Question

Using the radial.plot function in library(plotrix) (p.135-8) and drawing on the helpful post in CrossValidated, I have made this spiderweb plot.

QUESTION

The plot displays the difference in mean between a treatment and a comparison group per item. Yet, I am particularly interested in POSITIVE change. Hence, I would like to highlight the values >= 0. To this end, I seek to

• paint the circle-line for 0-values black

• make the area for values <= 0, i.e. inside the 0-circle, more transparent (“lighter”).

I am happy to share the code I used to make the spiderweb plot:

items.M<-c(-0.15,0.05,0.12,-0.12,-0.02,0.27,0.53,0,-0.33,0.19,0.34)
items.J<-c(-0.09,0.08,1.63,-0.1,-0.1,-0.09,0.15,0.05,-0.12,0.51,0.02)
items.names<-c("item 1", "item 2", "item 3", "item 4", "item 5", "item 6", "item 7", "item 8", "item n1", "item n2", "item n3")


spider.data<- rbind(items.M, items.J)


library(plotrix)
radial.plot(spider.data,
  labels=items.names,
  rp.type="p",
  radial.lim=c(-0.4,1.7),
  poly.col=c(rgb(255/255, 215/255, 0, .8), rgb(0, 0, 1, .8)),
  line.col=c("black", "black"),
  lwd=1)

Many thanks for your help.

Answer 1

For transparency you can play with The alpha graphical parameter setting of the grid package. First I use the gridBase package to combine grid with graphics.

You get something like this:

library(gridBase)
vps <- baseViewports()
vp <- vps$plot
vp$gp <-gpar(alpha=0.3)   # you can play with alpha here
pushViewport(vp)
grid.circle(r=unit(vp$xscale/6,'native'),    # /6 to get the small circle
         gp=gpar(fill='white',col='black'))
upViewport()
pushViewport(vps$plot)
grid.circle(r=unit(vp$xscale/6,'native'),
        gp=gpar(fill='NA',col='black',lwd=2))  ## line width = 2 to show the black line effect
upViewport()