Created
November 16, 2016 19:30
-
-
Save jailee/261150e3a40fd0a8fa4b98d5f92c6e50 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
#Visualization 4: Column graph for labor division between white men and women | |
#load packages | |
library(dplyr) | |
library(readr) | |
library(ggplot2) | |
library(RColorBrewer) | |
#Read in IPUMS data | |
a <- read_csv('usa_00067.csv',col_types=cols(PERWT=col_double())) | |
#Filter age from 15 to 65 and exclude Alaska and Hawaii in the data | |
b <- a %>% filter(AGE>=15 & AGE<=65 & YEAR>=1960 | !(STATEFIP %in% c(2,15))) | |
#Label race by character | |
c <- b %>% mutate(RACE=factor(ifelse(RACE %in% c(1), 1, 2), | |
labels=c('white','nonwhite'))) | |
#Filter White | |
d <- c %>% filter(RACE=='white') | |
#None>=980 | |
#Professional 0~99 | |
#Farmers 100-199, 800-899 (FARMER LABORERS) | |
#Managerial/clerical/sales 200-499 | |
#Craftsmen/operatives/laborers 500-699 900-979 | |
#Service 700-799 | |
#Create occupation by recoding OCC1950 | |
f <- d %>% mutate(OCCUPATION=factor(ifelse((OCC1950>=100 & OCC1950 <=199)|(OCC1950>=800 & OCC1950<=899), 1, | |
ifelse(OCC1950>=200 & OCC1950<=299), 2, | |
ifelse((OCC1950>=599 & OCC1950<=699)|(OCC1950>=900 & OCC1950<=979), 3, | |
ifelse(OCC1950>=980, 4,5)))), | |
labels=c('farmers','Managers/Officials/Proprietors','craftmen/operatives/laborers','none','other')) | |
#Label Sex | |
o3 <- f %>% mutate(SEX=ifelse(SEX==1,'male','female')) | |
#Group by Year, Race, Sex, and Occupation and weight by PERWT | |
o4 <- o3 %>% group_by(YEAR,RACE,SEX,OCCUPATION) %>% summarise(Number=sum(PERWT)) | |
#Graphing Figure 2 | |
png('OccupM-F.png',height=500,width=1000) | |
fig2 <- ggplot(data=o4,aes(x=YEAR,y=Number,fill=OCCUPATION))+ | |
labs(x='Year',y='Percent of Population',fill='Occupation',title='Occupation of White Americans by Sex and Year, 1940-2000')+ | |
geom_bar(stat='identity', position='fill') + | |
scale_y_continuous(labels=scales::percent) + | |
scale_x_continuous(breaks=c(1940,1970,2000)) + | |
scale_fill_brewer(palette='Set1') + | |
facet_grid(SEX~.~RACE) + | |
theme_bw() + theme(legend.position='bottom') | |
#Export figures to png | |
png('Occup.png',height=500,width=1000) | |
print(fig2) | |
dev.off() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment