Merge pull request #522 from walkerke/dhc-update

Update `get_decennial()` to support the new DHC and DP summary files

DESCRIPTION

@@ -1,12 +1,12 @@
 Package: tidycensus
 Type: Package
 Title: Load US Census Boundary and Attribute Data as 'tidyverse' and 'sf'-Ready Data Frames
-Version: 1.3.4
+Version: 1.4
 Authors@R: c(
     person(given = "Kyle", family = "Walker", email="kyle@walker-data.com", role=c("aut", "cre")),
     person(given = "Matt", family = "Herman", email = "mfherman@gmail.com", role = "aut"),
     person(given = "Kris", family = "Eberwein", email = "eberwein@knights.ucf.edu", role = "ctb"))
-Date: 2023-05-19
+Date: 2023-05-25
 URL: https://walker-data.com/tidycensus/
 BugReports: https://github.com/walkerke/tidycensus/issues
 Description: An integrated R interface to several United States Census Bureau 

R/census.R

@@ -11,9 +11,9 @@
 #'                    Defaults to FALSE; if TRUE, only needs to be called once per
 #'                    dataset.  If variables dataset is already cached via the
 #'                    \code{load_variables} function, this can be bypassed.
-#' @param year The year for which you are requesting data. Defaults to 2010; 2000,
+#' @param year The year for which you are requesting data. Defaults to 2020; 2000,
 #'             2010, and 2020 are available.
-#' @param sumfile The Census summary file; defaults to \code{"sf1"} but will switch to \code{"pl"} if the year supplied is 2020.  Not all summary files are available for each decennial Census year.
+#' @param sumfile The Census summary file; defaults to \code{"dhc"}.  Not all summary files are available for each decennial Census year.
 #' @param state The state for which you are requesting data. State
 #'              names, postal codes, and FIPS codes are accepted.
 #'              Defaults to NULL.
@@ -22,8 +22,7 @@
 #'               to `state`.  Defaults to NULL.
 #' @param geometry if FALSE (the default), return a regular tibble of ACS data.
 #'                 if TRUE, uses the tigris package to return an sf tibble
-#'                 with simple feature geometry in the `geometry` column.  state, county, tract, and block group are
-#'                 supported for 2000 through 2020; block and ZCTA geometry are supported for 2000 and 2010.
+#'                 with simple feature geometry in the `geometry` column.
 #' @param output One of "tidy" (the default) in which each row represents an
 #'               enumeration unit-variable combination, or "wide" in which each
 #'               row represents an enumeration unit and the variables are in the
@@ -69,8 +68,9 @@ get_decennial <- function(geography,
                           variables = NULL,
                           table = NULL,
                           cache_table = FALSE,
-                          year = 2010,
-                          sumfile = c("sf1", "sf2", "sf3", "sf4",
+                          year = 2020,
+                          sumfile = c("pl", "dhc", "dp", "sf1", "sf2",
+                                      "sf3", "sf4",
                                       "sf2profile", "sf3profile",
                                       "sf4profile",
                                       "pl", "plnat", "aian",
@@ -108,7 +108,7 @@ get_decennial <- function(geography,
   }
 
   if (year == 2020 && sumfile == "pl" && geography == "public use microdata area") {
-    stop("PUMAs are not defined yet for the 2020 decennial Census.", call. = FALSE)
+    stop("PUMAs are not available in the 2020 PL file.", call. = FALSE)
   }
 
   if (geography == "voting district" && year != 2020) {
@@ -157,7 +157,7 @@ get_decennial <- function(geography,
   }
 
   if (year == 2020 && sumfile == "pl" && geography == "zip code tabulation area") {
-    stop("ZCTAs are not currently available for the 2020 decennial Census.", call. = FALSE)
+    stop("ZCTAs are not available in the 2020 PL file.", call. = FALSE)
   }
 
   # if (geography == "zip code tabulation area" && is.null(state)) {
@@ -424,7 +424,7 @@ get_decennial <- function(geography,
     # Give users a heads-up about differential privacy in the 2020 decennial data
     # This should print as the final message before data are returned
     # For right now, this pertains to the PL file; adjust when new data come out in 2023
-    if (year == 2020 && sumfile == "pl") {
+    if (year == 2020) {
 
       msg <- c(crayon::cyan(stringr::str_wrap("Note: 2020 decennial Census data use differential privacy, a technique that introduces errors into data to preserve respondent confidentiality.")),
                i = crayon::magenta("Small counts should be interpreted with caution."),
@@ -442,7 +442,7 @@ get_decennial <- function(geography,
     # Give users a heads-up about differential privacy in the 2020 decennial data
     # This should print as the final message before data are returned
     # For right now, this pertains to the PL file; adjust when new data come out in 2023
-    if (year == 2020 && sumfile == "pl") {
+    if (year == 2020) {
 
       msg <- c(crayon::cyan(stringr::str_wrap("Note: 2020 decennial Census data use differential privacy, a technique that introduces errors into data to preserve respondent confidentiality.")),
                i = crayon::magenta("Small counts should be interpreted with caution."),

R/search_variables.R

@@ -4,7 +4,7 @@
 #'   or endyear of the decennial Census or ACS sample. 5-year ACS data is
 #'   available from 2009 through 2020. 1-year ACS data is available from 2005
 #'   through 2021, with the exception of 2020.
-#' @param dataset One of "sf1", "sf2", "sf3", "sf4", "pl",
+#' @param dataset One of "sf1", "sf2", "sf3", "sf4", "pl", "dhc", "dp",
 #'   "as", "gu", "mp", "vi", "acsse", "acs1", "acs3", "acs5", "acs1/profile",
 #'   "acs3/profile", "acs5/profile", "acs1/subject", "acs3/subject", "acs5/subject",
 #'   "acs1/cprofile", or "acs5/cprofile".
@@ -20,7 +20,7 @@
 #'
 load_variables <- function(
   year,
-  dataset = c("sf1", "sf2", "sf3", "sf4", "pl",
+  dataset = c("sf1", "sf2", "sf3", "sf4", "pl", "dhc", "dp",
               "as", "gu", "mp", "vi", "acsse",
               "dpas", "dpgu", "dpmp", "dpvi",
               "acs1", "acs3", "acs5", "acs1/profile",
@@ -73,7 +73,7 @@ load_variables <- function(
   }
 
   if (dataset %in% c("sf1", "sf2", "sf3", "sf4", "pl",
-                     "as", "gu", "mp", "vi",
+                     "as", "gu", "mp", "vi", "dhc", "dp",
                      "dpas", "dpgu", "dpmp", "dpvi")) {
     dataset <- paste0("dec/", dataset)
   }