Unemployment revisited
[This article was first published on Wiekvoet, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
Approximately a year ago I made a post graphing unemployment in Europe and other locations. I have always wanted to do this again, not because the R-code would be so interesting, but just because I wanted to see the plots. As time progressed I attempted not to do this in R, but in Julia. I could not get it good enough in Julia, so this is, alas, the R version. Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
Data
Data from Eurostat. Or, if you are lazy, Google une_rt_m, which is the name of the table. There is a bit of pre-processing of the data, mostly getting names of countries decent for plotting. The plots shown are unemployment and its first derivative, both smoothed.Plots
Smoothed data
First derivative
Code
library(ggplot2)
library(KernSmooth)
library(plyr)
library(scales) # to access breaks/formatting functions
r1 <- read.csv("une_rt_m_1_Data.csv",na.strings=':')
levels(r1$GEO) <- sub(' countries)',')' ,levels(r1$GEO),fixed=TRUE)
levels(r1$GEO) <- sub('European Union','EU' ,levels(r1$GEO))
levels(r1$GEO)[levels(r1$GEO)==’Euro area (EA11-2000, EA12-2006, EA13-2007, EA15-2008, EA16-2010, EA17-2013, EA18)’] <- "EAll"
levels(r1$GEO)[levels(r1$GEO)==’United Kingdom’] <- 'UK'
levels(r1$GEO)[levels(r1$GEO)==’United States’] <- 'US'
levels(r1$GEO)[levels(r1$GEO)==’Germany (until 1990 former territory of the FRG)’] <- 'Germany'
levels(r1$GEO)
grep(’12|13|15|16|17|25|27′,x=levels(r1$GEO),value=TRUE)
r1 <- r1[!(r1$GEO %in% grep('12|13|15|16|17|25|27',x=levels(r1$GEO),value=TRUE)),]
r1$GEO <- factor(r1$GEO)
r1$Age <- factor(r1$AGE,levels=levels(r1$AGE)[c language="(2,1,3)"][/c])
r1$Date <- as.Date(paste(gsub('M','-',as.character(r1$TIME)),'-01',sep=''))
#
maxi <- aggregate(r1$Value,by=list(GEO=r1$GEO),FUN=max,na.rm=TRUE)
parts <- data.frame(
low = maxi$GEO[maxi$x
)
#ggplot(r1[r1$GEO %in% low,],aes(x=Date,y=Value,colour=Age)) +
# facet_wrap( ~ GEO, drop=TRUE) +
# geom_line() +
# theme(legend.position = “bottom”)
# ylab(‘% Unemployment’) + xlab(‘Year’)
r1$class <- interaction(r1$GEO,r1$Age)
r3 <- r1[complete.cases(r1),]
r3$class <- factor(r3$class)
Perc <- ddply(.data=r3,.variables=.(class),
function(piece,…) {
lp <- locpoly(x=as.numeric(piece$Date),y=piece$Value,
drv=0,bandwidth=90)
sdf <- data.frame(Date=as.Date(lp$x,origin='1970-01-01'),
sPerc=lp$y,Age=piece$Age[1],GEO=piece$GEO[1])}
,.inform=FALSE
)
for (i in c(‘low’,’middle’,’high’)) {
png(paste(i,’.png’,sep=”))
print(
ggplot(Perc[Perc$GEO %in% parts[,i] ,],
aes(x=Date,y=sPerc,colour=Age)) +
facet_wrap( ~ GEO, drop=TRUE) +
geom_line() +
theme(legend.position = “bottom”)+
ylab(‘% Unemployment’) + xlab(‘Year’) +
scale_x_date(breaks = date_breaks(“5 years”),
labels = date_format(“%y”))
)
dev.off()
}
dPerc <- ddply(.data=r3,.variables=.(class),
function(piece,…) {
lp <- locpoly(x=as.numeric(piece$Date),y=piece$Value,
drv=1,bandwidth=365/2)
sdf <- data.frame(Date=as.Date(lp$x,origin='1970-01-01'),
dPerc=lp$y,Age=piece$Age[1],GEO=piece$GEO[1])}
,.inform=FALSE
)
for (i in c(‘low’,’middle’,’high’)) {
png(paste(‘d’,i,’.png’,sep=”))
print(
ggplot(dPerc[dPerc$GEO %in% parts[,i] ,],
aes(x=Date,y=dPerc,colour=Age)) +
facet_wrap( ~ GEO, drop=TRUE) +
geom_line() +
theme(legend.position = “bottom”)+
ylab(‘Change in % Unemployment’) + xlab(‘Year’)+
scale_x_date(breaks = date_breaks(“5 years”),
labels = date_format(“%y”))
)
dev.off()
}
library(KernSmooth)
library(plyr)
library(scales) # to access breaks/formatting functions
r1 <- read.csv("une_rt_m_1_Data.csv",na.strings=':')
levels(r1$GEO) <- sub(' countries)',')' ,levels(r1$GEO),fixed=TRUE)
levels(r1$GEO) <- sub('European Union','EU' ,levels(r1$GEO))
levels(r1$GEO)[levels(r1$GEO)==’Euro area (EA11-2000, EA12-2006, EA13-2007, EA15-2008, EA16-2010, EA17-2013, EA18)’] <- "EAll"
levels(r1$GEO)[levels(r1$GEO)==’United Kingdom’] <- 'UK'
levels(r1$GEO)[levels(r1$GEO)==’United States’] <- 'US'
levels(r1$GEO)[levels(r1$GEO)==’Germany (until 1990 former territory of the FRG)’] <- 'Germany'
levels(r1$GEO)
grep(’12|13|15|16|17|25|27′,x=levels(r1$GEO),value=TRUE)
r1 <- r1[!(r1$GEO %in% grep('12|13|15|16|17|25|27',x=levels(r1$GEO),value=TRUE)),]
r1$GEO <- factor(r1$GEO)
r1$Age <- factor(r1$AGE,levels=levels(r1$AGE)[c language="(2,1,3)"][/c])
r1$Date <- as.Date(paste(gsub('M','-',as.character(r1$TIME)),'-01',sep=''))
#
maxi <- aggregate(r1$Value,by=list(GEO=r1$GEO),FUN=max,na.rm=TRUE)
parts <- data.frame(
low = maxi$GEO[maxi$x
)
#ggplot(r1[r1$GEO %in% low,],aes(x=Date,y=Value,colour=Age)) +
# facet_wrap( ~ GEO, drop=TRUE) +
# geom_line() +
# theme(legend.position = “bottom”)
# ylab(‘% Unemployment’) + xlab(‘Year’)
r1$class <- interaction(r1$GEO,r1$Age)
r3 <- r1[complete.cases(r1),]
r3$class <- factor(r3$class)
Perc <- ddply(.data=r3,.variables=.(class),
function(piece,…) {
lp <- locpoly(x=as.numeric(piece$Date),y=piece$Value,
drv=0,bandwidth=90)
sdf <- data.frame(Date=as.Date(lp$x,origin='1970-01-01'),
sPerc=lp$y,Age=piece$Age[1],GEO=piece$GEO[1])}
,.inform=FALSE
)
for (i in c(‘low’,’middle’,’high’)) {
png(paste(i,’.png’,sep=”))
print(
ggplot(Perc[Perc$GEO %in% parts[,i] ,],
aes(x=Date,y=sPerc,colour=Age)) +
facet_wrap( ~ GEO, drop=TRUE) +
geom_line() +
theme(legend.position = “bottom”)+
ylab(‘% Unemployment’) + xlab(‘Year’) +
scale_x_date(breaks = date_breaks(“5 years”),
labels = date_format(“%y”))
)
dev.off()
}
dPerc <- ddply(.data=r3,.variables=.(class),
function(piece,…) {
lp <- locpoly(x=as.numeric(piece$Date),y=piece$Value,
drv=1,bandwidth=365/2)
sdf <- data.frame(Date=as.Date(lp$x,origin='1970-01-01'),
dPerc=lp$y,Age=piece$Age[1],GEO=piece$GEO[1])}
,.inform=FALSE
)
for (i in c(‘low’,’middle’,’high’)) {
png(paste(‘d’,i,’.png’,sep=”))
print(
ggplot(dPerc[dPerc$GEO %in% parts[,i] ,],
aes(x=Date,y=dPerc,colour=Age)) +
facet_wrap( ~ GEO, drop=TRUE) +
geom_line() +
theme(legend.position = “bottom”)+
ylab(‘Change in % Unemployment’) + xlab(‘Year’)+
scale_x_date(breaks = date_breaks(“5 years”),
labels = date_format(“%y”))
)
dev.off()
}
To leave a comment for the author, please follow the link and comment on their blog: Wiekvoet.
R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.