[R] vis.gam() contour plots

David Winsemius dwinsemius at comcast.net
Tue Oct 13 04:20:34 CEST 2009


On Oct 12, 2009, at 8:20 PM, Jason Gasper wrote:

> Greetings,
>
> I have what I hope is a simple question.  I would like to change my  
> contour interval on the vis.gam( plot.type="contour")  in the mgcv  
> package.  Is this a situation where I need to modify the function or  
> is there a default value I can change?

Looking at the help page, it seemed pretty likely that passing the  
appropriate parameter to contour ought to work. Looking at the help  
page for contour you should see nlevels, andrunning a contour example  
is amenable to adding nlevels:

library(mgcv)
set.seed(0)
n<-200;sig2<-4
x0 <- runif(n, 0, 1);x1 <- runif(n, 0, 1)
x2 <- runif(n, 0, 1)
y<-x0^2+x1*x2 +runif(n,-0.3,0.3)
g<-gam(y~s(x0,x1,x2))
# display the prediction surface in x0, x1 ....
# contour examples.... vis.gam(g,  
view=c("x1","x2"),plot.type="contour",color="heat", nlevels=20)
Warning messages:
1: In plot.window(...) : "nlevels" is not a graphical parameter
2: In plot.xy(xy, type, ...) : "nlevels" is not a graphical parameter
3: In axis(side = side, at = at, labels = labels, ...) :
   "nlevels" is not a graphical parameter
4: In axis(side = side, at = at, labels = labels, ...) :
   "nlevels" is not a graphical parameter
5: In box(...) : "nlevels" is not a graphical parameter
6: In title(...) : "nlevels" is not a graphical parameter

# This does result in warnings that do not seem correct (since nlevels  
is listed as a graphics parameter in the help page of contour) but the  
desired effect seems to be occurring. I have seen such warnings many  
times before an have learned to ignore them. Whether that is the  
correct posture to assume, I am not sure.
> Thanks

--

David Winsemius, MD
Heritage Laboratories
West Hartford, CT




More information about the R-help mailing list