children.r

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

#load data
ipums <- read_csv('data/usa_00011.csv', col_types=cols(HHWT=col_double(),PERWT=col_double()))

#Remove Alaska and Hawaii
a <- ipums %>% filter(!(YEAR < 1960 & STATEFIP %in% c(2,15)))

#Make factors for region and sex
b <- a %>% mutate(REGION=factor(ifelse(STATEFIP %in% c(17, 18, 19, 20, 26, 27, 29, 31, 38, 39, 46, 55), 1,
                                       ifelse(STATEFIP %in% c(4, 6, 8, 16, 30, 32, 35, 41, 49, 53, 56), 2,
                                              ifelse(STATEFIP %in% c(9, 23, 25, 33, 34, 36, 42, 44, 50), 3, 4))),
                                labels=c('Midwest','West','Northeast','South')))
#Get rid of group quarters
bb<- b %>% filter(GQ==1)

#Make data set of children
c <- bb %>% filter(AGE<18)

#Make data set of adult men
d <- a %>% filter(SEX==1 & AGE>=18)
dd <- d %>% mutate(DRace=RACE)
ddd <- dd %>% select(YEAR,SERIAL,DRace,PERNUM)

#Attach them if poploc=pernum (if they're dads)
e <- left_join(c, ddd, by=c('YEAR','SERIAL','POPLOC'='PERNUM'))

#make data set of adult women
g <- a %>% filter(SEX==2 & AGE >=18)
gg <- g %>% mutate(MRace=RACE)
ggg <- gg %>% select(YEAR,SERIAL,MRace,PERNUM)

#Attach moms to children and dads
h <- left_join(e,ggg, by=c('YEAR','SERIAL','MOMLOC'='PERNUM'))

#Sort into catagories
i <- h %>% mutate(Type=factor(ifelse(MOMLOC==0 | POPLOC==0,1,
                              ifelse(MRace!=DRace,2,3)),
                              labels=c('Only one Parent','Different Races', 'Same Race')))

#Total up by region and year to get number of children
j <- i %>% group_by(YEAR,REGION) %>% summarize(Total=sum(PERWT))

#Total up each type of household
k <- i %>% group_by(YEAR,REGION,Type) %>% summarize(Number=sum(PERWT))

#Join the matricies so they can be divided
l <- left_join(k,j, by=c('YEAR','REGION'))

#Divide them to get percentages
m <- l %>% mutate(Percent=Number/Total)

#Create Spine graph:
graph1 <- ggplot(m,aes(x=REGION, y=Percent, fill=Type)) +
  geom_bar(aes(width=rescale(Total,c(.1,1))), stat='identity', position='stack') +
  scale_y_continuous(labels=scales::percent) +
  scale_fill_brewer(palette='Set2') +
  facet_wrap(~YEAR, ncol = 5)+
  labs(title = 'Percent of Children with Parents of Same Race and Different Races, 1900-1990', x = 'Region', y = 'Percent of Children', fill = 'Parents')

#Label the Different Race Percent
graph2 <- graph1 +
  geom_text(label=ifelse(m$Type=='Different Races',paste(round(m$Percent*100,1),'%',sep=''),''),
            y=ifelse(m$Type=='Different Races',.5,.9), angle=90)
ggsave('TitleKids.pdf',width=20, height=7.5)