Rename the IT CHI deaths file functions (#698)

* Rename the IT CHI deaths file functions

* Update documentation

* [check-spelling] Update metadata

Update for https://github.com/Public-Health-Scotland/source-linkage-files/actions/runs/5331531642/attempts/1
Accepted in #698 (comment)

Signed-off-by: check-spelling-bot <[email protected]>

---------

Signed-off-by: check-spelling-bot <[email protected]>
Co-authored-by: Moohan <[email protected]>
Co-authored-by: Jennit07 <[email protected]>

.github/actions/spelling/expect.txt

@@ -198,4 +198,5 @@ xlsx
 yearstay
 YYYYQX
 zsav
-zstd
+zstd
+zstd

NAMESPACE

@@ -55,7 +55,7 @@ export(get_service_use_cohorts_path)
 export(get_sg_homelessness_pub_path)
 export(get_simd_path)
 export(get_slf_ch_name_lookup_path)
-export(get_slf_deaths_path)
+export(get_slf_chi_deaths_path)
 export(get_slf_dir)
 export(get_slf_ep_temp_path)
 export(get_slf_gpprac_path)
@@ -94,7 +94,7 @@ export(process_extract_nrs_deaths)
 export(process_extract_outpatients)
 export(process_extract_prescribing)
 export(process_extract_sds)
-export(process_lookup_chi_deaths)
+export(process_it_chi_deaths)
 export(process_lookup_gpprac)
 export(process_lookup_ltc)
 export(process_lookup_postcode)
@@ -115,6 +115,7 @@ export(process_tests_gp_ooh)
 export(process_tests_home_care)
 export(process_tests_homelessness)
 export(process_tests_individual_file)
+export(process_tests_it_chi_deaths)
 export(process_tests_lookup_gpprac)
 export(process_tests_lookup_pc)
 export(process_tests_ltcs)
@@ -126,7 +127,6 @@ export(process_tests_prescribing)
 export(process_tests_sc_ch_episodes)
 export(process_tests_sc_demographics)
 export(process_tests_sds)
-export(produce_slf_deaths_tests)
 export(produce_source_extract_tests)
 export(produce_test_comparison)
 export(read_extract_acute)
@@ -142,7 +142,7 @@ export(read_extract_nrs_deaths)
 export(read_extract_outpatients)
 export(read_extract_prescribing)
 export(read_file)
-export(read_lookup_chi_deaths)
+export(read_it_chi_deaths)
 export(read_lookup_ltc)
 export(read_lookup_sc_client)
 export(read_lookup_sc_demographics)

R/get_slf_lookup_paths.R

@@ -40,6 +40,9 @@ get_slf_gpprac_path <- function(update = latest_update(), ...) {
 #'
 #' @description Get the full path to the SLF deaths lookup file
 #'
+#'
+#' @description Get the full path to the CHI deaths file
+#'
 #' @param update The update month to use,
 #' defaults to [latest_update()]
 #' @param ... additional arguments passed to [get_file_path()]
@@ -48,14 +51,14 @@ get_slf_gpprac_path <- function(update = latest_update(), ...) {
 #' @export
 #' @family slf lookup file path
 #' @seealso [get_file_path()] for the generic function.
-get_slf_deaths_path <- function(update = latest_update(), ...) {
-  slf_deaths_file_path <- get_file_path(
+get_slf_chi_deaths_path <- function(update = latest_update(), ...) {
+  slf_chi_deaths_path <- get_file_path(
     directory = fs::path(get_slf_dir(), "Deaths"),
-    file_name = stringr::str_glue("all_deaths_{update}.rds"),
+    file_name = stringr::str_glue("chi_deaths_{update}.parquet"),
     ...
   )
 
-  return(slf_deaths_file_path)
+  return(slf_chi_deaths_path)
 }
 
 #' Get the full path to the SLF read code lookup

R/process_it_chi_deaths.R

@@ -0,0 +1,31 @@
+#' Process the CHI deaths extract
+#'
+#' @description This will process the CHI deaths extract, it will return the
+#' final data and write the data out.
+#'
+#' @param data The extract to process
+#' @param write_to_disk (optional) Should the data be written to disk default is
+#' `TRUE` i.e. write the data to disk.
+#'
+#' @return the final data as a [tibble][tibble::tibble-package].
+#' @export
+#' @family process extracts
+process_it_chi_deaths <- function(data, write_to_disk = TRUE) {
+  it_chi_deaths_clean <- data %>%
+    dplyr::arrange(
+      dplyr::desc(.data$death_date_nrs),
+      dplyr::desc(.data$death_date_chi)
+    ) %>%
+    dplyr::distinct(.data$chi, .keep_all = TRUE) %>%
+    # Use the NRS death_date unless it isn't there
+    dplyr::mutate(
+      death_date = dplyr::coalesce(.data$death_date_nrs, .data$death_date_chi)
+    )
+
+  if (write_to_disk) {
+    it_chi_deaths_clean %>%
+      write_file(get_slf_chi_deaths_path(check_mode = "write"))
+  }
+
+  return(it_chi_deaths_clean)
+}

R/produce_slf_deaths_tests.R → R/process_tests_it_chi_deaths.R

@@ -1,15 +1,31 @@
-#' SLF Deaths Lookup Tests
+#' Process CHI Deaths tests
 #'
-#' @description Produce the tests for SLF deaths lookup
+#' @inherit process_tests_lookup_pc
+#'
+#' @export
+process_tests_it_chi_deaths <- function(data, update = previous_update()) {
+  comparison <- produce_test_comparison(
+    old_data = produce_it_chi_deaths_tests(
+      read_file(get_slf_chi_deaths_path(update = update))
+    ),
+    new_data = produce_it_chi_deaths_tests(data)
+  ) %>%
+    write_tests_xlsx(sheet_name = "it_chi_deaths")
+
+  return(comparison)
+}
+
+#' CHI death tests
+#'
+#' @description Produce the tests for IT CHI deaths
 #'
 #' @param data new or old data for testing summary
-#' flags (data is from [get_slf_deaths_path()])
+#' flags (data is from [get_slf_chi_deaths_path()])
 #
 #' @return a dataframe with a count of each flag
 #' from [calculate_measures()]
-#' @export
 #' @family slf test functions
-produce_slf_deaths_tests <- function(data) {
+produce_it_chi_deaths_tests <- function(data) {
   data %>%
     # create test flags
     dplyr::mutate(

R/read_lookup_chi_deaths.R → R/read_it_chi_deaths.R

@@ -1,30 +1,24 @@
-#' Process the CHI deaths lookup
-#'
-#' @description This will read and process the
-#' CHI deaths lookup, it will return the final data
-#' but also write this out as an rds.
+#' Read the CHI deaths extract
 #'
+#' @description This will read the CHI deaths extract and return the data.
 #' @param file_path Path to CHI Deaths file
 #'
 #' @return the final data as a [tibble][tibble::tibble-package].
 #' @export
 #' @family process extracts
-
-read_lookup_chi_deaths <- function(file_path = get_it_deaths_path()) {
-  # Read data -------------------------------------------------------
-  deaths_data <- read_file(file_path,
+read_it_chi_deaths <- function(file_path = get_it_deaths_path()) {
+  it_chi_deaths <- read_file(file_path,
     col_type = cols(
       "PATIENT_UPI [C]" = col_character(),
       "PATIENT DoD DATE (NRS)" = col_date(format = "%d-%m-%Y"),
       "PATIENT DoD DATE (CHI)" = col_date(format = "%d-%m-%Y")
     )
   ) %>%
-    # rename variables
     dplyr::rename(
       chi = "PATIENT_UPI [C]",
       death_date_nrs = "PATIENT DoD DATE (NRS)",
       death_date_chi = "PATIENT DoD DATE (CHI)"
     )
 
-  return(deaths_data)
+  return(it_chi_deaths)
 }

_targets.R

@@ -29,9 +29,9 @@ list(
   tar_target(locality_path, get_locality_path(), format = "file"),
   tar_target(simd_path, get_simd_path(), format = "file"),
   tar_target(spd_path, get_spd_path(), format = "file"),
-  tar_file_read(chi_deaths_data,
+  tar_file_read(it_chi_deaths_extract,
     command = get_it_deaths_path(),
-    read = read_lookup_chi_deaths(!!.x)
+    read = read_it_chi_deaths(!!.x)
   ),
   tar_file_read(dd_data, get_dd_path(), read_extract_delayed_discharges(!!.x)),
   tar_file_read(ltc_data, get_it_ltc_path(), read_lookup_ltc(!!.x)),
@@ -56,14 +56,17 @@ list(
     sc_demog_lookup_tests,
     process_tests_sc_demographics(sc_demog_lookup)
   ),
-  # TODO add tests for the CHI deaths lookup
   tar_target(
-    slf_chi_deaths_lookup,
-    process_lookup_chi_deaths(
-      data = chi_deaths_data,
+    it_chi_deaths_data,
+    process_it_chi_deaths(
+      data = it_chi_deaths_extract,
       write_to_disk = write_to_disk
     )
   ),
+  tar_target(
+    it_chi_deaths_tests,
+    process_tests_it_chi_deaths(it_chi_deaths_data)
+  ),
   tar_target(
     source_gp_lookup,
     process_lookup_gpprac(