10.27.r

#load libraries
library(readr)
library(dplyr)
library(ggplot2)
library(RColorBrewer)
library(scales)

#load data
ipums <- read_csv('data/usa_00014.csv', col_types=cols(PERWT=col_double()))

#Filter by age
a <- ipums %>% filter(GQ==1 & AGE>=16 & INCWAGE>0 & INCWAGE<999999)


#BOX PLOT
#Split up by race
b <- a  %>% mutate(SingleRace=factor(ifelse(HISPAN>0,1,
                                    ifelse(RACESING==1,2,
                                    ifelse(RACESING==2,3,
                                    ifelse(RACESING==3,4,
                                    ifelse(RACESING==4,5,6)))))))

levels(b$SingleRace) <- c('HIspanic','White','Black','Native American','Asian','Other')

#Remove Other
c <- b %>% filter(SingleRace!='Other')

#Crete Sex variable
d <- c %>% mutate(Sex=factor(SEX,labels=c('Male','Female')))

#Adjust for inflataion
e <- d %>% mutate(AdjInc=INCWAGE*CPI99)

#In 1950 this question was used on the long form so for that year we use SLWT
ee <- e %>% mutate(Weight=ifelse(YEAR!=1950,PERWT,SLWT))

#Account for the income ceiling
eee <- ee %>% mutate(AdjInc=ifelse(AdjInc>59941.9,59941.99,AdjInc))

#Identify the median, first and third quartile, 10% and 90%
f <- eee %>% group_by(SingleRace,YEAR,Sex) %>%
  summarize(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))

#Graph the Box plot
ggplot(data=f,aes(x=YEAR,ymin=MIN,lower=LOW,middle=MED,upper=HIGH,ymax=MAX,fill=Sex)) +
  geom_boxplot(stat='identity',position='dodge') +
  facet_wrap(~SingleRace) +
  labs(title ='Income by Race and Sex for Those with Income, 1940-2000', y='Income, in U.S. Dollars', x='Year')
ggsave('Box.pdf',width=10, height=7.5) 

#Graph the line graph
ggplot(f,aes(x=YEAR,y=MED,color=SingleRace)) +
  geom_line() + geom_point() +
  facet_grid(Sex~.) +
  labs(title= 'Median Income by Race and Sex for Those with Income, 1940-2000', x='Year', y='Median Income, in U.S. Dollars')
ggsave('Line.pdf',width=10, height=7.5) 

#Create income groups
g <- eee %>% mutate(Group=factor(ifelse(AdjInc<=9999,1,
                              ifelse(AdjInc<=19000,2,
                              ifelse(AdjInc<=29999,3,
                              ifelse(AdjInc<=39999,4,
                              ifelse(AdjInc<=58999,5,6)))))))
#label income groups
levels(g$Group) <- c('$1-9,999','$10,000-19,000','$20,000-29,999','$30,000-39,999','$40-58,999','$59,000+')

#Create graphing groups
h <- g %>% group_by(YEAR,Sex,SingleRace,Group) %>% summarise(Number=sum(Weight))

#Create the bar graph
ggplot(data=h, aes(x=YEAR,y=Number, fill=Group)) +
  geom_bar(stat='identity',position='fill') +
  facet_grid(Sex~.~SingleRace) +
  scale_fill_brewer(palette='Set2') +
  scale_y_continuous(labels=scales::percent) +
  labs(title='Income by Race and Sex for Those with Income, 1940-2000',y='Percent',x='Year')
ggsave('IncomeColumns.pdf',width=10, height=7.5)