786 duplicates of chi in individual files

R/create_individual_file.R

@@ -61,7 +61,7 @@ create_individual_file <- function(
     remove_blank_chi() %>%
     add_cij_columns() %>%
     add_all_columns() %>%
-    aggregate_ch_episodes_zihao() %>%
+    aggregate_ch_episodes() %>%
     clean_up_ch(year) %>%
     recode_gender() %>%
     aggregate_by_chi() %>%
@@ -741,13 +741,25 @@ join_sc_client <- function(
       sc_demographics %>%
         dplyr::select("sending_location", "social_care_id", "chi"),
       by = c("sending_location", "social_care_id")
-    )
+    ) %>%
+    dplyr::mutate(count_not_known = rowSums(dplyr::select(., all_of(
+      c(
+        "sc_living_alone",
+        "sc_support_from_unpaid_carer",
+        "sc_social_worker",
+        "sc_meals",
+        "sc_day_care"
+      )
+    )) == "Not Known")) %>%
+    dplyr::arrange(chi, count_not_known) %>%
+    dplyr::distinct(chi, .keep_all = TRUE)
 
   # Match on client variables by chi
   individual_file <- individual_file %>%
     dplyr::left_join(
       join_client_demog,
-      by = "chi"
+      by = "chi",
+      relationship = "one-to-one"
     ) %>%
     dplyr::select(!c("sending_location", "social_care_id", "sc_latest_submission"))
 

R/process_tests_individual_file.R

@@ -64,9 +64,8 @@ produce_individual_file_tests <- function(data) {
     create_demog_test_flags() %>%
     create_hb_test_flags(.data$hbrescode) %>%
     create_hb_cost_test_flags(.data$hbrescode, .data$health_net_cost) %>%
-    create_hscp_test_flags(.data$hscp2018) %>%
     # keep variables for comparison
-    dplyr::select("valid_chi":dplyr::last_col()) %>%
+    dplyr::select(c("valid_chi":dplyr::last_col())) %>%
     # use function to sum new test flags
     calculate_measures(measure = "sum")
 
@@ -86,7 +85,9 @@ produce_individual_file_tests <- function(data) {
 
   min_max_measures <- data %>%
     calculate_measures(
-      vars = "health_net_cost",
+      vars = c(
+        "health_net_cost"
+      ),
       measure = "min-max"
     )
 
@@ -99,11 +100,18 @@ produce_individual_file_tests <- function(data) {
       measure = "sum"
     )
 
+  dup_chi <- data.frame(
+    measure = "duplicated chi number",
+    value = duplicated(data$chi) %>%
+      sum() %>% as.integer()
+  )
+
   join_output <- list(
     test_flags,
     all_measures,
     min_max_measures,
-    sum_measures
+    sum_measures,
+    dup_chi
   ) %>%
     purrr::reduce(dplyr::full_join, by = c("measure", "value"))