Merge pull request #11 from CMAP-REPOS/update_geos

Update data as of 2/12/23

DESCRIPTION

@@ -36,4 +36,4 @@ Suggests:
     ggplot2,
     tidycensus
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.1.2
+RoxygenNote: 7.2.3

R/data.R

@@ -8,9 +8,8 @@
 #'
 #' The Census Blocks within the 7-county Chicago Metropolitan Agency for
 #' Planning (CMAP) region. From the US Census Bureau's TIGER/Line shapefiles,
-#' 2021 vintage. **Use `block_sf` for data from the 2020 decennial census or the
-#' American Community Survey (ACS) from 2020 onward. For data from the 2010
-#' decennial census or ACS from 2010 through 2019, use `block_sf_2010`.**
+#' 2022 vintage. **Use `block_sf` for data from the 2020 decennial census or the
+#' American Community Survey (ACS) from 2020 onward.**
 #'
 #' Census Bureau description:
 #'
@@ -54,20 +53,11 @@
 #' ggplot(block_sf) + geom_sf(lwd = 0.1) + theme_void()
 "block_sf"
 
-#' @rdname block_sf
-#' @format `block_sf_2010` is a multipolygon `sf` object with
-#' `r nrow(block_sf_2010)` rows and `r ncol(block_sf_2010)` variables.
-"block_sf_2010"
-
-
 #' Census Block Groups
 #'
 #' The Census Block Groups within the 7-county Chicago Metropolitan Agency for
 #' Planning (CMAP) region. From the US Census Bureau's TIGER/Line shapefiles,
-#' 2021 vintage. **Use `blockgroup_sf` for data from the 2020 decennial census
-#' or the American Community Survey (ACS) from 2020 onward. For data from the
-#' 2010 decennial census or ACS from 2010 through 2019, use
-#' `blockgroup_sf_2010`.**
+#' 2022 vintage.
 #'
 #' Census Bureau description:
 #'
@@ -114,19 +104,11 @@
 #' ggplot(blockgroup_sf) + geom_sf(lwd = 0.1) + theme_void()
 "blockgroup_sf"
 
-#' @rdname blockgroup_sf
-#' @format `blockgroup_sf_2010` is a polygon `sf` object with
-#' `r nrow(blockgroup_sf_2010)` rows and `r ncol(blockgroup_sf_2010)` variables.
-"blockgroup_sf_2010"
-
-
 #' Census Tracts
 #'
 #' The Census Tracts within the 7-county Chicago Metropolitan Agency for
 #' Planning (CMAP) region. From the US Census Bureau's TIGER/Line shapefiles,
-#' 2021 vintage. **Use `tract_sf` for data from the 2020 decennial census or the
-#' American Community Survey (ACS) from 2020 onward. For data from the 2010
-#' decennial census or ACS from 2010 through 2019, use `tract_sf_2010`.**
+#' 2022 vintage.
 #'
 #' Census Bureau description:
 #'
@@ -182,19 +164,11 @@
 #' ggplot(tract_sf) + geom_sf(lwd = 0.1) + theme_void()
 "tract_sf"
 
-#' @rdname tract_sf
-#' @format `tract_sf_2010` is a polygon `sf` object with `r nrow(tract_sf_2010)`
-#' rows and `r ncol(tract_sf_2010)` variables.
-"tract_sf_2010"
-
-
 #' Census Public Use Microdata Areas (PUMAs)
 #'
 #' The Census PUMAs covering the 7-county Chicago Metropolitan Agency for
 #' Planning (CMAP) region. From the US Census Bureau's TIGER/Line shapefiles,
-#' 2021 vintage. **These PUMAs are valid for use with ACS PUMS data from 2012
-#' through 2021. They will be superseded by the 2020 PUMAs when the 2022 ACS
-#' data is published.**
+#' 2022 vintage.
 #'
 #' Census Bureau description:
 #'
@@ -203,14 +177,17 @@
 #' census records that are screened to protect confidentiality. These extracts
 #' are referred to as public use microdata sample (PUMS) files.*
 #'
-#' *"For the 2010 Census, each state, the District of Columbia, Puerto Rico, and
-#' some Island Area participants delineated PUMAs for use in presenting PUMS
-#' data based on a 5 percent sample of decennial census or American Community
-#' Survey data. These areas are required to contain at least 100,000 people.
-#' This is different from Census 2000 when two types of PUMAs were defined: a 5
-#' percent PUMA as for 2010 and an additional super-PUMA designed to provide a 1
-#' percent sample. The PUMAs are identified by a five-digit census code unique
-#' within state."*
+#' *"PUMAs are statistical geographic areas defined for the tabulation and
+#' dissemination of American Community Survey (ACS) and Puerto Rico Community
+#' Survey Public Use Microdata Sample (PUMS) data as well as ACS period
+#' estimates, and decennial census data. Nesting within states or equivalent
+#' entities, PUMAs cover the entirety of the United States, Puerto Rico, Guam,
+#' and the U.S. Virgin Islands. PUMA delineations are subject to population
+#' threshold criteria, “building block” geography criteria, and geographic
+#' nesting criteria. State Data Centers (SDCs) define PUMAs with the cooperation
+#' of regional, state, local, and tribal governments, organizations, and other
+#' interested data users. Each PUMA must have a minimum population of 100,000 at
+#' the time of delineation and throughout the decade.*
 #'
 #' @format
 #' A multipolygon `sf` object with `r nrow(puma_sf)` rows and `r ncol(puma_sf)`
@@ -239,7 +216,7 @@
 #'
 #' The Census ZCTAs covering the 7-county Chicago Metropolitan Agency for
 #' Planning (CMAP) region. From the US Census Bureau's TIGER/Line shapefiles,
-#' 2021 vintage.
+#' 2022 vintage.
 #'
 #' Census Bureau description:
 #'
@@ -287,10 +264,11 @@
 #' Illinois State Senate Districts
 #'
 #' The Illinois General Assembly Senate Districts. From the US Census Bureau's
-#' TIGER/Line shapefiles, 2021 vintage. **These districts were in effect for
+#' TIGER/Line shapefiles, 2022 vintage. **These districts were in effect for
 #' elections from 2012 through 2020 (i.e. the 98th through 102nd General
 #' Assemblies). They will be superseded by new district boundaries for the 2022
-#' election (for the 103rd General Assembly).**
+#' election (for the 103rd General Assembly). Updated shapefiles from the Census
+#' Bureau are expected in spring 2023.**
 #'
 #' Census Bureau description:
 #'
@@ -343,10 +321,12 @@
 #' Illinois State House Districts
 #'
 #' The Illinois General Assembly House Districts. From the US Census Bureau's
-#' TIGER/Line shapefiles, 2021 vintage. **These districts were in effect for
+#' TIGER/Line shapefiles, 2022 vintage. **These districts were in effect for
 #' elections from 2012 through 2020 (i.e. the 98th through 102nd General
 #' Assemblies). They will be superseded by new district boundaries for the 2022
-#' election (for the 103rd General Assembly).**
+#' election (for the 103rd General Assembly). As with Illinois State Senate
+#' districts, updated files are expected from the Census Bureau in spring
+#' 2023.**
 #'
 #' Census Bureau description:
 #'
@@ -399,10 +379,10 @@
 #' U.S. Congressional Districts
 #'
 #' The United States Congressional Districts in the state of Illinois. From the
-#' US Census Bureau's TIGER/Line shapefiles, 2021 vintage. **These districts
+#' US Census Bureau's TIGER/Line shapefiles, 2022 vintage. **These districts
 #' were in effect for elections from 2012 through 2020 (i.e. the 113th through
 #' 117th Congresses). They will be superseded by new district boundaries for the
-#' 2022 election (for the 118th Congress).**
+#' 2022 election (for the 118th Congress). Updates are expected in spring 2023.**
 #'
 #' Census Bureau description:
 #'
@@ -442,7 +422,7 @@
 #' The 284 municipalities (also referred to as "incorporated places" in Census
 #' Bureau terminology) that are at least partially within the 7-county Chicago
 #' Metropolitan Agency for Planning (CMAP) region. From the US Census Bureau's
-#' TIGER/Line shapefiles, 2021 vintage.
+#' TIGER/Line shapefiles, 2022 vintage.
 #'
 #' Census Bureau description:
 #'
@@ -483,7 +463,7 @@
 #' Bureau terminology) that are within the CMAP Metropolitan Planning Area
 #' (MPA). (The MPA includes the 7 CMAP counties, plus Aux Sable Township in
 #' Grundy County and Sandwich & Somonauk Townships in DeKalb County.) From the
-#' US Census Bureau's TIGER/Line shapefiles, 2021 vintage.
+#' US Census Bureau's TIGER/Line shapefiles, 2022 vintage.
 #'
 #' Census Bureau description:
 #'
@@ -526,7 +506,7 @@
 #' The counties that are within the CMAP travel modeling area **or** the
 #' "Chicago-Naperville-Elgin, IL-IN-WI" Metropolitan Statistical Area (as
 #' defined by the United States Office of Management and Budget). From the US
-#' Census Bureau's TIGER/Line shapefiles, 2021 vintage.
+#' Census Bureau's TIGER/Line shapefiles, 2022 vintage.
 #'
 #' Census Bureau description:
 #'
@@ -577,7 +557,7 @@
 #' by the Illinois Department of Transportation (IDOT). Includes a column
 #' indicating which of the five transportation regions each district belongs to.
 #' Created using the county boundaries in the US Census Bureau's TIGER/Line
-#' shapefiles, 2021 vintage.
+#' shapefiles, 2022 vintage.
 #'
 #' @format
 #' A polygon `sf` object with `r nrow(idot_sf)` rows and `r ncol(idot_sf)`
@@ -606,7 +586,7 @@
 
 #' Chicago Community Areas (CCAs)
 #'
-#' The official boundaries of the Chicago Community Areas. Obtained 3/24/2021.
+#' The official boundaries of the Chicago Community Areas. Obtained 2/12/2023.
 #'
 #' @format
 #' A multipolygon `sf` object with `r nrow(cca_sf)` rows and `r ncol(cca_sf)`
@@ -631,7 +611,8 @@
 #' Chicago Wards
 #'
 #' The official boundaries of the Chicago wards established in May of 2015.
-#' Obtained 3/24/2021.
+#' Obtained 2/12/2023. Updated boundaries will be provided once the 2023 wards
+#' come into effect in May 2023.
 #'
 #' @format
 #' A multipolygon `sf` object with `r nrow(ward_sf)` rows and `r ncol(ward_sf)`
@@ -679,7 +660,7 @@
 #' }
 #'
 #' @source
-#' [CMAP Data Hub](https://datahub.cmap.illinois.gov/dataset/cmap-metropolitan-planning-area-september-2014)
+#' [CMAP Data Hub (temporarily offline)](https://datahub.cmap.illinois.gov/dataset/cmap-metropolitan-planning-area-september-2014)
 #'
 #' @examples
 #' # Display the CMAP MPA counties with ggplot2
@@ -726,7 +707,7 @@
 #' }
 #'
 #' @source
-#' [CMAP Data Hub](https://datahub.cmap.illinois.gov/dataset/councils-of-mayors-boundaries)
+#' [CMAP Data Hub (temporarily offline)](https://datahub.cmap.illinois.gov/dataset/councils-of-mayors-boundaries)
 #'
 #' @seealso
 #' <https://www.cmap.illinois.gov/committees/advisory/council-of-mayors/subregional-councils>
@@ -772,7 +753,7 @@
 #' }
 #'
 #' @source
-#' [CMAP Data Hub](https://datahub.cmap.illinois.gov/dataset/on-to-2050-layer-edas-disinvested-areas)
+#' [CMAP Data Hub (temporarily offline)](https://datahub.cmap.illinois.gov/dataset/on-to-2050-layer-edas-disinvested-areas)
 #'
 #' @seealso
 #' <https://www.cmap.illinois.gov/2050/maps/eda>
@@ -811,7 +792,7 @@
 #' }
 #'
 #' @source
-#' [CMAP Data Hub](https://datahub.cmap.illinois.gov/dataset/facility-planning-areas-fpa)
+#' [CMAP Data Hub (temporarily offline)](https://datahub.cmap.illinois.gov/dataset/facility-planning-areas-fpa)
 #'
 #' @seealso
 #' <https://www.cmap.illinois.gov/programs/water/water-quality/wastewater-planning>
@@ -875,7 +856,7 @@
 #' }
 #'
 #' @source
-#' [CMAP Data Hub](https://datahub.cmap.illinois.gov/dataset/cmap-modeling-zone-systems)
+#' [CMAP Data Hub (temporarily offline)](https://datahub.cmap.illinois.gov/dataset/cmap-modeling-zone-systems)
 #'
 #' @examples
 #' # Display the subzones with ggplot2
@@ -915,7 +896,7 @@
 #' }
 #'
 #' @source
-#' [CMAP Data Hub](https://datahub.cmap.illinois.gov/dataset/cmap-modeling-zone-systems)
+#' [CMAP Data Hub (temporarily offline)](https://datahub.cmap.illinois.gov/dataset/cmap-modeling-zone-systems)
 #'
 #' @examples
 #' # Display the zones with ggplot2

data-raw/generate_xwalks.R

@@ -2,7 +2,7 @@ library(tidyverse)
 devtools::load_all()
 
 # Set parameters
-tigerline_year <- 2021  # Latest TIGER/Line vintage
+tigerline_year <- 2022  # Latest TIGER/Line vintage
 lehd_year <- 2019  # Latest LEHD year available, for employment data
 census_year <- 2020  # Latest Decennial Census
 census_vars <- c("H1_001N", "H1_002N", "P1_001N")  # HU, HH, POP vars in 2020 redistricting data
@@ -54,10 +54,11 @@ lehd_data <- lehdr::grab_lodes(
   select(w_geocode, emp = C000)
 
 
-### PROCESS LEHD EMPLOYMENT DATA USING 2010 CENSUS BLOCKS ###
-# Note: this section is only needed until LEHD switches to use the 2020 blocks.
-# As of the 2019 LEHD, it still uses the 2010 blocks. Once it switches, remove
-# this section and the LEHD data will be joined to block_data directly.
+### PROCESS LEHD EMPLOYMENT DATA USING 2010 CENSUS BLOCKS
+### Note: this section is only needed until LEHD switches to use the 2020
+# blocks. This is still needed as of February 12, 2023. As of the 2019 LEHD, it
+# still uses the 2010 blocks. Once it switches, remove this section and the LEHD
+# data will be joined to block_data directly.
 
 # Get 2010 Census block geometries for entire modeling area
 block2010_21co_sf <- tigris::blocks(state = "IL", county = counties_il, year = 2019) %>%

data-raw/load_census_api.R

@@ -2,7 +2,7 @@ library(tidyverse)
 devtools::load_all()
 
 # Set common parameters
-BASE_YEAR <- 2021  # TIGER/Line vintage to use by default
+BASE_YEAR <- 2022  # TIGER/Line vintage to use by default
 STATE <- "17"  # Illinois
 COUNTIES_7CO <- c("031", "043", "089", "093", "097", "111", "197")  # CMAP 7
 COUNTIES_MPO <- c(COUNTIES_7CO, "063", "037")  # CMAP 7, plus Grundy and DeKalb
@@ -71,7 +71,7 @@ municipality_sf <- tigris::places(state = STATE, year = BASE_YEAR) %>%
   arrange(geoid_place)
 
 # Process Congressional Districts (U.S. House of Representatives)
-# Note: still 2011 districts, as of 2020 TIGER/Line
+# Note: still 2011 districts, as of 2022 TIGER/Line. Updates are expected in spring 2023.
 congress_sf <- tigris::congressional_districts(year = BASE_YEAR) %>%
   filter(STATEFP == STATE, LSAD == "C2") %>%
   sf::st_transform(cmap_crs) %>%
@@ -86,7 +86,7 @@ congress_sf <- tigris::congressional_districts(year = BASE_YEAR) %>%
   arrange(dist_num)
 
 # Process IL House Districts (Illinois General Assembly)
-# Note: still 2011 districts, as of 2020 TIGER/Line
+# Note: still 2011 districts, as of 2022 TIGER/Line. Updates are expected in spring 2023.
 ilga_house_sf <- tigris::state_legislative_districts(state = STATE, house = "lower", year = BASE_YEAR) %>%
   filter(LSAD == "LL") %>%
   sf::st_transform(cmap_crs) %>%
@@ -98,7 +98,7 @@ ilga_house_sf <- tigris::state_legislative_districts(state = STATE, house = "low
   arrange(dist_num)
 
 # Process IL Senate Districts (Illinois General Assembly)
-# Note: still 2011 districts, as of 2020 TIGER/Line
+# Note: still 2011 districts, as of 2022 TIGER/Line. Updates are expected in spring 2023.
 ilga_senate_sf <- tigris::state_legislative_districts(state = STATE, house = "upper", year = BASE_YEAR) %>%
   filter(LSAD == "LU") %>%
   sf::st_transform(cmap_crs) %>%
@@ -110,18 +110,16 @@ ilga_senate_sf <- tigris::state_legislative_districts(state = STATE, house = "up
   arrange(dist_num)
 
 # Process Public Use Microddata Areas (PUMAs)
-# Note: still 2010 boundaries, as of 2020 TIGER/Line
+# Note: Now includes 2020 boundaries, as of 2022 TIGER/Line
 puma_sf <- tigris::pumas(state = STATE, year = BASE_YEAR) %>%
   sf::st_transform(cmap_crs) %>%
   filter(intersects_cmap(.)) %>%  # Restrict to CMAP region
   rmapshaper::ms_erase(temp_lakemich_sf) %>%  # Erase Lake Michigan
-  rename(geoid_puma = GEOID10,
-         name = NAMELSAD10) %>%
+  rename(geoid_puma = GEOID20,
+         name = NAMELSAD20) %>%
   mutate(sqmi = unclass(sf::st_area(geometry) / sqft_per_sqmi)) %>%
   select(geoid_puma, name, sqmi) %>%
-  arrange(geoid_puma) %>%
-  ## Manually exclude one PUMA, which appears to mistakenly include a *tiny* block in McHenry
-  filter(geoid_puma != "1702901")
+  arrange(geoid_puma)
 
 # Process ZIP Code Tabulation Areas (ZCTAs)
 zcta_sf <- tigris::zctas(starts_with = "6", year = BASE_YEAR) %>%
@@ -187,36 +185,6 @@ block_sf <- tigris::blocks(state = STATE, county = COUNTIES_7CO, year = BASE_YEA
   arrange(geoid_block)
 
 
-# Process 2010 Census geographies (block, block group, tract)
-# Note: remove these datasets from cmapgeo once 2021 1-year ACS is released
-tract_sf_2010 <- tigris::tracts(state = STATE, county = COUNTIES_7CO, year = 2019) %>%
-  filter(TRACTCE != "990000") %>%  # Exclude Lake Michigan tracts
-  sf::st_transform(cmap_crs) %>%
-  rename(geoid_tract = GEOID) %>%
-  mutate(county_fips = paste0(STATEFP, COUNTYFP),
-         sqmi = unclass(sf::st_area(geometry) / sqft_per_sqmi)) %>%
-  select(geoid_tract, county_fips, sqmi) %>%
-  arrange(geoid_tract)
-
-blockgroup_sf_2010 <- tigris::block_groups(state = STATE, county = COUNTIES_7CO, year = 2019) %>%
-  filter(TRACTCE != "990000") %>%  # Exclude Lake Michigan tracts
-  sf::st_transform(cmap_crs) %>%
-  rename(geoid_blkgrp = GEOID) %>%
-  mutate(county_fips = paste0(STATEFP, COUNTYFP),
-         sqmi = unclass(sf::st_area(geometry) / sqft_per_sqmi)) %>%
-  select(geoid_blkgrp, county_fips, sqmi) %>%
-  arrange(geoid_blkgrp)
-
-block_sf_2010 <- tigris::blocks(state = STATE, county = COUNTIES_7CO, year = 2019) %>%
-  filter(TRACTCE10 != "990000") %>%  # Exclude Lake Michigan tracts
-  sf::st_transform(cmap_crs) %>%
-  rename(geoid_block = GEOID10) %>%
-  mutate(county_fips = paste0(STATEFP10, COUNTYFP10),
-         sqmi = unclass(sf::st_area(geometry) / sqft_per_sqmi)) %>%
-  select(geoid_block, county_fips, sqmi) %>%
-  arrange(geoid_block)
-
-
 # Save processed data to package's data dir
 usethis::use_data(county_sf, overwrite = TRUE)
 usethis::use_data(township_sf, overwrite = TRUE)
@@ -230,6 +198,3 @@ usethis::use_data(idot_sf, overwrite = TRUE)
 usethis::use_data(tract_sf, overwrite = TRUE)
 usethis::use_data(blockgroup_sf, overwrite = TRUE)
 usethis::use_data(block_sf, overwrite = TRUE)
-usethis::use_data(tract_sf_2010, overwrite = TRUE)
-usethis::use_data(blockgroup_sf_2010, overwrite = TRUE)
-usethis::use_data(block_sf_2010, overwrite = TRUE)