Merge branch 'feature/error_handling' of https://github.com/dfe-analy…

…tical-services/CSC_outcomes_and_enablers into feature/error_handling
dfe-analytical-services · Mar 19, 2024 · 7c64edf · 7c64edf
2 parents 5b3b8f3 + 04e04eb
commit 7c64edf
Show file tree

Hide file tree

Showing 7 changed files with 425 additions and 96 deletions.
diff --git a/R/enabler2_page.R b/R/enabler2_page.R
@@ -77,22 +77,22 @@ enabler2_tab <- function() {
           condition = "(input.geographic_breakdown_e2 == 'North Northamptonshire / West Northamptonshire')",
           p("North Northamptonshire and West Northamptonshire submitted a joint workforce return in 2021 and onwards, and their data is reported together")
         ),
-        conditionalPanel(
-          condition = "(input.geographic_breakdown_e2 == 'Cumbria')",
-          p("To view 2023 and onwards data select ", strong("Cumberland"), "or", strong("Westmorland and Furness"), ". Cumbria local authority was replaced with two new unitary authorities, Cumberland and Westmorland and Furness, in April 2023.")
-        ),
-        conditionalPanel(
-          condition = "(input.geographic_breakdown_e2 == 'Northamptonshire')",
-          p("To view 2021 and onwards data select ", strong("North Northamptonshire / West Northamptonshire"), ". Northamptonshire local authority was replaced with two new unitary authorities, North Northamptonshire and West Northamptonshire, in April 2021.")
-        ),
-        conditionalPanel(
-          condition = "(input.geographic_breakdown_e2 == 'Poole')",
-          p("To view 2019 and onwards data select ", strong("Bournemouth, Christchurch and Poole"), ". Bournemouth, Christchurch and Poole local authority was formed in April 2019.")
-        ),
-        conditionalPanel(
-          condition = "(input.geographic_breakdown_e2 == 'Bournemouth')",
-          p("To view 2019 and onwards data select ", strong("Bournemouth, Christchurch and Poole"), ". Bournemouth, Christchurch and Poole local authority was formed in April 2019.")
-        ),
+        # conditionalPanel(
+        #   condition = "(input.geographic_breakdown_e2 == 'Cumbria')",
+        #   p("To view 2023 and onwards data select ", strong("Cumberland"), "or", strong("Westmorland and Furness"), ". Cumbria local authority was replaced with two new unitary authorities, Cumberland and Westmorland and Furness, in April 2023.")
+        # ),
+        # conditionalPanel(
+        #   condition = "(input.geographic_breakdown_e2 == 'Northamptonshire')",
+        #   p("To view 2021 and onwards data select ", strong("North Northamptonshire / West Northamptonshire"), ". Northamptonshire local authority was replaced with two new unitary authorities, North Northamptonshire and West Northamptonshire, in April 2021.")
+        # ),
+        # conditionalPanel(
+        #   condition = "(input.geographic_breakdown_e2 == 'Poole')",
+        #   p("To view 2019 and onwards data select ", strong("Bournemouth, Christchurch and Poole"), ". Bournemouth, Christchurch and Poole local authority was formed in April 2019.")
+        # ),
+        # conditionalPanel(
+        #   condition = "(input.geographic_breakdown_e2 == 'Bournemouth')",
+        #   p("To view 2019 and onwards data select ", strong("Bournemouth, Christchurch and Poole"), ". Bournemouth, Christchurch and Poole local authority was formed in April 2019.")
+        # ),
         # p(htmlOutput("enabler2_choice_text2")),
         br(),
         div(

diff --git a/R/outcome1_page.R b/R/outcome1_page.R
@@ -70,18 +70,18 @@ outcome1_tab <- function() {
       gov_row(
         br(),
         p(htmlOutput("outcome1_choice_text1"), htmlOutput("outcome1_choice_text2")),
-        conditionalPanel(
-          condition = "(input.geographic_breakdown_o1 == 'Northamptonshire')",
-          p("To view 2021 and onwards data select ", strong("North Northamptonshire"), "or", strong("West Northamptonshire"), ". Northamptonshire local authority was replaced with two new unitary authorities, North Northamptonshire and West Northamptonshire, in April 2021.")
-        ),
-        conditionalPanel(
-          condition = "(input.geographic_breakdown_o1 == 'Poole')",
-          p("To view 2020 and onwards data select ", strong("Bournemouth, Christchurch and Poole"), ". Bournemouth, Christchurch and Poole local authority was formed in April 2019.")
-        ),
-        conditionalPanel(
-          condition = "(input.geographic_breakdown_o1 == 'Bournemouth')",
-          p("To view 2020 and onwards data select ", strong("Bournemouth, Christchurch and Poole"), ". Bournemouth, Christchurch and Poole local authority was formed in April 2019.")
-        ),
+        # conditionalPanel(
+        #   condition = "(input.geographic_breakdown_o1 == 'Northamptonshire')",
+        #   p("To view 2021 and onwards data select ", strong("North Northamptonshire"), "or", strong("West Northamptonshire"), ". Northamptonshire local authority was replaced with two new unitary authorities, North Northamptonshire and West Northamptonshire, in April 2021.")
+        # ),
+        # conditionalPanel(
+        #   condition = "(input.geographic_breakdown_o1 == 'Poole')",
+        #   p("To view 2020 and onwards data select ", strong("Bournemouth, Christchurch and Poole"), ". Bournemouth, Christchurch and Poole local authority was formed in April 2019.")
+        # ),
+        # conditionalPanel(
+        #   condition = "(input.geographic_breakdown_o1 == 'Bournemouth')",
+        #   p("To view 2020 and onwards data select ", strong("Bournemouth, Christchurch and Poole"), ". Bournemouth, Christchurch and Poole local authority was formed in April 2019.")
+        # ),
       ),
       gov_row(
         br(),

diff --git a/R/read_data.R b/R/read_data.R
@@ -26,32 +26,46 @@ convert_perc_cols_to_numeric <- function(x) {
   return(x)
 }
 
-# sample data functions we dont need this~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-read_revenue_data <- function(file = "data/la_maintained_schools_revenue_reserve_final.csv") {
-  # This reads in an example file. For the purposes of this demo, we're using the
-  # latest LA expenditure data downloaded from the EES release.
-  dfRevenue <- read.csv(file)
-  # The time period column name has some non-ascii characters so we're just going to rename it here.
-  colnames(dfRevenue)[1] <- "time_period"
-  dfRevenue <- dfRevenue %>% mutate(
-    year = as.numeric(paste0("20", substr(format(time_period), 5, 6))),
-    area_name = case_when(
-      geographic_level == "National" ~ country_name,
-      geographic_level == "Regional" ~ region_name,
-      TRUE ~ la_name
-    )
-  )
-  return(dfRevenue)
+remove_old_la_data <- function(data) {
+  ons_la_data <- read.csv("data/Lower_Tier_Local_Authority_to_Upper_Tier_Local_Authority_(April_2023)_Lookup_in_England_and_Wales.csv")
+  ons_la_data <- ons_la_data %>%
+    select(UTLA23CD, UTLA23NM) %>%
+    filter(!str_starts(UTLA23CD, "W")) %>%
+    unique()
+
+  removed_old_las <- data %>% filter(new_la_code == "" | new_la_code %in% (ons_la_data$UTLA23CD))
+
+  return(removed_old_las)
 }
 
+
+# # sample data functions we dont need this~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+# read_revenue_data <- function(file = "data/la_maintained_schools_revenue_reserve_final.csv") {
+#   # This reads in an example file. For the purposes of this demo, we're using the
+#   # latest LA expenditure data downloaded from the EES release.
+#   dfRevenue <- read.csv(file)
+#   # The time period column name has some non-ascii characters so we're just going to rename it here.
+#   colnames(dfRevenue)[1] <- "time_period"
+#   dfRevenue <- dfRevenue %>% mutate(
+#     year = as.numeric(paste0("20", substr(format(time_period), 5, 6))),
+#     area_name = case_when(
+#       geographic_level == "National" ~ country_name,
+#       geographic_level == "Regional" ~ region_name,
+#       TRUE ~ la_name
+#     )
+#   )
+#   return(dfRevenue)
+# }
+
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
 # Test not important
-read_definitions <- function(file = "data/definitions.csv") {
-  definitions <- read.csv(file)
-  # colnames(definitions) <- c("Outcome/Enabler", "Domain", "Indicator", "Rationale/Description")
-  #  definitions <- definitions[,1:4]
-  return(definitions)
-}
+# read_definitions <- function(file = "data/definitions.csv") {
+#   definitions <- read.csv(file)
+#   # colnames(definitions) <- c("Outcome/Enabler", "Domain", "Indicator", "Rationale/Description")
+#   #  definitions <- definitions[,1:4]
+#   return(definitions)
+# }
 
 
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -621,39 +635,35 @@ read_cin_referral_data <- function(file = "data/c1_children_in_need_referrals_an
 # }
 
 read_outcome2 <- function(file = "data/la_children_who_ceased_during_the_year.csv") {
-  ceased_cla_data <- read.csv(file)
-  old_dorset <- ceased_cla_data %>% filter(time_period <= 2019, new_la_code == "E10000009")
-  new_dorset <- ceased_cla_data %>% filter(time_period > 2019, new_la_code == "E06000059")
-  data_without_dorset <- ceased_cla_data %>% filter(la_name != "Dorset")
-
-  dorset_data <- bind_rows(new_dorset, old_dorset)
-  final_filtered_data <- bind_rows(data_without_dorset, dorset_data)
+  read_data <- read.csv(file)
+  # Call remove old la data function to remove the old
+  # final_filtered_data <- remove_old_la_data(read_data)
+  las_to_remove <- c("Poole", "Bournemouth", "Northamptonshire")
 
+  final_filtered_data <- read_data %>% filter(new_la_code != "E10000009", !la_name %in% las_to_remove)
   ceased_cla_data <- final_filtered_data %>%
     mutate(geo_breakdown = case_when(
       geographic_level == "National" ~ "National", # NA_character_,
       geographic_level == "Regional" ~ region_name,
       geographic_level == "Local authority" ~ la_name
     )) %>%
-    mutate(number = case_when(
+    mutate(number_num = case_when(
       number == "z" ~ NA,
       number == "x" ~ NA,
       number == "c" ~ NA,
       TRUE ~ as.numeric(number)
     )) %>%
-    filter("new_la_code" != "E10000009") %>%
-    select("time_period", "geographic_level", "geo_breakdown", "cla_group", "characteristic", "number", "percentage")
+    select("time_period", "geographic_level", "geo_breakdown", "old_la_code", "new_la_code", "cla_group", "characteristic", "number", "number_num", "percentage")
 
   totals <- ceased_cla_data %>%
-    filter(characteristic == "Total" & cla_group == "Reason episode ceased") %>%
-    rename("Total" = "number") %>%
-    select(time_period, geographic_level, geo_breakdown, cla_group, Total)
+    filter(characteristic == "Total") %>%
+    rename("Total_num" = "number_num") %>%
+    mutate("Total" = number) %>%
+    select(time_period, geographic_level, geo_breakdown, cla_group, Total_num, Total)
 
+  joined <- left_join(ceased_cla_data, totals, by = c("time_period", "geographic_level", "geo_breakdown", "cla_group"))
+  joined$perc <- round((joined$number_num / joined$Total_num) * 100, digits = 1)
 
-  test <- ceased_cla_data %>% filter(cla_group == "Reason episode ceased" & characteristic != "Total")
-
-  joined <- left_join(test, totals, by = c("time_period", "geographic_level", "geo_breakdown", "cla_group"))
-  joined$perc <- round((joined$number / joined$Total) * 100, digits = 1)
   joined <- joined %>%
     mutate(perc = case_when(
       percentage == "z" ~ "z",
@@ -669,6 +679,5 @@ read_outcome2 <- function(file = "data/la_children_who_ceased_during_the_year.cs
       percentage == "x" ~ NA,
       TRUE ~ as.numeric(perc)
     ))
-
   return(joined)
 }