Capital in the 21st Century: Chapter 7
Data provenance
The data were downloaded as Excel files from: http://piketty.pse.ens.fr/en/capital21c2.
Loading relevant libraries and data
This document depends on the xlsx, reshape2, and ggplot2 packages.
Below, we separately load the data required to make each figure.
library(ggplot2)
library(xlsx)
library(reshape2)
#First we'll make a quick function for melting and renaming tables
melt_name<-function(x,name,id.vars="Year",...){
#if all measurements are missing for a given year, we will generate a versionof the figure with interpolations for that year.
#We'll show both interpolated and non interpolated figures
NArows<-apply(x,1,function(r) {all(is.na(r[-1]))} )
out_interp<-melt(x[!NArows,],id.vars=id.vars,...)
out_raw<-melt(x,id.vars=id.vars,...)
list(out_interp,name,out_raw)
}
#####################################
# Spread Sheet TS7.7
# Inequality of labor income across time and space
#####################################
#Gini-Lorenz curves
ts7.7 = read.xlsx("../_data/Chapter7TablesFigures.xlsx",sheetName="TS7.7",rowIndex=8:108,colIndex=1:3,header=FALSE)
names(ts7.7) <- c("x","linear","continuous")Recreate Figures
There is basically only one figure in this chapter, the rest are all tables
baseline <- expression(paste("45",degree," degree line (perfect equality)"))
ggplot(data=ts7.7)+
geom_point(aes(x=x,y=x,color= 'black')) +
geom_point(aes(x=x,y=linear,color= 'red')) +
geom_point(aes(x=x,y=continuous,color= 'green')) +
ylab('Total income or capital share owned by the poorest x%') +
xlab('Curve 1 assumes that the poorest 90% and the richest 10% own 50% of total income or capital each, and that both groups are homogenous \n (hence a linear curve); curve 2 assumes a continuous distribution') +
scale_color_discrete("Legend", labels = c(baseline, "Curve #1: distribution with 2 groups", "Curve #2: continuous distribution"))