Merge branch 'master' into rename_smrtype

00_Sort_BI_Extracts.R

@@ -0,0 +1,50 @@
+# Define the source directory and financial year pattern
+compress_files <- FALSE
+source_dir <- "/conf/sourcedev/Source_Linkage_File_Updates/Extracts Temp"
+pattern <- "-20(\\d{4})\\.csv"
+
+
+# List all the CSV files in the source directory
+cat(stringr::str_glue("Looking in '{source_dir}' for csv files."))
+csv_files <- list.files(source_dir, pattern = ".csv", full.names = TRUE)
+print(stringr::str_glue("Found {length(csv_files)} csv files to process."))
+
+# Create a function to extract the financial year from a filename
+extract_financial_year <- function(filename) {
+  match <- regexpr(pattern, basename(filename))
+  if (match[[1]][1] > 0) {
+    financial_year <- substr(basename(filename), match[[1]][1] + 3, match[[1]][1] + 6)
+    return(financial_year)
+  } else {
+    return(NULL)
+  }
+}
+
+# Create directories for each financial year and move files
+for (csv_file in csv_files) {
+  financial_year <- extract_financial_year(csv_file)
+  # check if year directory exists
+  if (!is.null(financial_year)) {
+    financial_year_dir <- file.path("/conf/sourcedev/Source_Linkage_File_Updates", financial_year, "Extracts")
+    # if not, create the year directory
+    if (!dir.exists(financial_year_dir)) {
+      dir.create(financial_year_dir)
+    }
+
+    # compress file
+    if (compress_files) {
+      cat("Compressing:", basename(csv_file), "\n")
+      system2(
+        command = "gzip",
+        args = shQuote(csv_file)
+      )
+      csv_file <- paste0(csv_file, ".gz")
+    }
+
+    # move file
+    new_file_path <- file.path(financial_year_dir, basename(csv_file))
+    file.copy(csv_file, new_file_path)
+    file.remove(csv_file)
+    cat("Moved:", csv_file, "to", new_file_path, "\n")
+  }
+}

NAMESPACE

@@ -14,7 +14,7 @@ export(convert_fyyear_to_year)
 export(convert_hb_to_hbnames)
 export(convert_hscp_to_hscpnames)
 export(convert_numeric_to_date)
-export(convert_sending_location_to_lca)
+export(convert_sc_sending_location_to_lca)
 export(convert_year_to_fyyear)
 export(create_episode_file)
 export(create_homelessness_lookup)
@@ -47,6 +47,7 @@ export(get_homelessness_completeness_path)
 export(get_it_deaths_path)
 export(get_it_ltc_path)
 export(get_it_prescribing_path)
+export(get_la_code_opendata_lookup)
 export(get_locality_path)
 export(get_lookups_dir)
 export(get_ltcs_path)
@@ -66,7 +67,9 @@ export(get_slf_ch_name_lookup_path)
 export(get_slf_chi_deaths_path)
 export(get_slf_deaths_lookup_path)
 export(get_slf_dir)
+export(get_slf_episode_path)
 export(get_slf_gpprac_path)
+export(get_slf_individual_path)
 export(get_slf_postcode_path)
 export(get_source_extract_path)
 export(get_sparra_path)
@@ -75,7 +78,6 @@ export(get_year_dir)
 export(gzip_files)
 export(is_date_in_fyyear)
 export(is_missing)
-export(la_code_lookup)
 export(last_date_month)
 export(latest_cost_year)
 export(latest_update)
@@ -172,17 +174,6 @@ export(write_file)
 importFrom(data.table,.N)
 importFrom(data.table,.SD)
 importFrom(magrittr,"%>%")
-importFrom(readr,col_character)
-importFrom(readr,col_date)
-importFrom(readr,col_datetime)
-importFrom(readr,col_double)
-importFrom(readr,col_factor)
-importFrom(readr,col_integer)
-importFrom(readr,col_logical)
-importFrom(readr,col_number)
-importFrom(readr,col_time)
-importFrom(readr,cols)
-importFrom(readr,cols_only)
 importFrom(rlang,":=")
 importFrom(rlang,.data)
 importFrom(tibble,tibble)

R/add_nsu_cohort.R

@@ -7,7 +7,7 @@
 #' @return A data frame containing the Non-Service Users as additional rows
 #' @export
 #'
-#' @family episode file
+#' @family episode_file
 #' @seealso [get_nsu_path()]
 add_nsu_cohort <- function(
     data,

R/add_ppa_flag.R

@@ -6,7 +6,7 @@
 #' @param data A data frame
 #'
 #' @return A data frame to use as a lookup of PPAs
-#' @family episode file
+#' @family episode_file
 add_ppa_flag <- function(data) {
   check_variables_exist(
     data,

R/convert_ca_to_lca.R

@@ -12,7 +12,7 @@
 #' convert_ca_to_lca(ca)
 #'
 #' @family code functions
-#' @seealso convert_sending_location_to_lca
+#' @seealso convert_sc_sending_location_to_lca
 convert_ca_to_lca <- function(ca_var) {
   lca <- dplyr::case_match(
     ca_var,

R/convert_sending_location_to_lca.R → R/convert_sc_sending_location_to_lca.R

@@ -10,12 +10,12 @@
 #'
 #' @examples
 #' sending_location <- c(100, 120)
-#' convert_sending_location_to_lca(sending_location)
+#' convert_sc_sending_location_to_lca(sending_location)
 #'
 #' @family code functions
 #'
 #' @seealso convert_ca_to_lca
-convert_sending_location_to_lca <- function(sending_location) {
+convert_sc_sending_location_to_lca <- function(sending_location) {
   lca <- dplyr::case_match(
     sending_location,
     100L ~ "01", # Aberdeen City

R/cost_uplift.R

@@ -3,6 +3,7 @@
 #' @param data episode data
 #'
 #' @return episode data with uplifted costs
+#' @family episode_file
 apply_cost_uplift <- function(data) {
   data <- data %>%
     # attach a uplift scale as the last column
@@ -34,6 +35,7 @@ apply_cost_uplift <- function(data) {
 #' @param data episode data
 #'
 #' @return episode data with a uplift scale
+#' @family episode_file
 lookup_uplift <- function(data) {
   # We have set uplifts to use for 2020/21, 2021/22 and 2022/23,
   # provided by Paul Leak.

R/create_episode_file.R

@@ -171,14 +171,7 @@ create_episode_file <- function(
   }
 
   if (write_to_disk) {
-    # TODO make the slf_path a function
-    slf_episode_path <- get_file_path(
-      get_year_dir(year),
-      stringr::str_glue(
-        "source-episode-file-{year}.parquet"
-      ),
-      check_mode = "write"
-    )
+    slf_episode_path <- get_slf_episode_path(year, check_mode = "write")
 
     write_file(episode_file, slf_episode_path)
   }