Initial commit

.gitattributes

@@ -0,0 +1,3 @@
+*.csv filter=lfs diff=lfs merge=lfs -text
+*.shp filter=lfs diff=lfs merge=lfs
+*.zip filter=lfs diff=lfs merge=lfs

.gitignore

@@ -0,0 +1,6 @@
+*.shp
+*.zip
+
+.Rhistory
+
+.venv

dcarea_functions.R

@@ -0,0 +1,34 @@
+## Functions to create data for DC Area
+## (DC & surrounding jurisdictions, including independent cities)
+
+select.dcarea <- function(dta) {
+## Arguments: `dta`: dataset from from which to select observations in
+##                   the DC Area
+## Returns: dataset containing only observations from the DC area
+
+    ## Identify counties to keep in DC Area dataset using FIPS county codes
+    counties <- c(
+          '110001'  # D.C.
+        , '240031'  # Montgomery County
+        , '240033'  # Prince George's County
+        , '510013'  # Arlington County
+        , '510059'  # Fairfax County
+        , '510510'  # Alexandria city
+        , '510600'  # Fairfax city
+        , '510610'  # Falls Church city
+    )
+
+    ## Select counties using regular expression based on FIPS codes above
+    ## and common `GISJOIN` variable
+    re <- paste0('^G', counties, collapse = '|')
+    dcarea <- dta[grep(re, dta$GISJOIN, perl=TRUE),]
+
+    ## Replace factor variables to contain only levels in the DC area
+    if('COUNTY' %in% names(dcarea)) {
+        dcarea$COUNTY <- factor(dcarea$COUNTY)
+    }
+    if('STATE' %in% names(dcarea)) {
+        dcarea$STATE <- factor(dcarea$STATE)
+    }
+    return(dcarea)
+}

tracts/1980/tabular/race-ethnicity/construction/create-tracts-1980TIGER-race-ethnicity.R

@@ -0,0 +1,24 @@
+## File creates file containing race & ethnicity variables at the
+## tract level for DC Area from 1980 Census STF-1 data
+
+## Set up environment
+library(tidyverse)
+
+## Identify race variable names
+races <- c('totpop', 'nhw', 'nhb', 'api', 'hsp', 'oth', 'two')
+praces <- paste0('p', races[-1])
+racevars <- c(races, praces)
+
+## Identify variables to keep that are not race variables
+nonracevars <- c('GISJOIN', 'STATE', 'COUNTY')
+
+## Set Functions
+source('dcarea_functions.R')
+
+load('../US/tracts/1980/tabular/race-ethnicity/dataset/tracts-1980TIGER-race-ethnicity.Rdata')
+
+## Select DC-area tracts
+racedta <- select.dcarea(trt80_re)
+
+## Write file containing wide dataset to CSV format
+write.csv(racedta, 'tracts/1980/tabular/race-ethnicity/dataset/tracts-1980TIGER-race-ethnicity.csv')

tracts/1980/tabular/race-ethnicity/dataset/tracts-1980TIGER-race-ethnicity.csv (Stored with Git LFS)

+size 242504

tracts/2010/tabular/age-race-sex/construction/tracts-2010TIGER-age-race-sex.R

@@ -0,0 +1,78 @@
+## Creates single file containing median variables at the
+## tract level for DC Area from the 2010 Census and 2010-2014 through
+## 2013-2017 American Community Surveys for tracts in the DC Area
+
+## Set up environment
+library(tidyverse)
+
+## Identify variables to keep representing age-race-sex variables
+### Abbreviations for racial groups
+races <- c(
+    'blk'  ## Black alone
+    , 'ami'  ## American Indian or Native Alaskan alone
+    , 'asi'  ## Asian alone
+    , 'pac'  ## Native Hawaiian or Other Pacific Islander alone
+    , 'oth'  ## Other race alone
+    , 'two'  ## Two or more races
+    , 'hsp'  ## Hispanic or Latino (of any race)
+    , 'nhw'  ## Non-Hispanic White
+)
+
+### Age group categories
+agegrps <- c(
+    '0004'
+    , '0509'
+    , '1014'
+    , '1517'
+    , '1819'
+    , '2024'
+    , '2529'
+    , '3034'
+    , '3544'
+    , '4554'
+    , '5564'
+    , '6574'
+    , '7584'
+    , '85up'
+)
+
+### Sex categories
+sexes <- c('m', 'f')
+
+arsvars <- as.vector(sapply(races, paste0, sapply(sexes, paste0, agegrps)))
+
+
+## Identify variables to keep that are not race variables
+geovars <- c('GISJOIN', 'STATE', 'COUNTY')
+
+## Set Functions
+source('dcarea_functions.R')
+
+## Create dataset that contains only DC-area tracts and constructed
+## age-race-sex variables
+select.arsvars <- function(dta) {
+    dta <- select.dcarea(dta)
+    dta$GISJOIN <- as.character(dta$GISJOIN)
+    return(dta[, c(geovars, arsvars)])
+}
+
+## Load datasets containing median age variables from 2010 TIGER/Line files
+load('../US/tracts/2010/tabular/age-race-sex/dataset/tracts-2010TIGER-age-race-sex.Rdata')
+
+## Create list of data frames for each year and restrict to created
+## age-race-sex variables
+dtas <- list(trt10_ars, trt14_ars, trt15_ars, trt16_ars, trt17_ars)
+arsdtas <- lapply(dtas, select.arsvars)
+
+## Create single wide data frame with year appended to variable name
+suffixes <- c('10', 14:17)
+namelist <- lapply(suffixes, function(x) c(geovars, paste0(arsvars, x)))
+arsdta <- mapply(setNames, arsdtas, namelist, SIMPLIFY = FALSE) %>%
+    reduce(left_join, by='GISJOIN')
+arsdta$STATE <- arsdta$STATE.x
+arsdta$COUNTY <- arsdta$COUNTY.x
+arsdta <- arsdta[, -(grep('^STATE.+|^COUNTY.+', names(arsdta), perl=TRUE))]
+
+## Write file containing wide dataset to CSV format
+write.csv(arsdta, 'tracts/2010/tabular/age-race-sex/dataset/tracts-2010TIGER-age-race-sex.csv')
+

tracts/2010/tabular/age-race-sex/dataset/tracts-2010TIGER-age-race-sex.csv (Stored with Git LFS)

+size 2653606

tracts/2010/tabular/children-present/construction/construct-tracts-2010TIGER-children-pres.R

@@ -0,0 +1,50 @@
+## Creates single file containing household presence of children variables
+## for tracts based on 2010 Census and the 2010-2014 through 2013-2017
+## American Community Surveys for tracts in the DC Area
+##
+## tothh = Total households
+## chpr  = Households with children present
+## ncpr  = Households with no children present
+
+## Set up environment
+library(tidyverse)
+
+## Identify variable abbreviations
+presence <- c('tothh', 'chpr', 'ncpr')
+ppresence <- paste0('p',presence[-1])
+presvars <- c(presence, ppresence)
+
+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.presvars <- function(dta) {
+    dta <- select.dcarea(dta)
+    dta$GISJOIN <- as.character(dta$GISJOIN)
+    return(dta[, c(geovars, presvars)])
+}
+
+## Load datasets containing children present variables from files based on
+## 2010 tracts
+load('../US/tracts/2010/tabular/children-present/dataset/tracts-2010TIGER-children-present.Rdata')
+
+## Create list of data frames for each year and restrict to created
+## children present variables
+dtas <- list(trt10c_cp, trt14_cp, trt15_cp, trt16_cp, trt17_cp)
+presdtas <- lapply(dtas, select.presvars)
+
+## Create single wide data frame with year appended to variable name
+namelist <- lapply(c('10c', 14:17),
+                   function(x) c(geovars, paste0(presvars, x)))
+presdta <- mapply(setNames, presdtas, namelist, SIMPLIFY = FALSE) %>%
+    reduce(left_join, by='GISJOIN')
+presdta$STATE <- presdta$STATE.x
+presdta$COUNTY <- presdta$COUNTY.x
+
+presdta <- presdta[, -(grep('^STATE.+|^COUNTY.+', names(presdta), perl=TRUE))]
+
+## Write file containing wide dataset to CSV format
+write.csv(presdta, 'tracts/2010/tabular/children-present/dataset/tracts-2010TIGER-children-present.csv')

tracts/2010/tabular/children-present/dataset/tracts-2010TIGER-children-present.csv (Stored with Git LFS)

+size 292289

tracts/2010/tabular/educ-attainment/construction/construct-tracts-2010TIGER-educ-attainment.R

@@ -0,0 +1,53 @@
+## Creates single file containing educational attainment variables at the
+## 2010-2014 through 2013-2017 American Community Surveys for tracts
+## in the DC Area
+
+## tot25o = Total population 25 and older
+## lh     = Less than high school
+## hs     = High school or GED
+## sc     = Some college
+## aa     = Associate's degree
+## ba     = Bachelor's degree
+## gr     = Graduate degree
+
+## Set up environment
+library(tidyverse)
+
+## Identify variable abbreviations
+attain <- c('tot25o', 'lh', 'hs', 'sc', 'aa', 'ba', 'gr')
+pattain <- paste0('p',attain[-1])
+attainvars <- c(attain, pattain)
+
+geovars <- c('GISJOIN', 'STATE', 'COUNTY')
+
+## Set Functions
+source('dcarea_functions.R')
+
+## Create dataset that contains only DC-area tracts and constructed
+## educational attainment variables
+select.attainvars <- function(dta) {
+    dta <- select.dcarea(dta)
+    dta$GISJOIN <- as.character(dta$GISJOIN)
+    return(dta[, c(geovars, attainvars)])
+}
+
+## Load datasets containing educational attainment variables from files based on
+## 2010 tracts
+load('../US/tracts/2010/tabular/educ-attainment/dataset/tracts-2010TIGER-educ-attainment.Rdata')
+
+## Create list of data frames for each year and restrict to created
+## educational attainmnet variables
+dtas <- list(trt14_ed, trt15_ed, trt16_ed, trt17_ed)
+attaindtas <- lapply(dtas, select.attainvars)
+
+## Create single wide data frame with year appended to variable name
+namelist <- lapply(14:17,
+                   function(x) c(geovars, paste0(attainvars, x)))
+attaindta <- mapply(setNames, attaindtas, namelist, SIMPLIFY = FALSE) %>%
+    reduce(left_join, by='GISJOIN')
+attaindta$STATE <- attaindta$STATE.x
+attaindta$COUNTY <- attaindta$COUNTY.x
+attaindta <- attaindta[, -(grep('^STATE.+|^COUNTY.+', names(attaindta), perl=TRUE))]
+
+## Write file containing wide dataset to CSV format
+write.csv(attaindta, 'tracts/2010/tabular/educ-attainment/dataset/tracts-2010TIGER-educ-attainment.csv')

tracts/2010/tabular/educ-attainment/dataset/tracts-2010TIGER-educ-attainment.csv (Stored with Git LFS)

+size 591056

tracts/2010/tabular/foreign-born/construction/construct-tracts-2010TIGER-foreign-born.R

@@ -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')
+
+
+

tracts/2010/tabular/foreign-born/dataset/tracts-2010TIGER-foreign-born.csv (Stored with Git LFS)

+size 418196

tracts/2010/tabular/marital-status/construction/construct-tracts-2010TIGER-marital-status.R

@@ -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')
+
+
+
+
+
+

tracts/2010/tabular/marital-status/dataset/tracts-2010TIGER-marital-status.csv (Stored with Git LFS)

+size 403477

tracts/2010/tabular/median-age/construction/construct-tracts-2010TIGER-median-age.R

@@ -0,0 +1,42 @@
+## Creates single file containing median variables at the
+## tract level for DC Area from the 2010 Census and 2010-2014 through
+## 2013-2017 American Community Surveys for tracts in the DC Area
+
+## Set up environment
+library(tidyverse)
+
+agevar <- 'mdage'
+
+## Identify variables to keep that are not race variables
+geovars <- c('GISJOIN', 'STATE', 'COUNTY')
+
+## Set Functions
+source('dcarea_functions.R')
+
+## Create dataset that contains only DC-area tracts and constructed
+## race variables
+select.agevars <- function(dta) {
+    dta <- select.dcarea(dta)
+    dta$GISJOIN <- as.character(dta$GISJOIN)
+    return(dta[, c(geovars, agevar)])
+}
+
+## Load datasets containing median age variables from 2010 TIGER/Line files
+load('../US/tracts/2010/tabular/median-age/dataset/tracts-2010TIGER-median-age.Rdata')
+
+## Create list of data frames for each year and restrict to created race
+## variables
+dtas <- list(trt10c_ag, trt14_ag, trt15_ag, trt16_ag, trt17_ag)
+agedtas <- lapply(dtas, select.agevars)
+
+## Create single wide data frame with year appended to variable name
+suffixes <- c('10c', 14:17)
+namelist <- lapply(suffixes, function(x) c(geovars, paste0(agevar, x)))
+agedta <- mapply(setNames, agedtas, namelist, SIMPLIFY = FALSE) %>%
+    reduce(left_join, by='GISJOIN')
+agedta$STATE <- agedta$STATE.x
+agedta$COUNTY <- agedta$COUNTY.x
+agedta <- agedta[, -(grep('^STATE.+|^COUNTY.+', names(agedta), perl=TRUE))]
+
+## Write file containing wide dataset to CSV format
+write.csv(agedta, 'tracts/2010/tabular/median-age/dataset/tracts-2010TIGER-median-age.csv')

tracts/2010/tabular/median-age/dataset/tracts-2010TIGER-median-age.csv (Stored with Git LFS)

+size 78786

tracts/2010/tabular/race-ethnicity/construction/construct-create-tracts-2010TIGER-race-ethnicity.R

@@ -0,0 +1,63 @@
+## File creates single file containing race & ethnicity variables at the
+## tract level for DC Area from the 2010 Census and 2007-2011 through
+## 2011-2015 American Community Surveys.
+##
+## Also includes variables indicating whether a neighborhood qualifies as a
+## "quadrivial" neighborhood (Asians, blacks, Latinxs, and whites each make
+## up at least 10% of the tract and no group is a majority) in each year.
+
+
+## Set up environment
+library(tidyverse)
+
+## Identify race variable names
+races <- c('totpop', 'nhw', 'nhb', 'api', 'hsp', 'oth', 'two')
+praces <- paste0('p', races[-1])
+racevars <- c(races, praces)
+
+## Identify variables to keep that are not race variables
+nonracevars <- c('GISJOIN', 'STATE', 'COUNTY')
+
+## Set Functions
+source('dcarea_functions.R')
+
+## Create dataset that contains only DC-area tracts and constructed
+## race variables
+select.racevars <- function(dta) {
+    dta <- select.dcarea(dta)
+    dta$GISJOIN <- as.character(dta$GISJOIN)
+    return(dta[, c(nonracevars, racevars)])
+}
+
+## Identify quadrivial neighborhoods
+id.quads <- function(dta) {
+    eligible <- sapply(dta[, praces[1:4]], function(x) x >= .10 & x < .5)
+    dta['quad'] <- apply(eligible, 1, all)
+    return(dta)
+}
+
+# ## Sets variable names for a specific dataset in the `racedtas` list
+# set.varnames <- function(x,y) setNames(racedtas[[x]], y)
+
+## Load datasets containing race-ethnicity variables from 2010 TIGER/Line files
+## for US tracts 2010
+load('../US/tracts/2010/tabular/race-ethnicity/dataset/tracts-2010TIGER-race-ethnicity.Rdata')
+
+## Create list of data frames for each year and restrict to created race
+## variables
+dtas <- list(trt10_re, trt11_re, trt12_re, trt13_re, trt14_re, trt15_re,
+             trt16_re, trt17_re)
+racedtas <- lapply(dtas, select.racevars) %>%
+    lapply(id.quads)
+
+## Create single wide data frame with year appended to variable name
+namelist <- lapply(10:17,
+                   function(x) c(nonracevars, paste0(c(racevars, 'quad'), x)))
+racedta <- mapply(setNames, racedtas, namelist, SIMPLIFY = FALSE) %>%
+    reduce(left_join, by='GISJOIN')
+racedta$STATE <- racedta$STATE.x
+racedta$COUNTY <- racedta$COUNTY.x
+racedta <- racedta[, -(grep('^STATE.+|^COUNTY.+', names(racedta), perl=TRUE))]
+
+## Write file containing wide dataset to CSV format
+write.csv(racedta, 'tracts/2010/tabular/race-ethnicity/dataset/tracts-2010TIGER-race-ethnicity.csv')

tracts/2010/tabular/race-ethnicity/dataset/tracts-2010TIGER-race-ethnicity.csv (Stored with Git LFS)

+size 1114494