forgot to save last R file

r_app/2_CI_data_prep.R

@@ -33,6 +33,7 @@ laravel_storage_dir <- here("laravel_app","storage","app")
 
 #preparing directories
 project = "chemba"
+new_project_question = TRUE
 planet_tif_folder <- here(laravel_storage_dir, project, "merged_tif")
 merged_final <- here(laravel_storage_dir, project,"merged_final_tif")
 
@@ -52,6 +53,7 @@ dir.create(here(cumulative_CI_vals_dir))
 dir.create(here(weekly_CI_mosaic))
 dir.create(here(daily_vrt))
 dir.create(merged_final)
+dir.create(harvest_dir)
 
 
 
@@ -257,27 +259,14 @@ extract_rasters_daily <- function(file, field_geojson, quadrants = TRUE, save_di
 # pivot_sf_q <- st_read(here("..", "Data", "pivot_20210625.geojson")) %>% dplyr::select(pivot, pivot_quadrant) %>% vect()
 pivot_sf <- st_read(here(data_dir, "pivot_20210625.geojson")) %>% dplyr::select(pivot, pivot_quadrant)   %>% group_by(pivot) %>% summarise() %>% vect()
 message("pivot loaded")
-if (!file.exists(here(cumulative_CI_vals_dir,"combined_CI_data.rds"))) {
 
-  print("combined_CI_data.rds does not exist. Running this part of the script...")
-} 
 raster_files_NEW <- list.files(merged_final,full.names = T, pattern = ".tif")
-filtered_files  <- map(dates$days_filter, ~ raster_files_NEW[grepl(pattern = .x, x = raster_files_NEW)]) %>%
+
-  compact() %>%
-  flatten_chr() 
-walk(filtered_files, extract_rasters_daily, field_geojson= pivot_sf_q, quadrants = TRUE, daily_CI_vals_dir)
-message("after walk")
 pivots_dates0 <- readRDS(here(harvest_dir, "harvest_data_new")) %>% filter(
   pivot %in% c("1.1", "1.2", "1.3", "1.4", "1.6", "1.7", "1.8", "1.9", "1.10", "1.11", "1.12", "1.13",
                "1.14" , "1.16" , "1.17" , "1.18" ,"2.1", "2.2", "2.3" , "2.4", "2.5", "3.1", "3.2", "3.3",
                "4.1", "4.2", "4.3", "4.4", "4.5", "4.6", "5.1" ,"5.2", "5.3", "5.4", "6.1", "6.2", "DL1.1", "DL1.3")
 )
-
-# pivots_dates_long <- pivots_dates0 %>%
-#   select(c("pivot_quadrant", "season_start_2021", "season_end_2021", "season_start_2022", "season_end_2022", "season_start_2023", "season_end_2023")) %>%
-#   pivot_longer(cols = c("season_start_2021", "season_end_2021", "season_start_2022", "season_end_2022", "season_start_2023", "season_end_2023")) %>%
-#   separate(pivot_quadrant, into = c("name", "Year"), sep = "\\.")
-
 harvesting_data <- pivots_dates0 %>%
   select(c("pivot_quadrant", "season_start_2021", "season_end_2021", "season_start_2022", "season_end_2022", "season_start_2023", "season_end_2023", "season_start_2024", "season_end_2024")) %>%
   pivot_longer(cols = starts_with("season"), names_to = "Year", values_to = "value") %>%
@@ -285,32 +274,77 @@ harvesting_data <- pivots_dates0 %>%
   mutate(name = str_to_title(name)) %>%
   pivot_wider(names_from = name, values_from = value) %>%
   rename(Field = pivot_quadrant)
-# extracted_values <-  list.files("C:\\Users\\timon\\Resilience BV\\4002 CMD App - General\\4002 CMD Team\\4002 TechnicalData\\04 WP2 technical\\DetectingSpotsR\\EcoFarm\\planet\\extracted",
+
-#                                      pattern ="_quadrant", full.names = TRUE)
+pivots_data_present <- unique(pivots_dates0$pivot_quadrant)
-extracted_values <-  list.files(here(daily_CI_vals_dir), full.names = TRUE)
+quadrant_list <- pivots_data_present
-#get CI values for this week only
+
+#If run for the firsttime, it will extract all data since the start and put into a table.rds. otherwise it will only add on to the existing table.
+if (new_project_question == TRUE) {
+  
+  print("combined_CI_data.rds does not exist. Preparing combined_CI_data.rds file for all available images.")
+  
+  walk(raster_files_NEW, extract_rasters_daily, field_geojson= pivot_sf_q, quadrants = TRUE, daily_CI_vals_dir)
+  
+  extracted_values <-  list.files(here(daily_CI_vals_dir), full.names = TRUE)
+  
+  pivot_stats <- extracted_values %>%
+    map(readRDS) %>% list_rbind() %>%
+    group_by(pivot_quadrant) %>%
+    summarise(across(everything(), ~ first(na.omit(.))))
+  
+  saveRDS(pivot_stats, here(cumulative_CI_vals_dir,"combined_CI_data.rds")) #used to save the rest of the data into one file
+  
+  pivot_stats2 <- pivot_stats
+  
+  print("All CI values extracted from allhistoric images")
+  
+} else {
+  print("combined_CI_data.rds exists, adding the latest image data to the table.")
+  
+  filtered_files  <- map(dates$days_filter, ~ raster_files_NEW[grepl(pattern = .x, x = raster_files_NEW)]) %>%
+    compact() %>% 
+    flatten_chr() 
+  
+  walk(filtered_files, extract_rasters_daily, field_geojson= pivot_sf_q, quadrants = TRUE, daily_CI_vals_dir)
+
+  extracted_values <-  list.files(daily_CI_vals_dir, full.names = TRUE)
+  
+  extracted_values <- map(dates$days_filter, ~ extracted_values[grepl(pattern = .x, x = extracted_values)]) %>%
+    compact() %>%
+    flatten_chr()
+  
+  pivot_stats <- extracted_values %>%
+    map(readRDS) %>% list_rbind() %>%
+    group_by(pivot_quadrant) %>%
+    summarise(across(everything(), ~ first(na.omit(.))))
+  
+  combined_CI_data <- readRDS(here(cumulative_CI_vals_dir,"combined_CI_data.rds")) %>% drop_na(pivot_quadrant)
+  pivot_stats2 <- bind_rows(pivot_stats, combined_CI_data)
+  print("All CI values extracted from latest 7 images.")
+  
+}
+
+
+
+
 #extracted_values <- map(dates$days_filter, ~ extracted_values[grepl(pattern = .x, x = extracted_values)]) %>%
 #  compact() %>%
 #  flatten_chr()
 
 #combine them into one df
-pivot_stats <- extracted_values %>%
+
-  map(readRDS) %>% list_rbind() %>%
-  group_by(pivot_quadrant) %>%
-  summarise(across(everything(), ~ first(na.omit(.))))
 
 
  #saveRDS(pivot_stats, here(cumulative_CI_vals_dir,"combined_CI_data.rds")) #used to save the rest of the data into one file
 
 
 #load historic CI data and update it with last week of CI data
-combined_CI_data <- readRDS(here(cumulative_CI_vals_dir,"combined_CI_data.rds")) %>% drop_na(pivot_quadrant)
+# combined_CI_data <- readRDS(here(cumulative_CI_vals_dir,"combined_CI_data.rds")) %>% drop_na(pivot_quadrant)
-pivot_stats2 <- bind_rows(pivot_stats, combined_CI_data)
+# pivot_stats2 <- bind_rows(pivot_stats, combined_CI_data)
 # pivot_stats2 <- purrr::map(list.files(here(daily_CI_vals_dir), full.names = TRUE, pattern = "quadrant"), readRDS) %>% list_rbind() %>% group_by(pivot_quadrant) %>%
 #   summarise(across(everything(), ~ first(na.omit(.))))
 
-pivots_data_present <- unique(pivots_dates0$pivot_quadrant)
+
-quadrant_list <- pivots_data_present
 
 # gather data into long format for easier calculation and visualisation
 pivot_stats_long <- pivot_stats2 %>%
@@ -321,7 +355,8 @@ pivot_stats_long <- pivot_stats2 %>%
   drop_na(c("value","Date")) %>%
   mutate(value = as.numeric(value))%>%
   filter_all(all_vars(!is.infinite(.)))%>%
-  rename(Field = pivot_quadrant)
+  rename(Field = pivot_quadrant) %>%
+  unique()
 
 # #2021
 pivots_dates_Data_2021 <- pivots_dates0 %>% filter(!is.na(season_start_2021))