Final Project Visualization Data Code

JaiCode

#Visualization 1: Income differential between white men and women in boxplot graph 

library(readr)
library(dplyr)
library(ggplot2)
library(RColorBrewer)
library(scales)

#Read in IPUMS data

ipums <- read_csv('usa_00070.csv',col_types=cols(PERWT=col_double()))

#Filter Income bigger than 0 and less than 999999, 
a1 <- ipums %>% filter(INCWAGE>0 & INCWAGE<999999)

#Filter women aged 20 to 40 in 1940 to 1990 without ones in Alaska and Hawaii
b <- a1 %>% filter(AGE>=16 & AGE<=65 & !(STATEFIP %in% c(2,15)) & YEAR>=1960)

#Label race by character
c <- b %>% mutate(RACE=factor(ifelse(RACE %in% c(1), 1, 2),
                              labels=c('White','Nonwhite')))

#label sex
c1 <- c %>% mutate(SEX=ifelse(SEX==1,'Male','Female'))

#Adjust income with CPI99
e <- c1 %>% mutate(AdjInc=INCWAGE*CPI99)

#filter out sampline-line variable in 1950 
ee <- e %>% mutate(Weight=ifelse(YEAR!=1950,PERWT,SLWT))

#adjust and set highest income as 59941.99
eee <- ee %>% mutate(AdjInc=ifelse(AdjInc>59941.99,59941.99,AdjInc))

#Classify quantile
f <- eee %>% group_by(RACE,YEAR,SEX) %>% 
  summarise(MED=median(rep(AdjInc,times=Weight)),
            MIN=quantile(rep(AdjInc,times=Weight),0.1),
            LOW=quantile(rep(AdjInc,times=Weight),0.25),
            HIGH=quantile(rep(AdjInc,times=Weight),0.75),
            MAX=quantile(rep(AdjInc,times=Weight),0.9))

#Draw Box plot
outputbox <-ggplot(f, aes(x=YEAR,ymin=MIN,lower=LOW,middle=MED,upper=HIGH,ymax=MAX,fill=SEX)) +
  geom_boxplot(stat='identity',position='dodge') +
  facet_wrap(~RACE)+
  labs(x='YEAR',y='Income, U.S. Dollars',fill='SEX',title="Income by Race and Sex for Those with Income, 1940-2000")+
  theme(legend.position='bottom')

#Export figures to png
png('IncomeBox.png',height=500,width=1000)
print(outputbox)
dev.off()