This notebook reads in the following U.S. Census Bureau county-level datasets on population estimates:
For the 2000-2010 period
For the 2010-2018 period
The raw datasets are saved in the input/
folder. The processed datasets are saved in the output/
folder.
The data are filtered to contain only counties in Maryland.
suppressMessages(library('tidyverse'))
suppressMessages(library('reshape2'))
suppressMessages(library('janitor'))
2000-2010 period
process_00_10 <- function (type) {
df <- read_csv(paste0('input/pop_00_10_', type, '.csv')) %>%
clean_names() %>%
select(-sumlev, -state, -region, -division) %>%
filter(stname == 'Maryland')
df.m <- melt(df, id.vars = c('stname', 'ctyname', 'county')) %>%
rename(label = variable, tot.pop = value) %>%
mutate(year.label =
case_when(grepl('2000', label) ~ 2000,
grepl('2001', label) ~ 2001,
grepl('2002', label) ~ 2002,
grepl('2003', label) ~ 2003,
grepl('2004', label) ~ 2004,
grepl('2005', label) ~ 2005,
grepl('2006', label) ~ 2006,
grepl('2007', label) ~ 2007,
grepl('2008', label) ~ 2008,
grepl('2009', label) ~ 2009,
grepl('2010', label) ~ 2010),
county = str_pad(county, 3, pad = "0"))
return(df.m)
}
md.inter <- suppressMessages(process_00_10('inter'))
md.post <- suppressMessages(process_00_10('post'))
write_csv(md.inter, 'output/md_inter_00_10.csv')
write_csv(md.post, 'output/md_post_00_10.csv')
2010-2018 period
md.18 <- suppressMessages(read_csv('input/CO-EST2018-Alldata.csv') %>%
clean_names() %>% filter(state == '24') %>% select(-sumlev,
-region,
-division,
-state))
md.18.m <- melt(md.18,
id.vars = c('county', 'stname', 'ctyname')) %>%
mutate(year.label = str_extract(variable, "\\-*\\d+\\.*\\d*"))
write_csv(md.18.m, 'output/md_10_18.csv')