Add historical subdomains

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: IMD
 Type: Package
 Title: Index of Multiple Deprivation Data for the UK
-Version: 2.0.0
+Version: 2.0.0.9000
 Authors@R: c(
     person(given = c("Matthew", "Gwynfryn"), 
            family = "Thomas", 
@@ -30,7 +30,7 @@ URL: https://github.com/humaniverse/IMD
 BugReports: https://github.com/humaniverse/IMD/issues
 Encoding: UTF-8
 LazyData: true
-LazyDataCompression:xz
+LazyDataCompression: xz
 RoxygenNote: 7.3.3
 Imports:
     rlang,

NEWS.md

@@ -1,3 +1,7 @@
+# IMD (development version)
+
+- Added subdomain data for England's 2004, 2007, 2010 and 2015 Indices of Deprivation
+
 # IMD 2.0.0
 
 ## Breaking changes

R/data.R

@@ -1488,6 +1488,36 @@ NULL
 #' @source \url{https://www.gov.uk/}
 "imd2015_england_lsoa11"
 
+#' Index of Multiple Deprivation (2015) subdomains for LSOAs in England
+#'
+#' A data set containing subdomain scores, ranks and deciles for LSOAs in England.
+#'
+#' @format A data frame of class "tbl" with 32,844 rows and 19 variables:
+#' \describe{
+#'   \item{lsoa11_code}{LSOA (2011) code}
+#'   \item{adult_skills_sub_domain_score}{Adult Skills score}
+#'   \item{children_and_young_people_sub_domain_score}{Children and Young People score}
+#'   \item{adult_skills_sub_domain_rank}{Adult Skills rank}
+#'   \item{children_and_young_people_sub_domain_rank}{Children and Young People rank}
+#'   \item{adult_skills_sub_domain_decile}{Adult Skills decile}
+#'   \item{children_and_young_people_sub_domain_decile}{Children and Young People decile}
+#'   \item{wider_barriers_sub_domain_score}{Wider Barriers score}
+#'   \item{geographical_barriers_sub_domain_score}{Geographical Barriers score}
+#'   \item{wider_barriers_sub_domain_rank}{Wider Barriers rank}
+#'   \item{geographical_barriers_sub_domain_rank}{Geographical Barriers rank}
+#'   \item{wider_barriers_sub_domain_decile}{Wider Barriers decile}
+#'   \item{geographical_barriers_sub_domain_decile}{Geographical Barriers decile}
+#'   \item{indoors_sub_domain_score}{Indoors score}
+#'   \item{outdoors_sub_domain_score}{Outdoors score}
+#'   \item{indoors_sub_domain_rank}{Indoors rank}
+#'   \item{outdoors_sub_domain_rank}{Outdoors ranks}
+#'   \item{indoors_sub_domain_decile}{Indoors decile}
+#'   \item{outdoors_sub_domain_decile}{Outdoors decile}
+#'   ...
+#' }
+#' @source \url{https://www.gov.uk/}
+"imd2015_england_lsoa01_subdomains"
+
 #' Index of Multiple Deprivation (2015) for Local Authorities in England
 #'
 #' A data set containing IMD proportions and extents for Local Authorites
@@ -1555,6 +1585,36 @@ NULL
 #' @source \url{https://www.gov.uk/}
 "imd2010_england_lsoa01"
 
+#' Index of Multiple Deprivation (2010) subdomains for LSOAs in England
+#'
+#' A data set containing subdomain scores, ranks and deciles for LSOAs in England.
+#'
+#' @format A data frame of class "tbl" with 32,482 rows and 19 variables:
+#' \describe{
+#'   \item{lsoa01_code}{LSOA (2001) code}
+#'   \item{skills_sub_domain_score}{Skills score}
+#'   \item{children_young_people_sub_domain_score}{Children and Young People score}
+#'   \item{skills_sub_domain_rank}{Skills rank}
+#'   \item{children_young_people_sub_domain_rank}{Children and Young People rank}
+#'   \item{skills_sub_domain_decile}{Skills decile}
+#'   \item{children_young_people_sub_domain_decile}{Children and Young People decile}
+#'   \item{wider_barriers_sub_domain_score}{Wider Barriers score}
+#'   \item{geographical_barriers_sub_domain_score}{Geographical Barriers score}
+#'   \item{wider_barriers_sub_domain_rank}{Wider Barriers rank}
+#'   \item{geographical_barriers_sub_domain_rank}{Geographical Barriers rank}
+#'   \item{wider_barriers_sub_domain_decile}{Wider Barriers decile}
+#'   \item{geographical_barriers_sub_domain_decile}{Geographical Barriers decile}
+#'   \item{indoors_sub_domain_score}{Indoors score}
+#'   \item{outdoors_sub_domain_score}{Outdoors score}
+#'   \item{indoors_sub_domain_rank}{Indoors rank}
+#'   \item{outdoors_sub_domain_rank}{Outdoors ranks}
+#'   \item{indoors_sub_domain_decile}{Indoors decile}
+#'   \item{outdoors_sub_domain_decile}{Outdoors decile}
+#'   ...
+#' }
+#' @source \url{https://www.gov.uk/}
+"imd2010_england_lsoa01_subdomains"
+
 #' Index of Multiple Deprivation (2010) for Local Authorities in England
 #'
 #' A data set containing IMD scores, proportions and extents for Local
@@ -1650,6 +1710,45 @@ NULL
 #' @source \url{https://www.gov.uk/}
 "imd2007_england_lsoa01"
 
+#' Index of Multiple Deprivation (2007) subdomains for LSOAs in England
+#'
+#' A data set containing subdomain scores, ranks and deciles for LSOAs in England.
+#'
+#' @format A data frame of class "tbl" with 32,482 rows and 28 variables:
+#' \describe{
+#'   \item{lsoa01_code}{LSOA (2001) code}
+#'   \item{skills_sub_domain_score}{Skills score}
+#'   \item{children_young_people_sub_domain_score}{Children and Young People score}
+#'   \item{education_skills_and_training_domain_score}{Education, Skills and Training score}
+#'   \item{skills_sub_domain_rank}{Skills rank}
+#'   \item{children_young_people_sub_domain_rank}{Children and Young People rank}
+#'   \item{education_skills_and_training_domain_rank}{Education, Skills and Training rank}
+#'   \item{skills_sub_domain_decile}{Skills decile}
+#'   \item{children_young_people_sub_domain_decile}{Children and Young People decile}
+#'   \item{education_skills_and_training_domain_decile}{Education, Skills and Training decile}
+#'   \item{wider_barriers_sub_domain_score}{Wider Barriers score}
+#'   \item{geographical_barriers_sub_domain_score}{Geographical Barriers score}
+#'   \item{barriers_to_housing_and_services_domain_score}{Barriers to Housing and Services score}
+#'   \item{wider_barriers_sub_domain_rank}{Wider Barriers rank}
+#'   \item{geographical_barriers_sub_domain_rank}{Geographical Barriers rank}
+#'   \item{barriers_to_housing_and_services_domain_rank}{Barriers to Housing and Services rank}
+#'   \item{wider_barriers_sub_domain_decile}{Wider Barriers decile}
+#'   \item{geographical_barriers_sub_domain_decile}{Geographical Barriers decile}
+#'   \item{barriers_to_housing_and_services_domain_decile}{Barriers to Housing and Services decile}
+#'   \item{indoors_sub_domain_score}{Indoors score}
+#'   \item{outdoors_sub_domain_score}{Outdoors score}
+#'   \item{living_environment_domain_score}{Living Environment score}
+#'   \item{indoors_sub_domain_rank}{Indoors rank}
+#'   \item{outdoors_sub_domain_rank}{Outdoors ranks}
+#'   \item{living_environment_domain_rank}{Living Environment rank}
+#'   \item{indoors_sub_domain_rank_decile}{Indoors decile}
+#'   \item{outdoors_sub_domain_rank_decile}{Outdoors decile}
+#'   \item{living_environment_domain_decile}{Living Environment decile}
+#'   ...
+#' }
+#' @source \url{https://www.gov.uk/}
+"imd2007_england_lsoa01_subdomains"
+
 #' Index of Multiple Deprivation (2007) for Local Authorities in England
 #'
 #' A data set containing IMD scores, proportions and extents for Local
@@ -1699,6 +1798,45 @@ NULL
 #' @source \url{https://www.gov.uk/}
 "imd2004_england_lsoa01"
 
+#' Index of Multiple Deprivation (2004) subdomains for LSOAs in England
+#'
+#' A data set containing subdomain scores, ranks and deciles for LSOAs in England.
+#'
+#' @format A data frame of class "tbl" with 32,482 rows and 28 variables:
+#' \describe{
+#'   \item{lsoa01_code}{LSOA (2001) code}
+#'   \item{skills_sub_domain_score}{Skills score}
+#'   \item{children_young_people_sub_domain_score}{Children and Young People score}
+#'   \item{education_skills_and_training_domain_score}{Education, Skills and Training score}
+#'   \item{skills_sub_domain_rank}{Skills rank}
+#'   \item{children_young_people_sub_domain_rank}{Children and Young People rank}
+#'   \item{education_skills_and_training_domain_rank}{Education, Skills and Training rank}
+#'   \item{skills_sub_domain_decile}{Skills decile}
+#'   \item{children_young_people_sub_domain_decile}{Children and Young People decile}
+#'   \item{education_skills_and_training_domain_decile}{Education, Skills and Training decile}
+#'   \item{wider_barriers_sub_domain_score}{Wider Barriers score}
+#'   \item{geographical_barriers_sub_domain_score}{Geographical Barriers score}
+#'   \item{barriers_to_housing_and_services_domain_score}{Barriers to Housing and Services score}
+#'   \item{wider_barriers_sub_domain_rank}{Wider Barriers rank}
+#'   \item{geographical_barriers_sub_domain_rank}{Geographical Barriers rank}
+#'   \item{barriers_to_housing_and_services_domain_rank}{Barriers to Housing and Services rank}
+#'   \item{wider_barriers_sub_domain_decile}{Wider Barriers decile}
+#'   \item{geographical_barriers_sub_domain_decile}{Geographical Barriers decile}
+#'   \item{barriers_to_housing_and_services_domain_decile}{Barriers to Housing and Services decile}
+#'   \item{indoors_sub_domain_score}{Indoors score}
+#'   \item{outdoors_sub_domain_score}{Outdoors score}
+#'   \item{living_environment_domain_score}{Living Environment score}
+#'   \item{indoors_sub_domain_rank}{Indoors rank}
+#'   \item{outdoors_sub_domain_rank}{Outdoors ranks}
+#'   \item{living_environment_domain_rank}{Living Environment rank}
+#'   \item{indoors_sub_domain_decile}{Indoors decile}
+#'   \item{outdoors_sub_domain_decile}{Outdoors decile}
+#'   \item{living_environment_domain_decile}{Living Environment decile}
+#'   ...
+#' }
+#' @source \url{https://www.gov.uk/}
+"imd2004_england_lsoa01_subdomains"
+
 #' Index of Multiple Deprivation (2004) for Local Authorities in England
 #'
 #' A data set containing IMD scores, proportions and extents for Local

data-raw/imd2004_england_lsoa01_subdomains.R

@@ -0,0 +1,85 @@
+library(tidyverse)
+library(devtools)
+library(readxl)
+library(janitor)
+library(compositr)
+
+# Load package
+load_all(".")
+
+# Set query url
+# query_url <-
+#   query_urls |>
+#   filter(data_set == "imd2004_lsoa01_england_subdomains") |>
+#   pull(query_url)
+
+# Had to download the file and unzip manually
+imd2004_education <- read_excel("data-raw/imd2004_england_lsoa01_subdomains.xls", sheet = "Education Skills & Training")
+imd2004_barriers <- read_excel("data-raw/imd2004_england_lsoa01_subdomains.xls", sheet = "Barriers to Housing & Services")
+imd2004_environment <- read_excel("data-raw/imd2004_england_lsoa01_subdomains.xls", sheet = "Living Environment")
+
+# Select data and calculate ranks and deciles
+imd2004_education <-
+  imd2004_education |>
+  clean_names() |> 
+  select(
+    lsoa01_code = soa_code,
+    skills_sub_domain_score,
+    children_young_people_sub_domain_score,
+    education_skills_and_training_domain_score
+  ) |>
+  mutate(
+    skills_sub_domain_rank = invert_rank(skills_sub_domain_score),
+    children_young_people_sub_domain_rank = invert_rank(children_young_people_sub_domain_score),
+    education_skills_and_training_domain_rank = invert_rank(education_skills_and_training_domain_score),
+
+    skills_sub_domain_decile = ntile(skills_sub_domain_rank, n = 10),
+    children_young_people_sub_domain_decile = ntile(children_young_people_sub_domain_rank, n = 10),
+    education_skills_and_training_domain_decile = ntile(education_skills_and_training_domain_rank, n = 10)
+  )
+
+imd2004_barriers <-
+  imd2004_barriers |>
+  clean_names() |> 
+  select(
+    lsoa01_code = soa_code,
+    wider_barriers_sub_domain_score,
+    geographical_barriers_sub_domain_score,
+    barriers_to_housing_and_services_domain_score
+  ) |>
+  mutate(
+    wider_barriers_sub_domain_rank = invert_rank(wider_barriers_sub_domain_score),
+    geographical_barriers_sub_domain_rank = invert_rank(geographical_barriers_sub_domain_score),
+    barriers_to_housing_and_services_domain_rank = invert_rank(barriers_to_housing_and_services_domain_score),
+
+    wider_barriers_sub_domain_decile = ntile(wider_barriers_sub_domain_rank, n = 10),
+    geographical_barriers_sub_domain_decile = ntile(geographical_barriers_sub_domain_rank, n = 10),
+    barriers_to_housing_and_services_domain_decile = ntile(barriers_to_housing_and_services_domain_rank, n = 10)
+  )
+
+imd2004_environment <- 
+  imd2004_environment |>
+  clean_names() |> 
+  select(
+    lsoa01_code = soa_code,
+    indoors_sub_domain_score = indoors_sub_domain,
+    outdoors_sub_domain_score = outdoors_sub_domain,
+    living_environment_domain_score = living_environment_domain
+  ) |>
+  mutate(
+    indoors_sub_domain_rank = invert_rank(indoors_sub_domain_score),
+    outdoors_sub_domain_rank = invert_rank(outdoors_sub_domain_score),
+    living_environment_domain_rank = invert_rank(living_environment_domain_score),
+
+    indoors_sub_domain_decile = ntile(indoors_sub_domain_rank, n = 10),
+    outdoors_sub_domain_decile = ntile(outdoors_sub_domain_rank, n = 10),
+    living_environment_domain_decile = ntile(living_environment_domain_score, n = 10)
+  )
+
+imd2004_england_lsoa01_subdomains <- 
+  imd2004_education |> 
+  left_join(imd2004_barriers) |> 
+  left_join(imd2004_environment)
+
+# Save output to data/ folder
+usethis::use_data(imd2004_england_lsoa01_subdomains, overwrite = TRUE)

data-raw/imd2007_england_lsoa01_subdomains.R

@@ -0,0 +1,85 @@
+library(tidyverse)
+library(devtools)
+library(readxl)
+library(janitor)
+library(compositr)
+
+# Load package
+load_all(".")
+
+# Set query url
+# query_url <-
+#   query_urls |>
+#   filter(data_set == "imd2007_lsoa01_england_subdomains") |>
+#   pull(query_url)
+
+# Had to download the file and unzip manually
+imd2007_education <- read_excel("data-raw/imd2007_england_lsoa01_subdomains.xls", sheet = "Education Skills & Training")
+imd2007_barriers <- read_excel("data-raw/imd2007_england_lsoa01_subdomains.xls", sheet = "Barriers to Housing & Services")
+imd2007_environment <- read_excel("data-raw/imd2007_england_lsoa01_subdomains.xls", sheet = "Living Environment")
+
+# Select data and calculate ranks and deciles
+imd2007_education <-
+  imd2007_education |>
+  clean_names() |> 
+  select(
+    lsoa01_code = lsoa_code,
+    skills_sub_domain_score,
+    children_young_people_sub_domain_score,
+    education_skills_and_training_domain_score
+  ) |>
+  mutate(
+    skills_sub_domain_rank = invert_rank(skills_sub_domain_score),
+    children_young_people_sub_domain_rank = invert_rank(children_young_people_sub_domain_score),
+    education_skills_and_training_domain_rank = invert_rank(education_skills_and_training_domain_score),
+
+    skills_sub_domain_decile = ntile(skills_sub_domain_rank, n = 10),
+    children_young_people_sub_domain_decile = ntile(children_young_people_sub_domain_rank, n = 10),
+    education_skills_and_training_domain_decile = ntile(education_skills_and_training_domain_rank, n = 10)
+  )
+
+imd2007_barriers <-
+  imd2007_barriers |>
+  clean_names() |> 
+  select(
+    lsoa01_code = lsoa_code,
+    wider_barriers_sub_domain_score,
+    geographical_barriers_sub_domain_score,
+    barriers_to_housing_and_services_domain_score
+  ) |>
+  mutate(
+    wider_barriers_sub_domain_rank = invert_rank(wider_barriers_sub_domain_score),
+    geographical_barriers_sub_domain_rank = invert_rank(geographical_barriers_sub_domain_score),
+    barriers_to_housing_and_services_domain_rank = invert_rank(barriers_to_housing_and_services_domain_score),
+
+    wider_barriers_sub_domain_decile = ntile(wider_barriers_sub_domain_rank, n = 10),
+    geographical_barriers_sub_domain_decile = ntile(geographical_barriers_sub_domain_rank, n = 10),
+    barriers_to_housing_and_services_domain_decile = ntile(barriers_to_housing_and_services_domain_rank, n = 10)
+  )
+
+imd2007_environment <- 
+  imd2007_environment |>
+  clean_names() |> 
+  select(
+    lsoa01_code = lsoa_code,
+    indoors_sub_domain_score = indoors_sub_domain,
+    outdoors_sub_domain_score = outdoors_sub_domain,
+    living_environment_domain_score = living_environment_domain
+  ) |>
+  mutate(
+    indoors_sub_domain_rank = invert_rank(indoors_sub_domain_score),
+    outdoors_sub_domain_rank = invert_rank(outdoors_sub_domain_score),
+    living_environment_domain_rank = invert_rank(living_environment_domain_score),
+
+    indoors_sub_domain_rank_decile = ntile(indoors_sub_domain_rank, n = 10),
+    outdoors_sub_domain_rank_decile = ntile(outdoors_sub_domain_rank, n = 10),
+    living_environment_domain_decile = ntile(living_environment_domain_score, n = 10)
+  )
+
+imd2007_england_lsoa01_subdomains <- 
+  imd2007_education |> 
+  left_join(imd2007_barriers) |> 
+  left_join(imd2007_environment)
+
+# Save output to data/ folder
+usethis::use_data(imd2007_england_lsoa01_subdomains, overwrite = TRUE)

data-raw/imd2010_england_lsoa01_subdomains.R

@@ -0,0 +1,34 @@
+library(tidyverse)
+library(devtools)
+library(janitor)
+
+# Load package
+load_all(".")
+
+# Set query url
+query_url <-
+  query_urls |>
+  filter(data_set == "imd2010_lsoa01_england") |>
+  pull(query_url)
+
+imd2010 <- read_csv(query_url)
+
+imd2010_england_lsoa01_subdomains <-
+  imd2010 |>
+  select(
+    lsoa01_code = `LSOA CODE`,
+    contains("Sub-domain")
+  ) |>
+  rename_with(~ str_remove(.x, fixed(" (where 1 is most deprived)"))) |> 
+  clean_names() |> 
+  mutate(
+    indoors_sub_domain_decile = ntile(indoors_sub_domain_rank, n = 10),
+    outdoors_sub_domain_decile = ntile(outdoors_sub_domain_rank, n = 10),
+    geographical_barriers_sub_domain_decile = ntile(geographical_barriers_sub_domain_rank, n = 10),
+    wider_barriers_sub_domain_decile = ntile(wider_barriers_sub_domain_rank, n = 10),
+    children_young_people_sub_domain_decile = ntile(children_young_people_sub_domain_rank, n = 10),
+    skills_sub_domain_decile = ntile(skills_sub_domain_rank, n = 10)
+  )
+
+# Save output to data/ folder
+usethis::use_data(imd2010_england_lsoa01_subdomains, overwrite = TRUE)