# NOT RUN {
# Generate some sample data, then compute mean and standard deviation
# in each group
df <- data.frame(
gp = factor(rep(letters[1:3], each = 10)),
y = rnorm(30)
)
ds <- do.call(rbind, lapply(split(df, df$gp), function(d) {
data.frame(mean = mean(d$y), sd = sd(d$y), gp = d$gp)
}))
# The summary data frame ds is used to plot larger red points on top
# of the raw data. Note that we don't need to supply `data` or `mapping`
# in each layer because the defaults from ggplot() are used.
ggplot(df, aes(gp, y)) +
geom_point() +
geom_point(data = ds, aes(y = mean), colour = 'red', size = 3)
# Same plot as above, declaring only the data frame in ggplot().
# Note how the x and y aesthetics must now be declared in
# each geom_point() layer.
ggplot(df) +
geom_point(aes(gp, y)) +
geom_point(data = ds, aes(gp, mean), colour = 'red', size = 3)
# Alternatively we can fully specify the plot in each layer. This
# is not useful here, but can be more clear when working with complex
# mult-dataset graphics
ggplot() +
geom_point(data = df, aes(gp, y)) +
geom_point(data = ds, aes(gp, mean), colour = 'red', size = 3) +
geom_errorbar(
data = ds,
aes(gp, mean, ymin = mean - sd, ymax = mean + sd),
colour = 'red',
width = 0.4
)
# }
Run the code above in your browser using DataLab