Income by Race and Sex 1940-2000: Box-plot, Line graph, Column Graph

Lab 7 Script

#Morgan Waterm
#Lab 7
#US History Through Census Data
#Income Analysis

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

#read in data
ipums <- read_csv('data/Lab7dataYUS.csv')

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

b <- a %>% mutate(Race= factor(ifelse(HISPAN>0, 1,
                                ifelse(RACESING==1, 2,
                                ifelse(RACESING==2, 3,
                                ifelse(RACESING==3, 4,
                                ifelse(RACESING==4, 5, 6)))))))
levels(b$Race) <- c('Hispanic', 'White', 'Black', 'Native American', 'Asian', 'Other')

c <- b %>% filter(Race!='Other')

d <- c %>% mutate(Sex = factor(SEX, labels=c('Male', 'Female')))
 
e <- d %>% mutate(AdjInc=INCWAGE*CPI99)

ee <- e %>% mutate(Weight=ifelse(YEAR!=1950, PERWT, SLWT))

eee <- ee %>% mutate(AdjInc=ifelse(AdjInc>599941.99, 59941.99, AdjInc)) 

inc <- eee %>% mutate(Income=factor(ifelse(AdjInc<9999, 1,
                                   ifelse(AdjInc<20000, 2,
                                   ifelse(AdjInc<30000, 3,
                                   ifelse(AdjInc<40000, 4,
                                   ifelse(AdjInc<59000, 5, 6))))),
                      
                            labels = c('$1-9,999', '$10,000-19,999', '$20,000-29,999', '$30,000-39,999', '$40,000-58,999', '$59,000+')))

inc2 <- inc %>% group_by(YEAR, Race, Sex, Income) %>% summarise(ptotal=sum(Weight))

inc3 <- inc %>% group_by(YEAR, Race, Sex) %>% summarise(total= sum(Weight))

incjoin <- left_join(inc2, inc3) %>% mutate(Percent= ptotal/total)
                                                                                             
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))

boxplot <- ggplot(f, aes(x=YEAR, ymin=MIN, lower=LOW, middle=MED, upper=HIGH, ymax=MAX, fill=Sex)) +
  labs(title = 'Income by Race and Sex for Those with Income, 1940-2000', x = 'Year', y = 'Income, US Dollars', Fill = 'Sex')+
  geom_boxplot(stat='identity', position= 'dodge') + 
  facet_wrap(~Race) +
  theme(legend.position = 'bottom') +
  scale_y_continuous(labels=scales::comma)
png('boxplotLab7.png', width=1000, height=500)
print(boxplot)
dev.off()

linegraph <- ggplot(f, aes(x=YEAR, y=MED, color=Race))+
  labs(title='Median Income by Race and Sex for Those with Income, 1940-2000', x='Year', y='Median Income, US Dollars', color = 'Race/Ethnicity') +
  geom_line(size=1.5) + geom_point(size=2)+
  facet_grid(Sex~.)+
  scale_y_continuous(labels=scales::comma)
png('linegraphLab7.png', width= 1000, height= 500)
print(linegraph)
dev.off()

columngraph <- ggplot(data = incjoin, aes(x = YEAR, y=Percent, fill=Income)) +
                geom_bar(stat='identity')+
                labs(title= 'Income by Race and Sex for Those with Income, 1940-2000', x='Year', y='Percent', fill='Income') +
                scale_y_continuous(labels=scales::percent) +
                theme(legend.position = 'bottom') +
                facet_grid(Sex~.~Race)
png('columngraphlab7.png', width=1000, height=500)
print(columngraph)
dev.off()