[R-sig-Geo] classIntervals function not finishing

[Paul Hiemstra]

Hi,

My experience with the fisher method of calculating intervals is that it 
becomes very slow if applied to a larger dataset. Your dataset is much 
much larger than what I have tried to do with style="fisher". So it is 
not strange what you are seeing. You could select a subset of the data 
to make the process somewhat faster, but "fisher" takes a lot of time.

cheers,
Paul

Edward Tomlinson schreef:
> Hi List,
>
> I am having trouble with the classIntervals function. Something seems to be
> going wrong as the function is not returning (in 8hr +).
>
> i am trying to call the function as follows
>
> t1 <- classIntervals(map$map.mapset, n=7, style="fisher")
>
> there are about 2.3 million cells in the image.
>
> The cpu goes to 100% cycle and the function never returns.
>
> I have tried the function with other styles "pretty" and "kmeans" and it
> returns fine.
>
> Is there a way i can verbose output from the function to see if i have done
> something wrong?
>
> THanks,
> Ed
>
> 	[[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>   


-- 
Drs. Paul Hiemstra
Department of Physical Geography
Faculty of Geosciences
University of Utrecht
Heidelberglaan 2
P.O. Box 80.115
3508 TC Utrecht
Phone:     +31302535773
Fax:    +31302531145
http://intamap.geo.uu.nl/~paul