From 6f7376c693b3e1aa80a3cc3c2cd6aacf00389192 Mon Sep 17 00:00:00 2001
From: dylanbenzi <dylanbenzi@gmail.com>
Date: Wed, 4 Jun 2025 14:58:37 -0400
Subject: [PATCH] update normalized cost data loading

---
 dashboard.Rmd | 88 +++++++++++++++++++++++++++++++++------------------
 1 file changed, 58 insertions(+), 30 deletions(-)

diff --git a/dashboard.Rmd b/dashboard.Rmd
index 1cdd173..c203cb7 100644
--- a/dashboard.Rmd
+++ b/dashboard.Rmd
@@ -11,6 +11,10 @@ output:
 ---
 
 ```{r setup, include=FALSE}
+# TODO:
+# - update normalization to new 2024 data
+# - 
+
 library(flexdashboard)
 library(shiny)
 library(leaflet)
@@ -169,35 +173,6 @@ storm_selection <- reactiveValues(
 
 ######
 
-###### SUPABASE PORT
-econ.normalized_landfalls <- dbGetQuery(con, "SELECT * FROM econ.normalized_landfalls")
-
-econ.storm_base_loss <- reactive({
-  req(storm_selection$is_selected)
-  
-  query <- paste0("
-    SELECT DISTINCT ON (storm_basin, storm_year, storm_name, lf_type, lf_id)
-      storm_basin,
-      storm_year,
-      storm_name,
-      lf_type,
-      lf_id,
-      base_loss_source,
-      base_loss
-    FROM econ.storm_base_loss
-    WHERE base_loss IS NOT NULL
-    ORDER BY
-      storm_basin, storm_year, storm_name, lf_type, lf_id,
-      CASE
-        WHEN base_loss_source LIKE '%ncei%' THEN 1
-        WHEN base_loss_source LIKE '%mwr%' THEN 2
-        ELSE 3
-      END
-  ")
-  
-  dbGetQuery(con, query)
-})
-
 # LAZY LOAD DB TABLES
 
 econ.normalized_landfalls <- tbl(con, I("econ.normalized_landfalls"))
@@ -219,6 +194,58 @@ metrics.geo_attributes <- tbl(con, I("metrics.geo_attributes"))
 #metrics.pop_and_housing <- tbl(con, I("metrics.pop_and_housing"))
 
 public.counties <- tbl(con, I("public.counties"))
+
+### COMMONLY USED DATA
+
+base_losses_by_lf <- econ.storm_base_loss %>% 
+  filter(!is.na(base_loss)) %>% 
+  mutate(
+    ncei_priority = case_when(
+      str_like(base_loss_source, "%ncei%") ~ 1,
+      str_like(base_loss_source, "%ncei%") ~ 2,
+      TRUE ~ 3
+    )
+  ) %>% 
+  group_by(storm_basin, storm_year, storm_name, lf_type, lf_id) %>% 
+  slice_min(ncei_priority, n = 1, with_ties = F) %>% 
+  ungroup() %>% 
+  collect()
+
+total_base_losses <- base_losses_by_lf %>% 
+  group_by(storm_basin, storm_year, storm_name) %>% 
+  summarize(
+    total_base_loss = sum(base_loss),
+    .groups = "drop"
+  ) %>% 
+  collect()
+
+normalized_losses_2024 <- econ.normalized_landfalls %>% 
+  filter(normalization_year == 2024) %>% 
+  left_join(econ.storm_base_loss %>% 
+              filter(!is.na(base_loss)) %>% 
+              mutate(
+                ncei_priority = case_when(
+                  str_like(base_loss_source, "%ncei%") ~ 1,
+                  str_like(base_loss_source, "%ncei%") ~ 2,
+                  TRUE ~ 3
+                )
+              ) %>% 
+              group_by(storm_basin, storm_year, storm_name, lf_type, lf_id) %>% 
+              slice_min(ncei_priority, n = 1, with_ties = F) %>% 
+              ungroup(),
+            by = c("storm_basin", "storm_year", "storm_name", "lf_type", "lf_id")) %>% 
+  mutate(
+    mmh_lf = (base_loss * gdp_deflator * rwhu * affected_housing),
+    mmp_lf = (base_loss * gdp_deflator * rwpc * affected_population)
+  ) %>% 
+  group_by(storm_basin, storm_year, storm_name) %>% 
+  summarize(
+    mmh = sum(mmh_lf, na.rm = T),
+    mmp = sum(mmp_lf, na.rm = T),
+    .groups = "drop"
+  ) %>% 
+  filter(!is.na(mmh) & !is.na(mmp)) %>% 
+  collect()
 ```
 
 ```{r}
@@ -424,7 +451,7 @@ observeEvent(input$selectStorm, {
 ```{r}
 output$allStorms <- renderDT({
   datatable(
-    normalized2024,
+    normalized_losses_2024 %>% select(Storm = storm_name, Year = storm_year, MMH24 = mmh, MMP24 = mmp),
     rownames = F,
     options = list(
       pageLength = 1000,
@@ -873,6 +900,7 @@ Top 50 Storms
 #DT with storm, hurdatid, base damage, mmh, mmp, maybe multipliers?, sparkline?
 
 
+
 ```
 
 About