Recreating Gapminder World Map with R & ggplot2

January 11, 2011
By

(This article was first published on Jason Bryer » R, and kindly contributed to R-bloggers)


Gapminder has posted an interesting chart using world development indicators from the World Bank. I thought it would be a good exercise to recreate this chart using R and ggplot2. While playing with the data, not log transforming GDP provides some interesting, and perhaps different, interpretation. The R script and graphics are below.

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
library(ggplot2)
library(reshape)
 
countries = read.csv('Data/WDI_GDF_Country.csv', strip.white=TRUE)
worldData = read.csv('Data/WDI_GDF_Data.csv', strip.white=TRUE)
 
worldData2 = worldData[which(worldData$Series.Code %in% c('NY.GDP.MKTP.KD', 'SE.XPD.TOTL.GD.ZS', 'SP.DYN.LE00.IN', 'SP.POP.TOTL')), c('Series.Code', 'Series.Name', 'Country.Name', 'Country.Code', 'X2008')]
worldData2 = merge(worldData2, countries[,c('Country.Code', 'Region')], by='Country.Code')
worldData2 = worldData2[which(worldData2$Region != 'Aggregates'),]
worldData2$Series.Name = as.factor(as.character(worldData2$Series.Name))
worldData2$Region = as.factor(as.character(worldData2$Region))
worldData3 = cast(worldData2, Country.Name + Region ~ Series.Name, mean, value='X2008')
names(worldData3) = c('Country', 'Region', 'GDP', 'Life.Expectancy', 'Population', 'Education')
 
worldData3$GDP.log = log(worldData3$GDP)
worldData3$GDP = worldData3$GDP / 1000000000 #Billions
worldData3$Population = worldData3$Population / 1000000 #Millions
 
p = ggplot(worldData3, aes(x=GDP, y=Life.Expectancy, label=Country))
p + geom_point(aes(size=Population, colour=Region), stat='identity', alpha=.6) + geom_text(hjust=-.2, vjust=.5, size=2) + scale_size_continuous('Population (Millions)', to=c(1,20)) + xlab('Gross Domestic Product (billions)') + ylab('Life Expectancy at birth (years)')
 
p = ggplot(worldData3, aes(x=GDP.log, y=Life.Expectancy, label=Country))
p + geom_point(aes(size=Population, colour=Region), stat='identity', alpha=.6) + geom_text(hjust=-.2, vjust=.5, size=2) + scale_size_continuous('Population (Millions)', to=c(1,20)) + xlab('Gross Domestic Product (log scale)') + ylab('Life Expectancy at birth (years)')
 
worldData4 = worldData3[which(worldData3$GDP < 2000),]
p = ggplot(worldData4, aes(x=GDP, y=Life.Expectancy, label=Country))
p + geom_point(aes(size=Population, colour=Region), stat='identity', alpha=.6) + geom_text(hjust=-.2, vjust=.5, size=2) + scale_size_continuous('Population (Millions)', to=c(1,20)) + xlab('Gross Domestic Product (billions)') + ylab('Life Expectancy at birth (years)')
 
gworldData = worldData[which(worldData$Series.Code %in% c('NY.GDP.MKTP.KD', 'SP.DYN.LE00.IN', 'SP.POP.TOTL')), c('Series.Code', 'Series.Name', 'Country.Name', 'Country.Code', 'X2000', 'X2001', 'X2002', 'X2003', 'X2004', 'X2005', 'X2006', 'X2007', 'X2008')]
gworldData = merge(gworldData, countries[,c('Country.Code', 'Region')], by='Country.Code')
gworldData = gworldData[which(gworldData$Region != 'Aggregates'),]
gworldData$Series.Name = as.factor(as.character(gworldData$Series.Name))
gworldData$Region = as.factor(as.character(gworldData$Region))
gworldData = melt(gworldData, id=c('Country.Code', 'Series.Code', 'Series.Name', 'Country.Name', 'Region'))
gworldData = cast(gworldData, Country.Name + Region + variable ~ Series.Name, mean, value='value')
names(gworldData) = c('Country', 'Region', 'Year', 'GDP', 'Life.Expectancy', 'Population')
gworldData$GDP = gworldData$GDP / 1000000000 #Billions
gworldData$Population = gworldData$Population / 1000000 #Millions
gworldData$Year = as.integer(substr(gworldData$Year, 2,5))
head(gworldData)
m = gvisMotionChart(gworldData, idvar='Country', timevar='Year')
cat(m$html$chart)
plot(m)

To leave a comment for the author, please follow the link and comment on their blog: Jason Bryer » R.

R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...



If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Tags: ,

Comments are closed.

Sponsors

Mango solutions



RStudio homepage



Zero Inflated Models and Generalized Linear Mixed Models with R

Quantide: statistical consulting and training

datasociety

http://www.eoda.de





ODSC

ODSC

CRC R books series





Six Sigma Online Training









Contact us if you wish to help support R-bloggers, and place your banner here.

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)