Population pyramid plot with ggplot2 and dplyr (instead of plyr)

Question

I am trying to reproduce the simple population pyramid from the post Simpler population pyramid in ggplot2

using ggplot2 and dplyr (instead

Answer 1

You can avoid both dplyr and plyr when making population pyramids with recent versions of ggplot2.

If you have counts of the sizes of age-sex groups then use the answer here

If your data is at the individual level (as yours is) then use the following:

set.seed(321)
test <- data.frame(v=sample(1:20,1000,replace=T), g=c('M','F'))
head(test)
#    v g
# 1 20 M
# 2 19 F
# 3  5 M
# 4  6 F
# 5  8 M
# 6  7 F

library("ggplot2")
ggplot(data = test, aes(x = as.factor(v), fill = g)) + 
  geom_bar(data = subset(test, g == "F")) + 
  geom_bar(data = subset(test, g == "M"), 
           mapping = aes(y = - ..count.. ),
           position = "identity") +
  scale_y_continuous(labels = abs) +
  coord_flip()

Answer 2

You avoid the error by specifying the argument data in geom_bar:

ggplot(data = test, aes(x = as.factor(v), fill = g)) + 
  geom_bar(data = dplyr::filter(test, g == "F")) + 
  geom_bar(data = dplyr::filter(test, g == "M"), aes(y = ..count.. * (-1))) + 
  scale_y_continuous(breaks = seq(-40, 40, 10), labels = abs(seq(-40, 40, 10))) + 
  coord_flip() 

Answer 3

To build an Age Pyramid with individual data or microdata you can use:

test <- data.frame(v=sample(1:100, 1000, replace=T), g=c('M','F'))

ggplot(data = test, aes(x = v, fill = g)) + 
  geom_histogram(data = subset(test, g == "F"), binwidth = 5, color="white", position = "identity") +
  geom_histogram(data = subset(test, g == "M"), binwidth = 5, color="white", position = "identity", 
                 mapping = aes(y = - ..count.. )) +
  scale_x_continuous("Age", breaks = c(seq(0, 100, by=5))) +
  scale_y_continuous("Population", breaks = seq(-30, 30, 10), labels = abs) +
  scale_fill_discrete(name = "Sex") +
  coord_flip() +
  theme_bw()
 

Changing the binwidth in geom_histogram() can group your data in wider categories.

Changing binwidth to 10 and adjusting the axis breaks:

ggplot(data = test, aes(x = v, fill = g)) + 
  geom_histogram(data = subset(test, g == "F"), binwidth = 10, color="white", position = "identity") +
  geom_histogram(data = subset(test, g == "M"), binwidth = 10, color="white", position = "identity", 
                 mapping = aes(y = - ..count.. )) +
  scale_x_continuous("Age", breaks = c(seq(0, 100, by = 10))) +
  scale_y_continuous("Population", breaks = seq(-100, 100, 10), labels = abs) +
  scale_fill_discrete(name = "Sex") +
  coord_flip() +
  theme_bw()