ggplot2: Adding sample size information to x-axis tick labels

Question

This question is related to Create custom geom to compute summary statistics and display them *outside* the plotting region (NOTE: All functions have been simplified; no error

Answer 1

My solution might be a little simple but it works well.

Given an example with faceting by am I start by creating labels using paste and \n.

mtcars2 <- mtcars %>% 
  group_by(cyl, am) %>% mutate(n = n()) %>% 
  mutate(label = paste0(cyl,'\nN = ',n))

I then use these labels instead of cyl in the ggplot code

ggplot(mtcars2,
   aes(x = factor(label), y = mpg, color = factor(label))) + 
  geom_point() + 
  xlab('cyl') + 
  facet_wrap(~am, scales = 'free_x') +
  theme(legend.position = "none")

To produce something like the figure below.

Answer 2

I have updated the EnvStats package to include a stat called stat_n_text which will add the sample size (the number of unique y-values) below each unique x-value. See the help file for stat_n_text for more information and a list of examples. Below is a simple example:

library(ggplot2)
library(EnvStats)

p <- ggplot(mtcars, 
  aes(x = factor(cyl), y = mpg, color = factor(cyl))) + 
  theme(legend.position = "none")

p + geom_point() + 
  stat_n_text() + 
  labs(x = "Number of Cylinders", y = "Miles per Gallon")

Answer 3

You can print the counts below the x-axis labels using geom_text if you turn off clipping, but you'll probably have to tweak the placement. I've included a "nudge" parameter for that in the code below. Also, the method below is intended for cases where all the facets (if any) are column facets.

I realize you ultimately want code that will work inside a new geom, but perhaps the examples below can be adapted for use in a geom.

library(ggplot2)
library(dplyr)

pgg = function(dat, x, y, facet=NULL, nudge=0.17) {

  # Convert x-variable to a factor
  dat[,x] = as.factor(dat[,x])

  # Plot points
  p = ggplot(dat, aes_string(x, y)) +
    geom_point(position=position_jitter(w=0.3, h=0)) + theme_bw() 

  # Summarise data to get counts by x-variable and (if present) facet variables
  dots = lapply(c(facet, x), as.symbol)
  nn = dat %>% group_by_(.dots=dots) %>% tally

  # If there are facets, add them to the plot
  if (!is.null(facet)) {
    p = p + facet_grid(paste("~", paste(facet, collapse="+")))
  }

  # Add counts as text labels
  p = p + geom_text(data=nn, aes(label=paste0("N = ", nn$n)),
                    y=min(dat[,y]) - nudge*1.05*diff(range(dat[,y])), 
                    colour="grey20", size=3.5) +
    theme(axis.title.x=element_text(margin=unit(c(1.5,0,0,0),"lines")))

  # Turn off clipping and return plot
  p <- ggplot_gtable(ggplot_build(p))
  p$layout$clip[p$layout$name=="panel"] <- "off"
  grid.draw(p)

}

pgg(mtcars, "cyl", "mpg")
pgg(mtcars, "cyl", "mpg", facet=c("am","vs"))

Another, potentially more flexible, option is to add the counts to the bottom of the plot panel. For example:

pgg = function(dat, x, y, facet_r=NULL, facet_c=NULL) {

  # Convert x-variable to a factor
  dat[,x] = as.factor(dat[,x])

  # Plot points
  p = ggplot(dat, aes_string(x, y)) +
    geom_point(position=position_jitter(w=0.3, h=0)) + theme_bw() 

  # Summarise data to get counts by x-variable and (if present) facet variables
  dots = lapply(c(facet_r, facet_c, x), as.symbol)
  nn = dat %>% group_by_(.dots=dots) %>% tally

  # If there are facets, add them to the plot
  if (!is.null(facet_r) | !is.null(facet_c)) {

    facets = paste(ifelse(is.null(facet_r),".",facet_r), " ~ " , 
                   ifelse(is.null(facet_c),".",facet_c))

    p = p + facet_grid(facets)
  }

  # Add counts as text labels
  p + geom_text(data=nn, aes(label=paste0("N = ", nn$n)),
                y=min(dat[,y]) - 0.15*min(dat[,y]), colour="grey20", size=3) +
    scale_y_continuous(limits=range(dat[,y]) + c(-0.1*min(dat[,y]), 0.01*max(dat[,y])))
}

pgg(mtcars, "cyl", "mpg")
pgg(mtcars, "cyl", "mpg", facet_c="am")
pgg(mtcars, "cyl", "mpg", facet_c="am", facet_r="vs")