***** To join INSNA, visit http://www.insna.org ***** Hi Ian, I can show you code for igraph -- would need to think about it a bit more in statnet, but the principles are the same. Not elegant, no doubt, but it works. There may, for example, be a simpler way to do this with a merge of some sort. I just did this on a graph I had handy. I colored the names according to communities (found using the spinglass.community algorithm) using the colorspace package. Given a graph g (370 vertices, 1565 edges): spc <- spinglass.community(g, spins=20) cols <- rainbow_hcl(10, c = c(80, 30), l = c(30, 90)) ## colorspace g.layout <- layout.fruchterman.reingold(g) ccc <- sort(betweenness(g), decreasing = TRUE) thebigs <- names(ccc[1:20]) bignames <- rep(NA,370) aaa <- rep(NA, 20) for(i in 1:20) aaa[i] <- which(thebigs[i] == V(g)$name) bignames[aaa] <- thebigs V(g)$bignames <- bignames plot(g, vertex.label=V(g)$bignames, layout=g.layout, vertex.size=0, vertex.color="white", vertex.frame.color="white", vertex.label.cex=0.75, vertex.label.color=cols[spc$membership], edge.color=rgb(209,209,209,70, max=255), edge.width=2) You can alter the vertex label size, for example passing a vector argument to the vertex.label.cex argument. Hope this helps. Cheers, Jamie -- James Holland Jones Associate Professor of Anthropology & Senior Fellow, Woods Institute for the Environment 450 Serra Mall Building 50 Stanford, CA 94305-2034 phone: 650-721-2484 fax: 650-725-0605 email: [log in to unmask] url: http://www.stanford.edu/~jhj1 > On Aug 23, 2015, at 4:33 PM, Ian McCulloh <[log in to unmask]> wrote: > > ***** To join INSNA, visit http://www.insna.org ***** > Hello! > > I'm doing an SNA project on an organization of about 120 nodes. I am using Statnet in R. I want to make an SNA visualization where I only visualize the labels for the most central 10 or 20 nodes. Does anyone have some R code that does this? > > For context and example, here is code I have that will allow me to scale the node label based on centrality, and I can color the edges gray for contrast. > > gplot(gn, label.cex=node.scale(node.scale(betweenness(gn))), label.col=1, label=network.vertex.names(gn), vertex.col=2, edge.col=8, vertex.cex=0.5) > > I'd also be interested in iGraph implementation, but I'm using statnet for this project. > > Kind Regards, > > Ian > > > _____________________________________________________________________ SOCNET is a service of INSNA, the professional association for social network researchers (http://www.insna.org). To unsubscribe, send an email message to [log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of the message. _____________________________________________________________________ SOCNET is a service of INSNA, the professional association for social network researchers (http://www.insna.org). To unsubscribe, send an email message to [log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of the message.