gistfile1.txt

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

#read in data
a<- read_csv('./data/usa_00005.csv')
#remove Hawaii and Alaska and pick out those of working age
b<- a %>% filter(AGE>=15 & AGE<=65 & !(STATEFIP %in% c(2,15)))

#Creating Race Groups 
c <- b %>% mutate(RACEGROUP=factor(ifelse((RACE==1),1,
                                  ifelse((RACE==2),2,
                                  ifelse((RACE==3),3,
                                  4))), 
                            labels=c('White','Black','Native American', 'Asian')))

#Recoding sex
d <- c %>% mutate(Sex=ifelse(SEX==1, 'male', 'female'))

#Creating Occupation catagory
e <- d %>% mutate(OCCUPATION=factor(ifelse(OCC1950<100, 6,
                                    ifelse(OCC1950>=980, 1,
                                    ifelse((OCC1950>=500 & OCC1950<=690) | (OCC1950>=910 & OCC1950<=970), 3,
                                    ifelse(OCC1950>=700 & OCC1950<=790, 5,
                                    ifelse(OCC1950>=200 & OCC1950<=490, 4,2))))),
                            labels=c('None','Farmers/Farm Laborers','Craftsmen/Operatives/Laborers','Managerial/Clerical/Sales','Service','Professionals')))

#Select just the variables I need
f <- e %>% select(YEAR, PERWT, Sex, RACEGROUP, OCCUPATION)

#For figrure 2
f1 <- f %>% group_by(YEAR, Sex, RACEGROUP) %>% summarise(NUMBER=sum(PERWT))
  
#For figure 4
f2 <- f %>% group_by(YEAR, Sex, RACEGROUP, OCCUPATION) %>% summarise(NUMBER=sum(PERWT))

#GRAPHING
#Create preliminary graph of figure 2
ggplot(data=f1, aes(x=YEAR, y=NUMBER, fill=Sex)) +
  geom_bar(stat='identity') +
  labs(x='Year', y='Population', fill='Sex', title='2. Population Aged 15-65 by Race, Year, and Sex, 1870-1920')+
  scale_y_continuous(labels=scales::comma) +
  scale_x_continuous(breaks=c(1870,1900,1920)) +
  scale_fill_brewer(palette='Set2',guide=guide_legend(reverse=TRUE)) +
  facet_wrap(~RACEGROUP,ncol=2,scales='free_y') +
  theme_bw()