Kriging with Matplotlib

Can someone tell me how to do kriging in Matplotlib?

I have tried the contourf() function with two bivariate_normal() objects as input which produces similar looking results to what I want to archive. My data however is geo-referenced and contains > 100000 samples. Generating 100000 objects doesn't sound like a good idea to me. I searched the docs before posting, but the term "kriging" doesn't even show in the docs.

Maybe I missed something obvious? Any hint appreciated.

Thanks,
Leif

This message has been checked for viruses but the contents of an attachment
may still contain software viruses, which could damage your computer system:
you are advised to perform your own checks. Email communications with the
University of Nottingham may be monitored as permitted by UK legislation.

Leif Oppermann wrote:

Can someone tell me how to do kriging in Matplotlib?

I have tried the contourf() function with two bivariate_normal() objects as input which produces similar looking results to what I want to archive. My data however is geo-referenced and contains > 100000 samples. Generating 100000 objects doesn't sound like a good idea to me. I searched the docs before posting, but the term "kriging" doesn't even show in the docs.

Maybe I missed something obvious? Any hint appreciated.

There is no kriging implementation in matplotlib. Kriging is a special case of Gaussian processes, though, so the RandomRealizations package or my own gp package might be of use to you. You will have to do some reading to translate the entities you are familiar with (variograms, etc.) to the entities used in Gaussian processes (covariance functions, etc.).

   http://code.google.com/p/random-realizations/
   http://www.enthought.com/~rkern/cgi-bin/hgwebdir.cgi/gp/

Anand has been doing more work on RandomRealizations than I have on gp, so try it first.

···

--
Robert Kern

"I have come to believe that the whole world is an enigma, a harmless enigma
  that is made terrible by our own mad attempt to interpret it as though it had
  an underlying truth."
   -- Umberto Eco