Except last I checked numpy.linalg doesn't have an efficient method for retrieving only a few PCA components.
So yeh, you can do PCA but it will be *really* slow on most of the types of problems that PCA is usually used for.
You need something like an ARPACK wrapper, which I think they have in the scipy.sandbox.

--bb

On 6/25/07, Matthieu Brucher < matthieu.brucher@gmail.com> wrote:
Hi,

You have everything you need for PCA in numpy.linalg.

Matthieu

2007/6/21, Alex Torquato S. Carneiro <archsheep@yahoo.com.br >:
I'm doing some projects in Python (system GNU / Linux - Ubuntu 7.0) about image processing. I'm needing a implementation of PCA, prefer to library for apt-get.

Thanks.
Alex.



Novo Yahoo! CadÍ? - Experimente uma nova busca.

_______________________________________________
Numpy-discussion mailing list
Numpy-discussion@scipy.org
http://projects.scipy.org/mailman/listinfo/numpy-discussion



_______________________________________________
Numpy-discussion mailing list
Numpy-discussion@scipy.org
http://projects.scipy.org/mailman/listinfo/numpy-discussion