Created
March 11, 2016 16:51
-
-
Save jakeesse/5c94914fab6445c1bdcd to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
setwd('/users/JakeEsse/Desktop/HIST 90') | |
library(readr) | |
library(dplyr) | |
library(ggplot2) | |
library(scales) | |
library(grid) | |
work_master_data <- read_csv('usa_00009.csv') | |
a <- work_master_data | |
aa <- filter(a, EMPSTAT==1) | |
b <- filter(aa, AGE >= 18 & AGE <65) # Filter out working age people | |
c <- mutate(b, sex=factor(SEX, labels = c('male','female'))) # create a new sex variable with labels | |
d <- mutate(c, race=factor(ifelse(RACE==1,1,0),labels=c('nonwhite','white'))) # factor race by 'white' and 'nonwhite' | |
e <- mutate(d, weight=ifelse(YEAR==1950, SLWT, PERWT)) # apply the correct weight variables by year | |
f <- mutate(e, income=ifelse(INCWAGE==999999, 0, INCWAGE)) # fix the 0 for income | |
g <- filter(f, URBAN>0) #filter out for those people that have a known urban or rural status | |
h <- mutate(g, urban=factor(URBAN, labels=c('rural', 'urban'))) #apply labels for the urban variable | |
head(h) | |
hh <- filter(h, race=='white') | |
hhh <- filter(h, race=='nonwhite') | |
i <- summarize(group_by(h, YEAR, urban, race), inc=median(rep(income, times=weight))) | |
head(i) | |
years <- c(1940, 1950, 1960, 1970, 1980, 1990) | |
index <- c(11.986, 7, 5.725, 4.54, 2.295, 1.344) | |
cpi <- as.data.frame(cbind(years,index)) | |
print(cpi) | |
j <- merge(i, cpi, by.x='YEAR', by.y='years') | |
head(j) | |
k <- ggplot(j, aes(x=YEAR, y=inc*index, color=race))+geom_line()+geom_point()+facet_grid(.~urban)+labs(title='Median Income, inflation adjusted', x='year', y='dollars') | |
print(k) | |
ii <- summarize(group_by(h, YEAR, urban, sex), inc=median(rep(income, times=weight))) | |
head(ii) | |
jj <- merge(ii, cpi, by.x='YEAR', by.y = 'years') | |
head(jj) | |
kk <- ggplot(jj, aes(x=YEAR, y=inc*index, color=sex))+geom_line()+geom_point()+facet_grid(.~urban)+labs(title='Median Income, inflation adjusted', x='year', y='dollars') | |
print(kk) | |
iii <- summarize(group_by(hh, YEAR, urban, sex), inc=median(rep(income, times=weight))) | |
head(iii) | |
jjj <- merge(iii, cpi, by.x='YEAR', by.y='years') | |
head(jjj) | |
kkk <- ggplot(jjj, aes(x=YEAR, y=inc*index, color=sex))+geom_line()+geom_point()+facet_grid(.~urban)+labs(title='White Cohort Median Income, inflation adjusted', x='year', y='dollars') | |
print(kkk) | |
iiii <- summarize(group_by(hhh, YEAR, urban, sex), inc=median(rep(income, times=weight))) | |
head(iiii) | |
jjjj <- merge(iiii, cpi, by.x='YEAR', by.y='years') | |
head(jjjj) | |
kkkk <- ggplot(jjjj, aes(x=YEAR, y=inc*index, color=sex))+geom_line()+geom_point()+facet_grid(.~urban)+labs(title='Non-White Cohort Median Income, inflation adjusted', x='year', y='dollars') | |
print(kkkk) | |
l <- mutate(h, hrswork=factor(HRSWORK2, labels = c('N/A', '1-14', '15-29', '30-34', '35-39', '40', '41-48', '49-59', '60+'))) | |
head (l) | |
ll <- filter(l, HRSWORK2>0) | |
m <- select(ll, YEAR, race, urban, hrswork, weight) | |
n <- merge(m, cpi, by.x='YEAR', by.y='years') | |
head(n) | |
o <- summarize(group_by(n, YEAR, race, urban, hrswork), NUMBER=sum(weight)) | |
head(o) | |
p <- ggplot(o, aes(x=YEAR, y=NUMBER, fill=hrswork)) + geom_bar(stat='identity', position = 'fill')+facet_grid(race~.~urban) + scale_fill_brewer(palette = 'Set3') + guides(fill=guide_legend(reverse=TRUE,title='Hours')) + labs(title='Hours Worked by Urban Status and Race', x='Year', y='Number') + scale_y_continuous(labels=scales::percent) | |
print(p) | |
mm <- select(ll, YEAR, sex, urban, hrswork, weight) | |
nn <- merge(mm, cpi, by.x='YEAR', by.y='years') | |
head(nn) | |
oo <- summarize(group_by(nn, YEAR, sex, urban, hrswork), NUMBER=sum(weight)) | |
head(oo) | |
pp <- ggplot(oo, aes(x=YEAR, y=NUMBER, fill=hrswork)) + geom_bar(stat='identity', position = 'fill')+facet_grid(sex~.~urban) + scale_fill_brewer(palette = 'Set3') + guides(fill=guide_legend(reverse=TRUE,title='Hours')) + labs(title='Hours Worked by Urban Status and Sex', x='Year', y='Number') + scale_y_continuous(labels=scales::percent) | |
print(pp) | |
z <- filter(ll, race=='white') | |
mmm <- select(z, YEAR, sex, urban, hrswork, weight) | |
nnn <- merge(mmm, cpi, by.x='YEAR', by.y='years') | |
head(nnn) | |
ooo <- summarize(group_by(nnn, YEAR, sex, urban, hrswork), NUMBER=sum(weight)) | |
head(ooo) | |
ppp <- ggplot(ooo, aes(x=YEAR, y=NUMBER, fill=hrswork)) + geom_bar(stat='identity', position = 'fill')+facet_grid(sex~.~urban) + scale_fill_brewer(palette = 'Set3') + guides(fill=guide_legend(reverse=TRUE,title='Hours')) + labs(title='White Cohort Hours Worked by Urban Status and Sex', x='Year', y='Number') + scale_y_continuous(labels=scales::percent) | |
print(ppp) | |
zz <- filter(ll, race=='nonwhite') | |
mmmm <- select(zz, YEAR, sex, urban, hrswork, weight) | |
nnnn <- merge(mmmm, cpi, by.x='YEAR', by.y='years') | |
head(nnnn) | |
oooo <- summarize(group_by(nnnn, YEAR, sex, urban, hrswork), NUMBER=sum(weight)) | |
head(oooo) | |
pppp <- ggplot(oooo, aes(x=YEAR, y=NUMBER, fill=hrswork)) + geom_bar(stat='identity', position = 'fill')+facet_grid(sex~.~urban) + scale_fill_brewer(palette = 'Set3') + guides(fill=guide_legend(reverse=TRUE,title='Hours')) + labs(title='Non-White Cohort Hours Worked by Urban Status and Sex', x='Year', y='Number') + scale_y_continuous(labels=scales::percent) | |
print(pppp) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment