Hi Olivier,
Yes that is the coefficient/statistic. Fukumizu, Gretton and coworkers also
have one based on RKHS covariance operators.
It would be useful to test whether any classification or regression problem
can be tractable. After all, if two variables are independent, it won't be
possible to try to classify or do regression with them.
In any case, I am willing to implement any desired feature that is already
listed.
2012/9/3 Olivier Grisel <[email protected]>
> 2012/9/3 Analytic Bastard <[email protected]>:
> > Hi guys,
> >
> > My name is Javier and I am a machine learning researcher.
> >
> > Currently, I am learning Python and found out this excellent package. I
> > would like to contribute by implementing any planned feature and by
> > implementing some ideas such as a non-linear correlation coefficient by
> > SZÉKELY and RIZZO.
>
> Hi Javier,
>
> I assume you are referring to
> http://en.wikipedia.org/wiki/Distance_correlation ?
>
> If so it could probably fit in the sklearn.metrics.pairwise module. Do
> you have any application in mind? Would this useful for building an
> affinity matrix for clustering of time series data for instance?
>
> --
> Olivier
> http://twitter.com/ogrisel - http://github.com/ogrisel
>
>
> ------------------------------------------------------------------------------
> Live Security Virtual Conference
> Exclusive live event will cover all the ways today's security and
> threat landscape has changed and how IT managers can respond. Discussions
> will include endpoint security, mobile security and the latest in malware
> threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
> _______________________________________________
> Scikit-learn-general mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
