Initial commit

2021-10-29 13:18:50 -04:00
commit c22b6c0c95
19 changed files with 488 additions and 0 deletions
@@ -0,0 +1,52 @@
+## Creates single file containing median variables at the
+## 2010-2014 through 2013-2017 American Community Surveys for tracts
+## in the DC Area
+
+## Set up environment
+library(tidyverse)
+
+## Identify marital status variable names
+statuses <- c('mar', 'nvm', 'wid', 'div')
+pstatuses <- paste0('p', statuses)
+statusvars <- c(statuses, pstatuses)
+
+## Identify geographic identifiers to keep
+geovars <- c('GISJOIN', 'STATE', 'COUNTY')
+
+## Set Functions
+source('dcarea_functions.R')
+
+## Define function to create dataset that contains only DC-area tracts and
+## constructed marital status variables
+select.statusvars <- function(dta) {
+    dta <- select.dcarea(dta)
+    dta$GISJOIN <- as.character(dta$GISJOIN)
+    return(dta[, c(geovars, statusvars)])
+}
+
+## Load datasets containing marital status variables using data from
+## files based on 2010 tracts
+load('../US/tracts/2010/tabular/marital-status/dataset/tracts-2010TIGER-marital-status.Rdata')
+
+## Create list of data frames for each year and restrict to created
+## marital status variables
+dtas <- list(trt14_ms, trt15_ms, trt16_ms, trt17_ms)
+statusdtas <- lapply(dtas, select.statusvars)
+
+## Create single wide data frame with year appended to variable name
+namelist <- lapply(14:17, function(x) c(geovars, paste0(statusvars, x)))
+statusdta <- mapply(setNames, statusdtas, namelist, SIMPLIFY = FALSE) %>%
+    reduce(left_join, by='GISJOIN')
+statusdta$STATE <- statusdta$STATE.x
+statusdta$COUNTY <- statusdta$COUNTY.x
+statusdta <- statusdta[, -(grep('^STATE.+|^COUNTY.+', names(statusdta), perl=TRUE))]
+
+## Write file containing wide dataset to CSV format
+write.csv(statusdta,
+          'tracts/2010/tabular/marital-status/dataset/tracts-2010TIGER-marital-status.csv')
+
+
+
+
+
+