[R-sig-Geo] Parallelized kriging in R (gstat/intamap)
pierre.roudier at gmail.com
Tue Dec 7 20:36:44 CET 2010
Jon and Edzer,
Sorry, I was a bit confused with how to specify the nclus option in
the intamap methods. This is clearer now.
Edzer, for some reason I thought it was not possible to parallelize
kriging in gstat so simply. Thanks for the pointer, I modified the
demo snow.R and adapted it to suit my needs.
Thank you both for the work on intamap - it really looks good.
2010/12/6 Edzer Pebesma <edzer.pebesma at uni-muenster.de>:
> The documentation for package intamap suggest that you first download
> and load package doSNOW from CRAN, and then pass the nclus parameter
> with a number larger than 1, as argument:
> interpolate(..., optList=list(nclus=2))
> Looking at the code, it tries to set up nodes on localhost, so for
> distributing load over a cluster composed of different machines, you (or
> we) would have to modify the code.
> Package gstat has a demo script, demo(snow), that shows how to
> distribute predictions over multiple hosts.
> On 12/06/2010 03:41 AM, Pierre Roudier wrote:
>> Dear list,
>> I've been wanting to parallelize kriging using R - on a cluster.
>> I am not aware of any parallelized method in gstat (which I'm an avid
>> and happy user), and I'm just discovering the intamap package (which
>> looks awesome) which seems to have that sort of capability (using the
>> nclus parameter). However, I don't really get how to use it.
>> Any pointers?
>> R-sig-Geo mailing list
>> R-sig-Geo at r-project.org
> Edzer Pebesma
> Institute for Geoinformatics (ifgi), University of Münster
> Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251
> 8333081, Fax: +49 251 8339763 http://ifgi.uni-muenster.de
> http://www.52north.org/geostatistics e.pebesma at wwu.de
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
More information about the R-sig-Geo