Merge pull request #45 from lm-hien/my-branch

Add year 2020 to `us_national_population`

Author: lm-hien

NEWS.md

@@ -23,6 +23,7 @@
 -   Fixed data formatting of `paulist_missions`
 -   Added `methodists` (#14)
 -   Added data for the year 2020 in `us_state_populations` (#44)
+-   Added the year 2020 in `us_national_population` (#45)
 
 # historydata 0.1
 

R/us-national-population.R

@@ -1,4 +1,4 @@
-#' Population of the United States, 1790-2010
+#' Population of the United States, 1790-2020
 #'
 #' Population figures for the entire United States of America from the decennial census.
 #'
@@ -11,11 +11,14 @@
 #'   \item \code{population}: population of the state or territory.
 #'
 #'   }
-#' @format A data frame with 23 observations of 2 variables.
+#' @format A data frame with 24 observations of 2 variables.
 #' @references This dataset has been gathered by the
-#'   \href{https://www.nhgis.org/}{NHGIS}. Minnesota Population Center,
-#'   \emph{National Historical Geographic Information System: Version 2.0}
-#'   (Minneapolis: University of Minnesota, 2011).
+#'   \href{https://www.nhgis.org/}{NHGIS}.
+#'   Steven Manson, Jonathan Schroeder, David Van Riper, Katherine Knowles, Tracy Kugler,
+#'   Finn Roberts, and Steven Ruggles.
+#'   \emph{IPUMS National Historical Geographic Information System: Version 19.0}
+#'   [dataset]. Minneapolis, MN: IPUMS, 2024.
+#'   \doi{10.18128/D050.V19.0}
 #' @examples
 #' head(us_national_population)
 #' if(require(ggplot2)) {

R/us-state-populations.R

@@ -22,7 +22,7 @@
 #'   Steven Manson, Jonathan Schroeder, David Van Riper, Katherine Knowles, Tracy Kugler,
 #'   Finn Roberts, and Steven Ruggles.
 #'   \emph{IPUMS National Historical Geographic Information System: Version 19.0}
-#'   \[dataset\]. Minneapolis, MN: IPUMS, 2024.
+#'   [dataset]. Minneapolis, MN: IPUMS, 2024.
 #'   \doi{10.18128/D050.V19.0}
 #' @examples
 #' head(us_state_populations)

data-raw/scripts/us-national-population.R

@@ -1,11 +1,20 @@
 library(dplyr)
-us_state_populations <- read.csv(file.path("data-raw", "nhgis0011_ts_state.csv"),
+library(tidyr)
+
+us_state_populations <- read.csv(file.path("data-raw", "nhgis0001_ts_nominal_state.csv"),
                                  stringsAsFactors = FALSE)
+
+census_year_pattern <- "A00AA(\\d{4})"
+
 us_national_population <- us_state_populations %>%
-  select(year = YEAR,
-         state = STATE,
-         state_population = A00AA) %>%
+  pivot_longer(
+    cols = matches(sprintf("%s$", census_year_pattern)),
+    names_to = "year",
+    values_to = "population",
+    names_pattern = census_year_pattern
+  ) %>%
+  mutate(year = as.integer(year)) %>%
   as_tibble() %>%
   group_by(year) %>%
-  summarize(population = sum(state_population, na.rm = TRUE))
+  summarize(population = sum(population, na.rm = TRUE))
 usethis::use_data(us_national_population, overwrite = TRUE)