2022 and 2024 data

Created a version of datadoc_cd-info and create_dist-level-data for 2022 and 2024 data

R/datadoc_cd-info.R

@@ -32,7 +32,7 @@
 #'    2018 given by Daily Kos. Some edits are made for changing district. See
 #'    Source for full citation.}
 #'    \item{largest_place}{The largest place in the district code in 2018 given by Daily Kos. Multiple districts may
-#'    have the largest place.}
+#'    have the same largest place.}
 #'  }
 #'
 #'

R/new_datadoc_cd-info.R

@@ -0,0 +1,68 @@
+#' Congressional District level information by The Downballot (formerly Daily Kos)
+#'
+#'
+#' Some of the most consequential variables to include in MRP are at the
+#' district-level. We include one such data for congressional districts. All data
+#' is collected by The Downballot. `cd_info_2022` is data on 2022 boundaries; `cd_info_2024`
+#' uses 2024 boundaries.
+#'
+#' @format Both `cd_info_2022` and `cd_info_2024` are dataframes with all `r nrow(cd_info_2022)` Congressional
+#'  Districts, one row per cd.
+#'  \describe{
+#'    \item{year}{The year for the district line. A congressional district's
+#'    actual geography can change year to year, and significantly so in different
+#'    redistricting cycles. Lines try to get the contemporaneous district map,
+#'    so that cd_info_2022 uses 2022 maps and cd_info_2024 uses 2024 maps.}
+#'    \item{cd}{District code. The formatting corresponds to the CCES cumulative
+#'    coding of \code{cd}: a two-letter abbreviation for the state followed by
+#'    a dash, and the district number padded with zeros to the left to be of length
+#'    2. At-large districts like Alaska are given a "-AL" for the district number.}
+#'    \item{presvotes_total}{In presidential years, the total number of votes cast for
+#'     the office of President that year. Taken from the Downballot estimates from precinct results.}
+#'    \item{pct_trump}{The two-party voteshare of Donald Trump in that district in 2020.}
+#'    \item{downballot_name}{The unique descriptive name for the district code in
+#'    2018 given by The Downballot. Some edits are made for changing district. See
+#'    Source for full citation.}
+#'    \item{largest_place}{The largest place in the district code in 2020 given by The Downballot. Multiple districts may
+#'    have the same largest place.}
+#'  }
+#'
+#'
+#' @source
+#'   The Downballot (formerly Daily Kos Elections), \url{https://www.the-downballot.com/p/data}
+#'
+#' @source
+#'   The Daily Kos Elections naming guide to the nation's congressional districts.
+#'   \url{https://bit.ly/2XsFI5W}
+#'
+#'   The Downballot, "Daily Kos Elections 2020 presidential election results for congressional districts used in 2022 elections"
+#'   \url{https://docs.google.com/spreadsheets/d/1CKngqOp8fzU22JOlypoxNsxL6KSAH920Whc-rd7ebuM/edit?usp=sharing}
+#'
+#'   The Downballot, "Daily Kos Elections 2020 presidential election results for congressional districts used in 2024 elections"
+#'   \url{https://docs.google.com/spreadsheets/d/1Sg4ZZz5FcX7lz-m2xqmYtndaO2uEMSaL7x99AbQOvv8/edit?usp=sharing}
+#'
+#'   The Downballot, "Daily Kos Elections 2020 presidential results by congressional district (old CDs used in 2020 vs. new CDs used in 2022)"
+#'   \url{https://docs.google.com/spreadsheets/d/1IfZ8OVWXVpdAvxZtTaDIA2HEN6DtN-H0I0J2KcdxRi4/edit?usp=sharing}
+#'
+#'   The Downballot, "Daily Kos Elections congressional district geographic descriptions & largest places (119th Congress)"
+#'   \url{https://docs.google.com/spreadsheets/d/12YaBonkqHAjkXhzyKlH2-1t-smZ6J5j76RCBSJEwQHo/edit?usp=sharing}
+#'
+#'   The Downballot, "Daily Kos Elections congressional district geographic descriptions & largest places (118th Congress)"
+#'   \url{https://docs.google.com/spreadsheets/d/1weoLFu2U5lmxQNcB8pFItGHj1Lb_M2E9Oi48sI4w1vY/edit?usp=sharing}
+#'
+#'   The Downballot, "Congressional district geographic descriptions and largest places (117th Congress)"
+#'   \url{https://docs.google.com/spreadsheets/d/16GoSYgRx5Mqfyfd355FMDRtr13tOAXFDOT94d9Dzwt0/edit?usp=sharing}
+#'
+#'   Also see Cha, Jeremiah; Kuriwaki, Shiro; Snyder, James M. Jr., 2021,
+#'    "Candidates in American General Elections", https://doi.org/10.7910/DVN/DGDRDT,
+#'    Harvard Dataverse.
+#'
+#' @importFrom tibble tibble
+#'
+#' @examples
+#' head(cd_info_2022)
+"cd_info_2022"
+
+
+#' @rdname cd_info_2022
+"cd_info_2024"

data-raw/new_create_dist-level-data.R

@@ -0,0 +1,64 @@
+library(tidyverse)
+library(googlesheets4)
+
+# Authenticate with Google Sheets
+gs4_auth()
+
+# URLs for your Google Sheets
+url_2022 <- "https://docs.google.com/spreadsheets/d/1CKngqOp8fzU22JOlypoxNsxL6KSAH920Whc-rd7ebuM/edit?usp=sharing"
+url_2024 <- "https://docs.google.com/spreadsheets/d/1Sg4ZZz5FcX7lz-m2xqmYtndaO2uEMSaL7x99AbQOvv8/edit?usp=sharing"
+url_geo_119 <- "https://docs.google.com/spreadsheets/d/12YaBonkqHAjkXhzyKlH2-1t-smZ6J5j76RCBSJEwQHo/edit?usp=sharing"
+url_geo_118 <- "https://docs.google.com/spreadsheets/d/1weoLFu2U5lmxQNcB8pFItGHj1Lb_M2E9Oi48sI4w1vY/edit?usp=sharing"
+
+# Read data from Google Sheets
+
+# 2022
+cd_info_2022 <- read_sheet(url_2022, sheet = 1) %>%
+  mutate(year = 2022) %>%
+  select(year, cd = District)
+
+voting_info_2022 <- read_sheet(url_2022, sheet = 2) %>%
+  select(cd = District,
+         presvotes_total = Total,
+         pct_trump = 'Trump %')
+
+region_2022 <- read_sheet(url_geo_118, sheet = 1) %>%
+  select(cd = CD,
+         dailykos_name = `Geographic Description`)
+
+largest_place_2022 <- read_sheet(url_geo_118, sheet = 2) %>%
+  select(cd = CD,
+         largest_place = `Largest place`)
+
+# 2024
+cd_info_2024 <- read_sheet(url_2024, sheet = 1) %>%
+  mutate(year = 2024) %>%
+  select(year, cd = District)
+
+voting_info_2024 <- read_sheet(url_2024, sheet = 2) %>%
+  select(cd = District,
+         presvotes_total = Total,
+         pct_trump = 'Trump %')
+
+region_2024 <- read_sheet(url_geo_119, sheet = 1) %>%
+  select(cd = CD,
+         dailykos_name = `Geographic Description`)
+
+largest_place_2024 <- read_sheet(url_geo_119, sheet = 2) %>%
+  select(cd = CD,
+         largest_place = `Largest place`)
+
+# Join geographic descriptions to the main datasets
+cd_info_2022 <- cd_info_2022 %>%
+  left_join(region_2022, by = "cd") %>%
+  left_join(largest_place_2022, by = "cd") %>%
+  left_join(voting_info_2022, by = "cd")
+
+cd_info_2024 <- cd_info_2024 %>%
+  left_join(region_2024, by = "cd") %>%
+  left_join(largest_place_2024, by = "cd") %>%
+  left_join(voting_info_2024, by = "cd")
+
+# Save the data
+usethis::use_data(cd_info_2022, overwrite = TRUE)
+usethis::use_data(cd_info_2024, overwrite = TRUE)