Initial commit

2021-10-29 13:18:50 -04:00
commit c22b6c0c95
19 changed files with 488 additions and 0 deletions
@@ -0,0 +1,59 @@
+## Creates single file containing foreign-born variables at the
+## 2010-2014 through 2013-2017 American Community Surveys for tracts
+## in the DC Area
+
+## fbpop = Foreign-born population
+## eur   = European foreign-born
+## asi   = Asian foreign-born
+## afr   = African foreign-born
+## oce   = Oceania foreign-born
+## lat   = Latin American foreign-born
+## Note `p` variables represent *proportion of foreign-born residents*
+##
+## Note: Remainder of foreign born are from North America, i.e.:
+##       fbpop - sum(eur + asi + afr + oce + lat) = N. American foreign-born
+
+## Set up environment
+library(tidyverse)
+
+## Identify variable abbreviations
+regions <- c('fbpop', 'eur','asi','afr','oce','lat')
+pregions <- paste0('p',regions[-1])
+regionvars <- c(regions, pregions)
+
+geovars <- c('GISJOIN', 'STATE', 'COUNTY')
+
+## Set Functions
+source('dcarea_functions.R')
+
+## Create dataset that contains only DC-area tracts and constructed
+## foreign-born variables
+select.regionvars <- function(dta) {
+    dta <- select.dcarea(dta)
+    dta$GISJOIN <- as.character(dta$GISJOIN)
+    return(dta[, c(geovars, regionvars)])
+}
+
+## Load datasets containing foreign-born variables from files based on
+## 2010 tracts
+load('../US/tracts/2010/tabular/foreign-born/dataset/tracts-2010TIGER-foreign-born.Rdata')
+
+## Create list of data frames for each year and restrict to created
+## foreign-born variables
+dtas <- list(trt14_fb, trt15_fb, trt16_fb, trt17_fb)
+regiondtas <- lapply(dtas, select.regionvars)
+
+## Create single wide data frame with year appended to variable name
+namelist <- lapply(14:17,
+                   function(x) c(geovars, paste0(regionvars, x)))
+regiondta <- mapply(setNames, regiondtas, namelist, SIMPLIFY = FALSE) %>%
+    reduce(left_join, by='GISJOIN')
+regiondta$STATE <- regiondta$STATE.x
+regiondta$COUNTY <- regiondta$COUNTY.x
+regiondta <- regiondta[, -(grep('^STATE.+|^COUNTY.+', names(regiondta), perl=TRUE))]
+
+## Write file containing wide dataset to CSV format
+write.csv(regiondta, 'tracts/2010/tabular/foreign-born/dataset/tracts-2010TIGER-foreign-born.csv')
+
+
+