Let ggplot2 histogram show classwise percentages on y axis

Question

library(ggplot2)
data = diamonds[, c(\'carat\', \'color\')]
data = data[data$color %in% c(\'D\', \'E\'), ]

I would like to compare the histogram of

Answer 1

It seems that binning the data outside of ggplot2 is the way to go. But I would still be interested to see if there is a way to do it with ggplot2.

library(dplyr)
breaks = seq(0,4,0.5)

data$carat_cut = cut(data$carat, breaks = breaks)

data_cut = data %>%
  group_by(color, carat_cut) %>%
  summarise (n = n()) %>%
  mutate(freq = n / sum(n))

ggplot(data=data_cut, aes(x = carat_cut, y=freq*100, fill=color)) + geom_bar(stat="identity",position="dodge") + scale_x_discrete(labels = breaks) +  ylab("Percentage") +xlab("Carat")

Answer 2

You can scale them by group by using the ..group.. special variable to subset the ..count.. vector. It is pretty ugly because of all the dots, but here it goes

ggplot(data, aes(carat, fill=color)) +
  geom_histogram(aes(y=c(..count..[..group..==1]/sum(..count..[..group..==1]),
                         ..count..[..group..==2]/sum(..count..[..group..==2]))*100),
                 position='dodge', binwidth=0.5) +
  ylab("Percentage") + xlab("Carat")