Data update 18 10 24 (#32)

* Fix: Relabelling stat neigh multi chart input

* Chore: Updating paths in BDS wide to long, pointing at new BDS and in-proj data dict

* Feat: New data dict and BDS long

* Chore: minor updates to checking new data quality in global

* Feat: Removing old data dict and updating this in data log

* Tests: Updating bar chart title and screenshot for LA UI tests for new KS1 data

02_dev/bds_wide_to_long.qmd

@@ -25,8 +25,8 @@ source(here::here("R/fn_load_data.R"))
 ```{r pull-latest-bds-data}
 # Load raw BDS wide from shared folder
 bds_wide_raw_sf <- readxl::read_xlsx(
-  path = paste0(shared_folder, "/../Project Documentation/BDS - 2024 (JAKE).xlsx"),
-  sheet = "BDS",
+  path = paste0(shared_folder, "/../Information for App Development/BDS - 2024 (JAKE).xlsx"),
+  sheet = "BDS for new LAIT",
   col_names = TRUE,
   skip = 1,
   # Replace multi-space with single-space
@@ -136,7 +136,7 @@ bds_long_la <- bds_long_clean |>
 # only public-safe/in-use measures)
 # NOTE: Children_away changed to Children_Away to match BDS
 data_dict <- readxl::read_xlsx(
-  path = paste0(shared_folder, "/LAIT Data Dictionary (To QA!).xlsx"),
+  path = paste0("01_data/02_prod/LAIT Data Dictionary.xlsx"),
   sheet = "Data_prod"
 ) |>
   dplyr::mutate(Measure_short = trimws(Measure_short)) |>

R/lait_modules/mod_stat_n_charts.R

@@ -393,7 +393,7 @@ StatN_Chart_InputUI <- function(id) {
   tagList(
     shiny::selectizeInput(
       inputId = ns("chart_line_input"),
-      label = "Select region to compare (max 3)",
+      label = "Select statistical neighbour to compare (max 3)",
       choices = NULL,
       multiple = TRUE,
       options = list(
@@ -404,7 +404,7 @@ StatN_Chart_InputUI <- function(id) {
     ),
     shiny::selectizeInput(
       inputId = ns("chart_bar_input"),
-      label = "Select region to compare (max 3)",
+      label = "Select statistical neighbour to compare (max 3)",
       choices = NULL,
       multiple = TRUE,
       options = list(

datafiles_log.csv

@@ -4,4 +4,3 @@ filename,status
 01_data/02_prod/LA code list.xlsx,published
 01_data/02_prod/SN_April 2021.xlsx,published
 01_data/02_prod/LAIT Data Dictionary.xlsx,published
-01_data/02_prod/LAIT Data Dictionary_old_11092024.xlsx,published

global.R

@@ -202,7 +202,6 @@ testthat::test_that(
   {
     testthat::expect_equal(
       bds_clean |>
-        dplyr::filter(`Short Desc` %notin% metrics_discontinued) |>
         nrow(),
       nrow(bds_metrics) - (nrow(bds_metrics_dupes) / 2)
     )
@@ -211,13 +210,25 @@ testthat::test_that(
 # Using waldo to do same as test
 waldo::compare(
   x = bds_clean |>
-    dplyr::filter(`Short Desc` %notin% metrics_discontinued) |>
     nrow() |>
     as.numeric(),
   y = (nrow(bds_metrics) - (nrow(bds_metrics_dupes) / 2)) |>
     as.numeric()
 )
 
+# Measures that have not been joined by BDS clean
+bds_metrics |>
+  dplyr::filter(is.na(`LA and Regions`)) |>
+  pull_uniques("Measure_short")
+
+# Measures in BDS metrics but not in BDS clean
+setdiff(
+  bds_metrics |> pull_uniques("Measure_short"),
+  bds_clean |> pull_uniques("Short Desc")
+)
+
+
+
 # PROOF 2: The unique values of Measure Short + Topic are the same
 testthat::test_that(
   "Unique vals of measure_short + topic are the same in BDS & Metrics",

tests/testthat/test-UI-mod_la_lvl_table.R

@@ -203,7 +203,7 @@ test_that("Check LA charts behave as expected", {
   # Check title
   testthat::expect_true(
     grepl(
-      "Pupils achieving Key Stage 1 Reading Expected Standard (%)",
+      "Pupils achieving expected level in Phonics decoding - all pupils (%)",
       cleaned_barplot_str,
       fixed = TRUE
     )