, Nov 9, 2011 at 6:21 AM, Gael Varoquaux
<[email protected]> wrote:
> Hi list,
>
> I'd like to ask for comments on the GraphLasso pull request that I have
> put in. I think that it is ready for merge, even though it has been in
> development for a short amount of time, because I have been working on
> similar algorithms for more than two years.
>
> To give you a run-through, and try to interest you, the algorithm
> implemented is a covariance learning algorithm, but it is particularly
> useful to recover a graph of conditional independence from empirical
> data.
>
> To apply it on real data (other than brain data, which is what I do), I
> have adapted the example where we do unsupervised learning on the stock
> market:
> https://github.com/GaelVaroquaux/scikit-learn/blob/glasso/examples/applications/plot_stock_market.py
>
> I find that the result is really cool:
> http://www.flickr.com/photos/66885349@N03/6328041585/sizes/l/in/photostream/
>
> I welcome criticism and comments on the code, the documentation and the
> examples in the pull request:
> https://github.com/scikit-learn/scikit-learn/pull/431

The graph looks very good, good advertising.

I have a general question.

graph_lasso(X,....) takes the data array as an argument, but except
calculating the empirical_covariance at the beginning X is not used
anymore, as far as I could see.

The algorithm looks very interesting, but I would have cases where I
need to calculate the empirical_covariance myself (e.g. long run
covariance which is a weighted average of covariance and covariance
with lags).

Would it be possible to use an empirical covariance instead of X as
the main argument, or would you get design inconsistencies?

Thanks,

Josef

>
> Gael
>
> ------------------------------------------------------------------------------
> 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
>

------------------------------------------------------------------------------
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