Investigate missing datazone from episode file (#773)

* Format postcode into `pc7` format * Style code * Style code * Update documentation * Update comment in R/process_extract_ae.R * Implement catch-all for PC7 format --------- Co-authored-by: Jennit07 <[email protected]> Co-authored-by: James McMahon <[email protected]> Co-authored-by: Moohan <[email protected]>
Public-Health-Scotland · Aug 2, 2023 · 42e461f · 42e461f
1 parent 9644e0e
commit 42e461f
Show file tree

Hide file tree

Showing 7 changed files with 15 additions and 10 deletions.
diff --git a/R/create_individual_file.R b/R/create_individual_file.R
@@ -846,7 +846,8 @@ join_slf_lookup_vars <- function(individual_file,
 #' @param year financial year.
 #' @param sc_client SC client lookup
 #' @param sc_demographics SC Demographic lookup
-join_sc_client <- function(individual_file,
+join_sc_client <- function(
+    individual_file,
     year,
     sc_client = read_file(get_source_extract_path(year, "Client")),
     sc_demographics = read_file(get_sc_demog_lookup_path(),

diff --git a/R/process_extract_ae.R b/R/process_extract_ae.R
@@ -35,6 +35,10 @@ process_extract_ae <- function(data, year, write_to_disk = TRUE) {
       .data$postcode_chi,
       .data$postcode_epi
     )) %>%
+    # A&E data has postcode in PC8 format but we need it in PC7 format
+    dplyr::mutate(
+      postcode = phsmethods::format_postcode(.data$postcode, "pc7")
+    ) %>%
     ## recode cypher HB codes ##
     dplyr::mutate(
       dplyr::across(c("hbtreatcode", "hbrescode"), ~ dplyr::case_when(

diff --git a/R/process_lookup_gpprac.R b/R/process_lookup_gpprac.R
@@ -12,7 +12,8 @@
 #' @return the final data as a [tibble][tibble::tibble-package].
 #' @export
 #' @family process extracts
-process_lookup_gpprac <- function(open_data = get_gpprac_opendata(),
+process_lookup_gpprac <- function(
+    open_data = get_gpprac_opendata(),
     gpprac_ref_path = get_gpprac_ref_path(),
     spd_path = get_spd_path(),
     write_to_disk = TRUE) {

diff --git a/R/read_lookup_sc_client.R b/R/read_lookup_sc_client.R
@@ -9,9 +9,8 @@
 #' @return the final data as a [tibble][tibble::tibble-package].
 #' @export
 #' @family process extracts
-read_lookup_sc_client <- function(
-        fyyear,
-        sc_dvprod_connection = phs_db_connection(dsn = "DVPROD")) {
+read_lookup_sc_client <- function(fyyear,
+                                  sc_dvprod_connection = phs_db_connection(dsn = "DVPROD")) {
   check_year_format(fyyear)
   year <- convert_fyyear_to_year(fyyear)
 

diff --git a/R/read_lookup_sc_demographics.R b/R/read_lookup_sc_demographics.R
@@ -5,8 +5,7 @@
 #' @return a [tibble][tibble::tibble-package]
 #' @export
 #'
-read_lookup_sc_demographics <- function(
-        sc_connection = phs_db_connection(dsn = "DVPROD")) {
+read_lookup_sc_demographics <- function(sc_connection = phs_db_connection(dsn = "DVPROD")) {
   sc_demog <- dplyr::tbl(
     sc_connection,
     dbplyr::in_schema("social_care_2", "demographic_snapshot")

diff --git a/R/read_sc_all_alarms_telecare.R b/R/read_sc_all_alarms_telecare.R
@@ -6,8 +6,7 @@
 #'
 #' @export
 #'
-read_sc_all_alarms_telecare <- function(
-        sc_dvprod_connection = phs_db_connection(dsn = "DVPROD")) {
+read_sc_all_alarms_telecare <- function(sc_dvprod_connection = phs_db_connection(dsn = "DVPROD")) {
   # Read in data---------------------------------------
 
   ## read in data - social care 2 demographic

diff --git a/R/run_episode_file.R b/R/run_episode_file.R
@@ -93,7 +93,9 @@ run_episode_file <- function(
         NA_character_,
         .data$chi
       ),
-      gpprac = convert_eng_gpprac_to_dummy(.data[["gpprac"]])
+      gpprac = convert_eng_gpprac_to_dummy(.data[["gpprac"]]),
+      # PC8 format may still be used. Ensure here that all datasets are in PC7 format.
+      postcode = phsmethods::format_postcode(.data$postcode, "pc7")
     ) %>%
     correct_cij_vars() %>%
     fill_missing_cij_markers() %>%