Created
September 23, 2016 16:57
-
-
Save helenaeitel/1b4035d52b9f26ba21cb59733feb6e0b 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
#Helena Eitel | |
#QSS 30.05 | |
#Lab Assignment 2 | |
#Last Modified: 9/22/16 | |
#open various packages to use later | |
library(dplyr) | |
library(readr) | |
library(tidyr) | |
#make sure working directory is correct | |
getwd() | |
#read IPUMS data | |
a <- read_csv("./Extract1.csv") | |
#read a file with the character conversions for race | |
r <- read_csv("./Race.csv") | |
#exclude Alaska and Hawaii altogether | |
aa <- a %>% filter(!(YEAR < 1960 & STATEFIP %in% c(2,15))) | |
#add the corresponding race characters to dataframe a in a new column | |
b <- right_join(aa,r,"RACE") | |
#within each year and within each race category return the number of people (sum of PERWTs) | |
c <- b %>% group_by(YEAR,RACEC) %>%summarise(NUMBER = sum(PERWT)) | |
#remove two race categories because there is no information there | |
d <- c %>% filter(!(RACEC == "Three or more major races" | RACEC == "Two major races")) | |
#display the table such that each race is a column | |
e <- d %>% spread(YEAR,NUMBER) | |
#save the final file to the working directory | |
write_csv(e,"RaceTable.csv") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment