ggplot a panel of histograms with histograms as subplots

Question

I have data collected at three sites, where in each these data were collected several times for several subjects.

Here's how the data look like:

set.seed(1)
df <- data.frame(site = c(rep("AA",1000),rep("BB",500),rep("CC",750)),
                 y = c(rnorm(1000,1,2),runif(500,1,3),rgamma(750,shape=1)))

#add subjects - using a function that randomly generates
#a number of subjects that adds up to their total at that site

site_a_subjects <- diff(c(0, sort(20*sample(19)), 1000))
site_b_subjects <- diff(c(0, sort(30*sample(9)), 500))
site_c_subjects <- diff(c(0, sort(40*sample(4)), 750))

#add these subjects
df$site_subjects <- c(unlist(sapply(1:20, function(x) rep(letters[x], site_a_subjects[x]))),
                  unlist(sapply(1:10, function(x) rep(letters[x], site_b_subjects[x]))),
                  unlist(sapply(1:5, function(x) rep(letters[x], site_c_subjects[x]))))

I want to plot a histogram of y per each site. This ggplot2 simple line achieves that easily:

ggplot(df, aes(x=y)) + geom_histogram(colour="black", fill="white") + facet_grid(. ~ site)

However, I additionally want to plot at each site histogram, a subplot which is a histogram of the counts of the number of each subject observation at that site. Something like adding:

hist(table(df$site_subjects[which(df$site == "AA")]))
hist(table(df$site_subjects[which(df$site == "BB")]))
hist(table(df$site_subjects[which(df$site == "CC")]))

to the three site histograms, respectively.

Any idea how can that be done?

I wonder if annotation_custom can be tweaked to achieve this?

This code will work, but only if the:

ggplotGrob(ggplot(df, aes(x=site_subjects)) + geom_bar() + theme_bw(base_size=9))

command could accept a list of ggplot objects or something like that.

here's the 'almost; solution: First figure out what is the maximum bar height among all facet histograms

ymax <- max(sapply(unique(df$site), function(x) max(hist(df$y[which(df$site == x)],plot=FALSE)$counts)))

Then:

main.plot <- ggplot(df, aes(x=y)) + geom_histogram(colour="black", fill="gray") + facet_grid(~site) + scale_y_continuous(limits=c(0,1.2*ymax))
main.plot.info <- ggplot_build(main.plot)
xmin <- min(main.plot.info$data[[1]]$x[which(main.plot.info$data[[1]]$PANEL == 1)])
xmax <- max(main.plot.info$data[[1]]$x[which(main.plot.info$data[[1]]$PANEL == 1)])
main.plot <- main.plot + annotation_custom(grob = grid::roundrectGrob(),xmin = xmin, xmax = xmax, ymin=ymax, ymax=1.2*ymax)
sub.plot <- ggplotGrob(ggplot(df, aes(x=site_subjects)) + geom_bar() + theme_bw(base_size=9))
combined.plot <- main.plot +  annotation_custom(grob = sub.plot, xmin = xmin, xmax = xmax, ymin=ymax, ymax=1.2*ymax)

And the result is:

Answer 1

Here's something reasonable:

ymax <- max(sapply(unique(df$site), function(x) max(hist(df$y[which(df$site == x)],plot=FALSE)$counts)))
sites <- unique(df$site)
plot.list <- sapply(sites, function(s) {
  main.plot = ggplot(df[which(df$site == s),], aes(x=y)) + geom_histogram(colour="black", fill="gray") + scale_y_continuous(limits=c(0,1.5*ymax))
  main.plot.info = ggplot_build(main.plot)
  xmin = min(main.plot.info$data[[1]]$x[which(main.plot.info$data[[1]]$PANEL == 1)])
  xmax = max(main.plot.info$data[[1]]$x[which(main.plot.info$data[[1]]$PANEL == 1)])
  sub.plot = ggplotGrob(ggplot(df[which(df$site == s),], aes(x=site_subjects)) + geom_bar() + theme_bw(base_size=9))
  return(ggplotGrob(main.plot + annotation_custom(grob = sub.plot, xmin = xmin, xmax = xmax, ymin=0.8*ymax, ymax=1.2*ymax)))})

grid.arrange(grobs=plot.list, ncol=3)

Answer 2

One way to do this is to create the main plot and then add each inset plot by creating viewports at each of the locations where you want an inset plot. We use functions from the grid package for these operations. Here's an example:

library(grid)

# Function to draw the inset plots 
  pp = function(var) {
    grid.draw(
      ggplotGrob(
        ggplot(df[df$site==var,], aes(site_subjects)) +
          geom_bar() +
          theme_bw(base_size=9)
      )
    )
  }  

# Function to place the viewports on the main graph
my_vp = function(x) {
  viewport(x=x, y=.8, width=0.25, height=0.2)
}

# Main plot
ggplot(df, aes(x=y)) + geom_histogram(colour="black", fill="white") + 
  facet_grid(. ~ site) +
  scale_y_continuous(limits=c(0,400))

# Draw each inset plot in a separate viewport
vp = my_vp(0.22)
pushViewport(vp)
pp("AA")
popViewport()

vp = my_vp(0.52)
pushViewport(vp)
pp("BB")
popViewport()

vp = my_vp(0.84)
pushViewport(vp)
pp("CC")