Major update of Care Home script

R/add_activity_after_death_flag.R

@@ -125,6 +125,7 @@
 #'
 #'
 # Read data------------------------------------------------
+
 process_combined_deaths_lookup <- function(update = latest_update(),
                                            write_to_disk = TRUE, ...) {
   dir_folder <- "/conf/hscdiip/SLF_Extracts/Deaths"
@@ -135,7 +136,7 @@
 
   # read all year specific deaths lookups and bind them together
   all_boxi_deaths <- lapply(file_names, arrow::read_parquet) %>%
     data.table::rbindlist() %>%
     # convert to chi for processing
     slfhelper::get_chi() %>%
     # Remove rows with missing or blank CHI number - could also use na.omit?

R/fill_ch_names.R

@@ -213,7 +213,7 @@ fill_ch_names <- function(ch_data,
       "match_mean2",
       # "open_interval",
       "ch_admission_date",
-      "qtr_start",
+      "period_start_date",
       "ch_date_registered",
       "latest_close_date",
       "ch_active",
@@ -305,7 +305,6 @@ fill_ch_names <- function(ch_data,
     "unique_identifier",
     "matching_quality_indicator",
     "sending_location",
-    "latest_sc_id",
     "chi",
     "ch_name",
     "ch_postcode",
@@ -320,9 +319,6 @@ fill_ch_names <- function(ch_data,
     "ch_admission_date",
     "ch_discharge_date",
     "age",
-    "record_date",
-    "qtr_start",
-    "latest_flag",
     "gender",
     "dob",
     "postcode",
@@ -763,7 +759,6 @@ fill_ch_names <- function(ch_data,
   ## produce output ----
   col_output <- c(
     "sending_location",
-    "latest_sc_id",
     "chi",
     "ch_name",
     "ch_postcode",
@@ -778,9 +773,6 @@ fill_ch_names <- function(ch_data,
     "ch_admission_date",
     "ch_discharge_date",
     "age",
-    "record_date",
-    "qtr_start",
-    "latest_flag",
     "gender",
     "dob",
     "postcode",

R/process_extract_care_home.R

@@ -39,11 +39,11 @@ process_extract_care_home <- function(
       is_date_in_fyyear(year, .data$record_keydate1, .data$record_keydate2)
     ) %>%
     # remove any episodes where the latest submission was before the current year
+    # this is what stops cases being in future files
     dplyr::filter(
       substr(.data$sc_latest_submission, 1L, 4L) >= convert_fyyear_to_year(year)
     )
 
-
   # Data Cleaning ---------------------------------------
   source_ch_clean <- ch_data %>%
     # create variables

R/process_lookup_sc_demographics.R

@@ -143,8 +143,8 @@ process_lookup_sc_demographics <- function(
     dplyr::ungroup()
 
   # check to make sure all cases of chi are still there
-  dplyr::n_distinct(sc_demog_lookup$chi) # 524810
-  dplyr::n_distinct(sc_demog_lookup$social_care_id) # 636404
+  dplyr::n_distinct(sc_demog_lookup$chi) # 525,834
+  dplyr::n_distinct(sc_demog_lookup$social_care_id) # 637,422
 
   sc_demog_lookup <- sc_demog_lookup %>%
     slfhelper::get_anon_chi()