[R-sig-Geo] To fit variogram model

Edzer Pebesma edzer.pebesma at uni-muenster.de
Wed May 21 12:07:38 CEST 2008


Well, the answer is that this is not the way to write out and read back 
objects, as it will alter contents (such as representation by real or 
integer) and class of objects.

Please use the save/load command to save/load data in binary format, or 
dump/source to save & read back in an ascii representation.
--
Edzer

PUJAN RAJ REGMI wrote:
>  
> Dear list, I tried to fit the model variogram to the experimental semivariogram. I used the following code:
> A<-read.table(file.choose(new=FALSE), sep = ",",skip=1,header=FALSE) 
>  
> names(A) <- c("S.N","x", "y", "B1","B2","B3","B4")
>  
> library(sp)
>  
> library(gstat)
>  
> coordinates(A) = ~x+y
>  
> C<-variogram(B1~x+y+x*y+x*x+y*y,A,cutoff=700,width=12,alpha=0,tol.hor=90)
>  
> model.1 <- fit.variogram(C,vgm(4,"Sph",800,add.to=vgm(1,"Sph",40,nugget=.9)))
>  
> plot(C,model=model.1,pch=1,col=”blue”,lty=1,lwd=2,plot.numbers=F,xlab=list("Distance(h) [m]",font=1,col="black"),ylab= list(expression("Semivariogram [-]"^2), font=1,col="black"))#,ylim = c(0,6, by=1), xlim = c(0,700, by=100))
>  
> Using the above code everything went ok. But I need to save the experimental semivariogram i.e (C) and then later utilize it to fit the model semivariogram for the same. So I first save it using the following code:
> write.table(C, file = "expm_vario.csv", sep = ",", col.names = T,qmethod="double")
>  
> Then I used the following code to read the saved file expm_vario.csv and try to fit the model for it;
> B<-read.table(file.choose(new=FALSE), sep = ",",skip=0,header=T) 
> class(B)=c("gstatVariogram","data.frame","numeric")
> model.2<- fit.variogram(B,vgm(4,"Sph",500,add.to=vgm(1,"Sph",80,nugget=.9))) But I couldn't fit the model. Following was the error message I got: "Error in fit.variogram(B, vgm(4, "Sph", 500, add.to = vgm(1, "Sph", 80,  :   REAL() can only be applied to a 'numeric', not a 'integer' "The problem seems to be the numeric and integer values but I couldn't figured it out. Any help will be greatly appreciated!
>  
> Regards,
> Pujan
> _________________________________________________________________
> Give to a good cause with every e-mail. Join the i’m Initiative from Microsoft.
>
> 	[[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
>




More information about the R-sig-Geo mailing list