FP - Figure 3

Figure 3

#FP Figure 3


#load packages
library(readr)

library(dplyr)

library(ggplot2)


library(RColorBrewer)

library(scales)

#read csv 
csv <- read_csv("~/Desktop/usa_00028.csv")
#only women older than 22
csv_new <- csv %>% filter(SEX==2 & AGE>=22)



#recode race

race_grouped <- csv_new %>% mutate(Race_2=factor(ifelse(HISPAN>0,1,
                                                         ifelse(RACESING==1,2,
                                                                ifelse(RACESING==2,3,
                                                                       ifelse(RACESING==3,4,
                                                                              ifelse(RACESING==4,5,6)))))))
levels(race_grouped$Race_2) <- c('Hispanic','White','Black','Native American','Asian','Other')






#create marriage status variable
edu_status <- race_grouped %>% mutate(Status=ifelse(MARST==6,'Unmarried','Married'))






#total number
total_num <- edu_status %>% group_by(YEAR, Race_2) %>% summarise(tnum=sum(PERWT))

#number married
married_number <- edu_status %>% group_by(YEAR, Race_2, Status) %>% summarise(mnum=sum(PERWT))




#join the two 
joined <- left_join(total_num,married_number,by=c('YEAR'='YEAR','Race_2'='Race_2'))

#calculate percent 
percentages <- joined %>% mutate(pct=mnum/tnum)




#graph


ggplot(data=percentages,aes(x=YEAR, y=pct, fill=Status)) + 
  geom_bar(stat='identity') +
  labs(x='Year',y='Percent',fill='Marital Status', title='Marriage Rate by Race for Women over 20, 1940-2000') +
  scale_y_continuous(labels=scales::percent) +
  theme_bw(base_size=22) +
  scale_fill_brewer(palette='Set2',guide=guide_legend(reverse=TRUE)) +
  facet_wrap(~Race_2,ncol=6)+
  scale_x_continuous(breaks=c(1950,1970,1990))