worked on procssing, human nutrition sheet.

R_to_SQL_database/Cifos_Model_Data_EU.R

@@ -906,18 +906,21 @@ dat_map_processing = dat_proc_asf %>% dplyr::select(proc_out) %>%
 
 
 # Comparing different processing sheets  ----------------------------------
-dat_proc_rec = read_excel("D:/GAMS/EU_model_Feb2022/European_CiFoS_model_data.xlsx", sheet = "Processing_Fraction" )
+# dat_proc_rec = read_excel("D:/GAMS/EU_model_Feb2022/European_CiFoS_model_data.xlsx", sheet = "Processing_Fraction" )
 
-dat_proc_comp = Processing_sheet_final %>% left_join(dat_proc_rec %>% select(proc_out, Utilization), by="proc_out") %>% 
-  mutate(Utilization = case_when(proc_out == "barleyfor" ~ "FeedOnly",
-                                 proc_out == "wheatfor" ~ "FeedOnly", 
-                                 TRUE ~ Utilization)) %>% 
-  dplyr::select(-dietary_products) %>% clean_names()
-  
-write_csv(dat_proc_comp, "Input_data/processing_sheet_17_02_22.csv")
-  
+# dat_proc_comp = Processing_sheet_final %>% left_join(dat_proc_rec %>% select(proc_out, Utilization), by="proc_out") %>% 
+#   mutate(Utilization = case_when(proc_out == "barleyfor" ~ "FeedOnly",
+#                                  proc_out == "wheatfor" ~ "FeedOnly", 
+#                                  TRUE ~ Utilization)) %>% 
+#   dplyr::select(-dietary_products) %>% clean_names()
+#   
+# write_csv(dat_proc_comp, "Input_data/processing_sheet_17_02_22.csv")
   
 
+# Removing duplicates  22.2.22 ----------------------------------------------------
+dat_proc_dup = read_excel("D:/GAMS/EU_model_Feb2022/European_CiFoS_model_data.xlsx", sheet = "Processing_Fraction" )
+dat_proc_dup %>% distinct() %>% write_csv("Input_data/processing_sheet_no_dup.csv")
+
 # Human nutrition sheet ---------------------------------------------------
 #  Human nutrtion sheet
 dat_humnutr = read_excel("Input_data/Copy of European_CiFoS_model_data_ANITANov21.xlsx", sheet = "Human_Nutr")
@@ -1108,6 +1111,26 @@ hum_nutr_all_FG = hum_nutr_all %>% dplyr::select(-FoodGroup) %>%
 # check = full_join(hum_nutr_all, proc_new, by = c("product"="proc_out"))
 write_csv(hum_nutr_all_FG, "Input_data/hum_nutr_all.csv")
 
+
+# Comparing versions - Demi NAs filling --------------------------------------
+hum_food_22.2.22 = read_xlsx('Input_data/Human_Food_Demi_22.2.22.xlsx', sheet = "Sheet1")
+hum_food_latest = read_excel("D:/GAMS/EU_model_Feb2022/European_CiFoS_model_data.xlsx", sheet = "Human_Food_Nutr" )
+
+# Consistency checks - Are the same products in both of the sheets 
+# - Number of rows are identical 139
+
+# # both sheets have the same products. Sheet can be directly replaced by demis sheet!
+hum_food_22.2.22$Product[!hum_food_22.2.22$Product %in% hum_food_latest$Product]
+hum_food_latest$Product[!hum_food_latest$Product %in% hum_food_22.2.22$Product]
+
+# Minor transformation and N calclation
+hum_food_updated = hum_food_22.2.22 %>% dplyr::select(-USDA_Code) %>% 
+  type.convert() %>% 
+  dplyr::mutate(N = case_when(is.na(N) ~ Protein/6.25,
+                       TRUE ~ N))
+
+write_csv(hum_food_updated, "Input_data/Human_food_update_22_2_22.csv")
+
 # Animal nutrition new ----------------------------------------------------
 # Cifos sheet 
 dat_animnutr = readxl::read_excel("Input_data/Copy of European_CiFoS_model_data_ANITANov21.xlsx", sheet = "Animal_Nutr") 
@@ -1296,7 +1319,6 @@ FunAnimDatExtract = function(dat, cvb_code, cvb_name, product){
     # Calculations 
     #[F.H11] GE (kJ/kg) = 24.14 x CP + 36.57 x CFAT + 20.92 x CF + 16.99 x NFE - 0.63 x SUG*
     dplyr::mutate(
-      
       ge =  case_when(
         sug > 80  ~ round((cp*24.14+cfat*36.57+cf*13.81+nfe*16.99-0.63*sug)/1000,1), 
         sug <= 80 ~ round((cp*24.14+cfat*36.57+cf*13.81+nfe*16.99-0.63)/1000,1)),
@@ -2002,6 +2024,17 @@ ani_nutr_v7.2.22=animal_nutrition_all_old %>% dplyr::select(c(product)) %>%
 write_csv(animal_nutrition_all, "Input_data/animal_nutrition_all.csv")
 read_csv("Input_data/animal_nutrition_all.csv")
 }
+
+
+# Update - 22.2.22  -------------------------------------------------------
+dat_aninutr_recent = read_excel("D:/GAMS/EU_model_Feb2022/European_CiFoS_model_data.xlsx", sheet = "Animal_Feed_Nutr" )
+
+dat_aninutr_updated = dat_aninutr_recent %>% dplyr::select(-Origin) %>% 
+  distinct(Product, .keep_all = T)
+
+write_csv(dat_aninutr_updated, "Input_data/dat_ani_nutr_update_22_2_22.csv")
+
+
 # Loss fraction sheet  ----------------------------------------------------
 dat_lossfrac = read_excel("Input_data/Copy of European_CiFoS_model_data_ANITANov21.xlsx", sheet = "Loss_Fraction_New")
 dat_lossfrac_join= dat_lossfrac %>% dplyr::select(c(1:10)) %>%  janitor::row_to_names(1)%>% select(-ProdCat ,-Fam_SPAM) %>% 
@@ -2614,6 +2647,15 @@ CropFert =
 
 write_csv(CropFert, "Input_data/cropfert_inter.csv")
 
+# Fert_Nutr ---------------------------------------------------------------
+# Sheet contains the products (procraw and procout) with NPK values on DM basis
+proc_recent = read_excel("D:/GAMS/EU_model_Feb2022/European_CiFoS_model_data.xlsx", sheet = "Processing" )
+
+dat_aninutr_updated = dat_aninutr_recent %>% dplyr::select(-Origin) %>% 
+  distinct(Product, .keep_all = T)
+
+write_csv(dat_aninutr_updated, "Input_data/dat_ani_nutr_update_22_2_22.csv")
+
 # Data maps ---------------------------------------------------------------
 # Anitas excel -- differs a bit to mine
 data_map = read_excel("Input_data/Copy of European_CiFoS_model_data_ANITANov21.xlsx", sheet = "Data_Map")