Hello all, I have been using the function ordirgl to plot 3D dynamic ordinations. The ordirgl function works just fine. IN fact, I was even able to write a function that allows me to identify points in the 3D plot:
identify.rgl<-function(env_var,ord,dim1,dim2,dim3) { tmp<-select3d(button="left") tmp.keep<-tmp(ord[,dim1],ord[,dim2],ord[,dim3]) env_var[tmp.keep=="TRUE"] } where env_var = a variable to be identified (e.g. plot IDs as in > row.names(dataframe)) ord = ordination points or scores created using a function such as metaMDS or nmds) that is recognized by points or scores dim1 = dimension 1 (e.g., 1) dim2 = dimension 2 (e.g., 2) dim 3 = dimension 3 (e.g, 3 e.g., > identify.rgl(row.names(vegmat),veg_nmds$points,1,2,3) My issue is that I would like to use the points3d function to add points of different colors and sizes to the dynamic 3D plot created by using ordirgl. In my case the different colored and sized points represent different clusters from the results of the Partitioning Around Mediods (pam) clustering function (from library cluster). I have used this with success in the past (two years back), but can't get it to work properly now. An example of the code I have used in the past is: > points3d(veg_nmds$points[,1],veg_nmds$points[,2],veg_nmds$points[,3],display = "sites",veg_pam12$clustering=="1",col=2,size=3) The code above is intended to add the points from cluster 1 to the nmds plot in the color red and size 3. Anyone have an ideas? Thanks, Aaron [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.