Skip to content
Snippets Groups Projects
Commit 735c7aa3 authored by Simon, Wolfram's avatar Simon, Wolfram
Browse files

Conflict with the local repo

parent bdd60802
Branches
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
R_to_SQL_database/Crop_cifos_DataPreparation_DB.R deleted 100644 → 0
+ 0
− 2276
View file @ bdd60802
Loading packages --------------------------------------------------------
# Loading the packages
# .libPaths("C:/Wolfram_Admin/R-4.1.2/R-4.1.2/library")
# install.packages("easypackages", dependencies = T)
# library("easypackages")
# Loading packages
easypackages::packages("odbc","DBI", "RSQLite", "dbplyr", "readxl", "fuzzyjoin",
"sqldf", "downloader", "tidyverse", "janitor", "FAOSTAT",
"validate")
# https://www.youtube.com/watch?v=CydajdNRJOU -----------------------------
# con <- dbConnect(odbc::odbc(),
# .connection_string = "Driver={MySQL ODBC 8.0 Unicode Driver};",
# Server = "localhost", Database = "data", UID = "root", PWD = "154236w.S",
# Port = 3306)
#
#
#
# install.packages("quantmod"); require("quantmod")
#
# ticker = "AAPL"
# stock = getSymbols(ticker, auto.assign = FALSE)
#
# # extracting index
# idx = as.data.frame(index(stock))
# stock = as.data.frame(cbind(idx,coredata(stock)))
# colnames(stock) = c("Date", "Open", "High", "Low", "Close", "Volume" , "Adjusted")
# head(stock)
#
# stock$Symbol = ticker
#
#
# TYPES = list(Date="date",
# Open="double(10,2)",
# High="double(10,2)",
# Low="double(10,2)",
# Close="double(10,2)",
# Volume="Int(25)",
# Adjusted="double(10,2)",
# Symbol="varchar(5)")
#
# # Writing data into the database -----------------------------------------
# system.time(
# dbWriteTable(con, name="temp", value=stock, field.types=TYPES, row.names=FALSE))
#
#
# # adding another table for AMZN
# ticker = "AMZN"
# stock = getSymbols(ticker, auto.assign = FALSE)
#
# # extracting index
# idx = as.data.frame(index(stock))
# stock = as.data.frame(cbind(idx,coredata(stock)))
# colnames(stock) = c("Date", "Open", "High", "Low", "Close", "Volume" , "Adjusted")
# head(stock)
#
# stock$Symbol = ticker
#
# tail(stock)
#
# # Writing data into the database -----------------------------------------
# system.time(
# dbWriteTable(con, name="temp", value=stock, field.types=TYPES, row.names=FALSE))
#
# dbSendQuery(con, "insert into stk select * from temp")
# dbSendQuery(con, "drop table temp")
#
# # End connection
# dbDisconnect(con)
#
# getSymbols(data_map, auto.assign = FALSE)
# # https://www.youtube.com/watch?v=F4HP3CXijC8 -----------------------------
# install.packages(c("DBI", "RSQLite", "dbplyr"))
# .libPaths(.libPaths()[2])
# library("DBI")
# library("RSQLite")
# library("dplyr") #loads dbplyr automatically
#
# portaldb = dbConnect(SQLite(), "portal.sqlite")
# portaldb = dbConnect(RSQLite::SQLite(), "portal.sqlite")
#
#
# dbListTables((con)) #shows the tables in the connection
# dbListFields(con, "stk") #gives the fields in the tables
#
# # Displaying the table in the database -- this table is not actually an R object yet.
# stk = tbl(con, "stk")
# stk
#
# stk_df = collect(stk) #this pulls the SQL table into R tbl
#
# odbc::odbc(),
# .connection_string = "Driver={MySQL ODBC 8.0 Unicode Driver};",
# Server = "localhost", Database = "data", UID = "root", PWD = "154236w.S",
# Port = 3306)
# Writing dfs into the cifos_crop schema (db: CIFOS_model_WJS) ------------
# Connection to a structured EER diagramm
con = dbConnect(odbc::odbc(),
.connection_string = "Driver={MySQL ODBC 8.0 Unicode Driver};",
Server = "localhost", Database = "cifos_crop", UID = "root", PWD = "154236w.S",
Port = 3306)
# Connection to a messy schema (no eer diagram)
con_crop_map = dbConnect(odbc::odbc(),
.connection_string = "Driver={MySQL ODBC 8.0 Unicode Driver};",
Server = "localhost",
Database = "crop_mapping",
UID = "root",
PWD = "154236w.S",
Port = 3306)
# https://db.rstudio.com/getting-started/database-queries
# Loading the data sets from Database -------------------------------------
data_map = tbl(con_crop_map, "data_map")
data_map = as_tibble(tbl(con_crop_map, "data_map"))
# Crops -------------------------------------------------------------------
# Issue: THis will not work anymore as the crop file on the database has been uploaded since.
crop_disag_map = as_tibble(tbl(con_crop_map, "crop_disag_map"))
# The crop dataset: Job is to add grass and get the original names back to column crop_cifos
crop = as_tibble(tbl(con, "crop"))
mapping_grasscrops = read_csv("Input_data/mapping_grasscrops_new.csv") %>%
dplyr::rename(crop_cifos = crops_cifos) %>% dplyr::select(crop_cifos)
dat_crop = as_tibble(crop) %>%
dplyr::mutate(old_cifos_crop = crop_cifos) %>%
dplyr::mutate(crop_cifos = ifelse(!is.na(crop_name_monfreda),
crop_name_monfreda,
crop_long_spam)) %>%
dplyr::filter(!grepl("grass", crop_cifos)) %>%
bind_rows(.,mapping_grasscrops) %>%
mutate(crop_cifos = tolower(crop_cifos),
crop_cifos = gsub("\\,", "", crop_cifos),
crop_cifos = gsub(" ", "_", crop_cifos)) %>%
dplyr::mutate(crop_cifos = dplyr::recode(crop_cifos,
"tobacco_unmanufactured" = "tobacco",
"groundnuts_with_shell" = "groundnuts",
# "dark_green_vegetables " = "green_vegetables",
"other_roots_and_tubers" = "other_tubers",
# grepl("red_and_orange",crop_cifos) = "red_vegetables",
# "other_vegetables " = "other_vegetables",
"sunflower_seed" = "sunflower",
"other_cereal_crops" = "other_cereals",
"sesame_seed" = "sesame"))
# write_csv(dat_crop, "Input_data/dat_crop_with_grass.csv")
#ISSUE: The vegetable values are behaving weird. Had to remove two spaces at the end manually in CSV.
#Be careful when changing again.
dat_crop2=read_csv("Input_data/dat_crop_with_grass.csv") %>%
dplyr::mutate(crop_cifos = dplyr::recode(crop_cifos,
"dark_green_vegetables" = "green_vegetables",
"red_and_orange_vegetables" = "red_vegetables",
"other_vegetables" = "other_vegetables"))
write_csv(dat_crop2, "Input_data/dat_crop_with_grass_final.csv")
dat_crop_final = read_csv("Input_data/dat_crop_with_grass_final.csv")
# crop_cifos = case_when(crop_cifos != is.na(crop_cifos) ~ crop_long_spam)) %>%
# dplyr::mutate(crop_cifos_2 = case_when(crop_cifos = is.na(crop_cifos) ~ crop_name_monfreda),
# TRUE ~ crop_cifos)
# class(data_map)
#
# # Loading data into R from database - 152 rows
# # Comment: Complete! ProcOutH -> Dietary Products
# #
# procOutH_dietprod = data_map %>%
# dplyr::select(`ProcOutH...1`:DietProd) %>%
# dplyr::arrange() %>%
# drop_na()
#
# # crops - 111 rows
# procOut_all = data_map %>%
# dplyr::select(`ProcOutH...5`) %>%
# dplyr::arrange() %>%
# drop_na()
#
# # crops_co product - rows 31
# # comments: mapping is not correct!!
# crops_coproduct = data_map %>%
# dplyr::select(`CROPS FAO...7`:`Co-Product...8`) %>%
# dplyr::arrange() %>%
# drop_na()
#
# # Crops and coproducts - 110 rows
# crops_coproduct_2 = data_map %>%
# dplyr::select(c(22,23)) %>%
# dplyr::arrange(c(1)) %>%
# drop_na()
#
# # Crops and coproducts and dietary products - 110 rows
# # # Not important! Ignore
# # crops_coproduct_dietaryprod = data_map %>%
# # dplyr::select(c(22,23,24)) %>%
# # dplyr::arrange(c(1)) %>%
# # drop_na()
#
# # Livestock - 11 rows
# livestock_co_product = data_map %>%
# dplyr::select(c(11,12)) %>%
# dplyr::arrange(LIVESTOCK) %>%
# drop_na()
#
# # Fish products - 18 rows
# Fish_coproducts = data_map %>%
# dplyr::select(c(15,16)) %>%
# dplyr::arrange(FISH) %>%
# drop_na()
#
# # #aquatic plants 14 rows
# aquatic_plants = data_map %>% dplyr::select(c(25)) %>%
# dplyr::arrange(c(1)) %>%
# drop_na()
#
# # crops-coprod-dietaryProd - 18 rows
# crops_coproduct_dietaryprod = data_map %>%
# dplyr::select(c(29, 30, 31)) %>%
# dplyr::arrange(c(1)) %>%
# drop_na()
#
# # Processing - Fraction - CropsFAO
# processingfrac_cropsfao = data_map %>%
# dplyr::select(`Processing Fraction - Products`, c(41))
# #
# # CropsFAO - FoodProducts
# Yield_food_prod = data_map %>% dplyr::select(`CROPS FAO - yield`, `Food Products`)
#
# # Checking the crops with the dietary sheet ----------------------------------------------------
# crop = as_tibble(tbl(con, "crop"))
dat_cifos <- read_excel("Input_data/Copy of European_CiFoS_model_data_ANITANov21.xlsx", sheet = "Animal_Nutr")
# Processing sheet --------------------------------------------------------
Processing_sheet = read_csv("Input_data/Copy of European_CiFoS_model_data_ANITANov21.csv")
dat_crop_final = read_csv("Input_data/dat_crop_with_grass_final.csv") %>%
# Adding the grass to the old crop name columns so it will not result in NA later.
dplyr::mutate(old_cifos_crop = case_when(is.na(old_cifos_crop) ~ crop_cifos,
TRUE ~ old_cifos_crop))
# Fuzzy join of processing sheet and the crop map
# crop_map_cifos_procraw =
dat_proc = Processing_sheet %>%
dplyr::select(c(1:5)) %>%
stringdist_right_join(drop_na(dat_crop_final, old_cifos_crop),
by = c("ProRaw" = "old_cifos_crop"),
max_dist = 2) %>% #This results in the 59 crops (incl grass) - Good!
dplyr::select(crop_cifos, ProRaw, ProcIn,ProcOut, Value, `Dietary Products`) %>%
dplyr::rename(Proc_Raw=ProRaw) %>% clean_names() %>%
# Adding the forage crops and grass to the processing sheet
dplyr::mutate(across(c(proc_raw, proc_in, proc_out),
~ case_when(str_detect(crop_cifos, "for") ~ crop_cifos,
str_detect(crop_cifos, "grass") ~ crop_cifos,
crop_cifos == "tobacco" ~ crop_cifos,
crop_cifos == "seed_cotton" ~ crop_cifos,
TRUE ~ .)),
across(c(value), ~ case_when(str_detect(crop_cifos, "for") ~ 1,
str_detect(crop_cifos, "grass") ~ 1,
crop_cifos == "tobacco" ~ 1,
crop_cifos == "seed_cotton" ~ 1,
TRUE ~ .)))
# removing disaggregated group elemetns that are not needed -
# Aim: To have only one surrogate crop per crop_group (temperate_fruits = Apples)
# First paragraph is about the aggregated crop groups
# The second paragraph is about the crops that show weird relative crops
# with no values. LIke this we can get rid of the unwanted crop rows in one go.
# Assumptions:
# - I deleted the potato starch as it had a value of 0 (Why?)
dat_2nd_level = Processing_sheet %>%
dplyr::select(c(1:5)) %>%
stringdist_right_join(drop_na(dat_crop_final, old_cifos_crop),
by = c("ProRaw" = "old_cifos_crop"),
max_dist = 2)
dat_2nd_level2 = anti_join(Processing_sheet,dat_2nd_level, by = "ProRaw") %>%
dplyr::select(-c(6:7)) %>%
dplyr::rename(proc_raw = ProRaw) %>%
drop_na() %>%
filter(`Dietary Products` %in% c("Sugar (Raw Equivalent)",
"Rice and products",
"Beer")) %>%
mutate(crop_cifos = c("sugar_beet", "sugar_beet", "rice", "rice",
"barley", "barley")) %>%
relocate(crop_cifos, .before = 1) %>%
clean_names()
dat_group = sqldf('SELECT * FROM dat_proc WHERE
crop_cifos == "temperate_fruit" AND proc_in == "Apple" OR
crop_cifos == "other_vegetables" AND proc_in == "Cabbage_White" OR
crop_cifos == "green_vegetables" AND proc_in == "Spinach" OR
crop_cifos == "red_vegetables" AND proc_in == "Carrot_Winter" OR
crop_cifos == "other_cereals" AND proc_in == "Oat_Food" OR
crop_cifos == "other_cereals" AND proc_in == "Oat_Feed" OR
crop_cifos == "other_pulses" AND proc_in == "Bean_french" OR
crop_cifos == "other_oil_crops" AND proc_raw == "Olives" OR
crop_cifos == "other_crops" OR
crop_cifos == "other_fibres" OR
crop_cifos == "tropical_fruits" AND proc_in == "oranges_for_juice" OR
crop_cifos == "tropical_fruits" AND proc_in == "Orange" OR
crop_cifos == "other_tubers" AND proc_raw == "Yautia" OR
crop_cifos == "treenuts" AND proc_in == "Walnut" OR
crop_cifos == "sunflower" AND proc_raw == "Sunflower seed" OR
crop_cifos == "bananas" AND proc_in == "Banana" OR
crop_cifos == "sugar_beet" AND proc_in == "Sugarbeet" OR
crop_cifos == "soybeans" AND proc_in == "Soyabean_for_oil" OR
crop_cifos == "soybeans" AND proc_in == "Soyabean_for_table" OR
crop_cifos == "maize" AND proc_in == "Maize" OR
crop_cifos == "pigeon_peas" AND proc_in == "Pea"
') %>% as_tibble()
# Remove the groupped crops from the mother df and bind the final dataset togehter
dat_proc_2 = dat_proc %>%
anti_join(., dat_group, by = "crop_cifos") %>% #then I delete all the rows with unwanted duplicates
bind_rows(dat_group)#then I add the nicely filtered rows and get a clean df
# Adding missing dietary products
# Cifos dietary products - here i filter for strings in the FAO database
dat_proc_2 %>% filter(grepl("Cocoa", dietary_products))
# From FAO supply sheet for year 2014 - here i filter for strings in the FAO database
dat_foodsupply = read_csv("Input_data/FAOSTAT_FoodSupply_data_11-23-2021.csv")
dat_foodsupply %>% dplyr::filter(Element=="Processing") %>%
filter(grepl("Cocoa", Item)) %>%
distinct(Item)
# df with missing dietary products
dat_missin_dietprod = dat_proc_2 %>%
dplyr::filter(is.na(dietary_products)) %>% pull(crop_cifos)
# Adding the missing dietary prodcucts to the dataframe
dat_dietprod_comp = dat_proc_2 %>%
# Adding dietary products to the missing crops
dplyr::mutate(dietary_products = case_when(
# Forage crops --- Fodder crops and products
crop_cifos == "beetfor" ~ "Sugar beet",
crop_cifos == "cabbagefor" ~ "Vegetables, Other",
crop_cifos == "carrotfor" ~ "Vegetables, Other",
crop_cifos == "oilseedfor" ~ "Soyabean Oil",
crop_cifos == "fornesfor" ~ "Vegetables, Other",
crop_cifos == "legumenesfor" ~ "Pulses, Other and products",
crop_cifos == "maizefor" ~ "Maize and products",
crop_cifos == "ryefor" ~ "Rye and products", # newly added to cifos
crop_cifos == "swedefor" ~ "Sugar beet",
crop_cifos == "turnipfor" ~ "Sugar beet",
crop_cifos == "vegfor" ~ "Vegetables, Other",
# Grassy crops
crop_cifos == "grass_pasture" ~ "Roughage", #no real FAO category
crop_cifos == "cloverfor" ~ "Roughage",
str_detect(crop_cifos, "grass") ~ "Roughage", #no real FAO category
# Food crops
crop_cifos == "cassava" ~ "Cassava and products", # newly added to cifos
crop_cifos == "coconuts" ~ "Coconuts - Incl Copra",
crop_cifos == "cow_peas_dry" ~ "Pulses, Other and products",
crop_cifos == "pearl_millet" ~ "Millet and products", # newly added to cifos
crop_cifos == "oil_palm_fruit" ~ "Palm kernels", # newly added to cifos; options: 1 Palm kernels, 2 Palmkernel Oil 3 Palm Oil
crop_cifos == "plantains" ~ "Plantains", # newly added to cifos;
crop_cifos == "seed_cotton" ~ "Fibres", #no real FAO category
crop_cifos == "sorghum" ~ "Sorghum and products",# newly added to cifos;
crop_cifos == "sugar_cane" ~ "Sugar cane", # newly added to cifos;
crop_cifos == "sweet_potatoes" ~ "Sweet potatoes", # newly added to cifos;
crop_cifos == "tea" ~ "Tea (including mate)", #newly added to cifos;
crop_cifos == "tobacco" ~ "Tobacco",#no real FAO category; newly added to cifos;
crop_cifos == "yams" ~ "Vegetables, Other",
crop_cifos == "other_crops" ~ "Pulses, Other and products",
crop_cifos == "other_fibres" ~ "Fibres",#no real FAO category;newly added to cifos;
crop_cifos == "cocoa_beans" ~ "Cocoa Beans and products", # newly added to cifos;
crop_cifos == "other_tubers" ~ "Vegetables, Other",
TRUE ~ dietary_products))
# Removing Nas in the columns procin and procout. Rough assumption: all prcessing fractions = 1. Names from proc_raw
vec_proc_raw = dat_dietprod_comp %>% dplyr::filter(is.na(proc_in)) %>% pull(proc_raw)
dat_comp = dat_dietprod_comp %>% dplyr::filter(is.na(proc_in)) %>%
tibble::add_column(na_replace = vec_proc_raw) %>%
dplyr::mutate(proc_in = na_replace,
proc_out = na_replace,
value = 1) %>%
dplyr::select(-na_replace)
# Merging dfs - FInal processing sheet
dat_complete = dat_dietprod_comp %>%
dplyr::filter(!is.na(proc_in)) %>%
bind_rows(., dat_comp) %>%
distinct_all() %>% # tobacco was triplicated
bind_rows(dat_2nd_level2)
# write_csv(dat_complete, "Input_data/processing_sheet_2.csv")
# dat_complete = read_csv("Input_data/processing_sheet_2.csv")
# Isolate new dietary products
new_dietprods = dat_complete %>%
anti_join(., dat_proc_2, by="dietary_products")
# Distinct new dietary products
new_dietprods_dist = dat_complete %>%
anti_join(., dat_proc_2, by="dietary_products") %>%
dplyr::distinct(dietary_products, .keep_all = T)
# This is the ones that are freely added and have a correspondant entry in the FAO supply data sheet
new_dietprods_dist_FAO = new_dietprods_dist %>%
dplyr::filter(!dietary_products %in% c("Roughage", "Fibres", "Tea", "Tobacco", "Fibres"))
# This is the ones that are freely added and have NO correspondant entry in the FAO supply data sheet
new_dietprods_dist_noFAO = new_dietprods_dist %>%
dplyr::filter(dietary_products %in% c("Roughage", "Fibres", "Tea", "Tobacco", "Fibres"))
# Adding the missing proc outs
# 1. Identifying the missing proc-outs
# new_procout = dat_complete %>%
# dplyr::filter(!is.na(proc_out)) %>%
# distinct_all() %>%
# dplyr::anti_join(.,Processing_sheet, by=c("proc_out" = "ProcOut"))
new_procin = dat_complete %>%
dplyr::filter(!is.na(proc_in)) %>%
distinct_all() %>%
dplyr::anti_join(.,Processing_sheet, by=c("proc_in" = "ProcIn"))
# Conclusion: There are 33 newly added processing products that need to be processed into different processing products
# Rules:
# - Forage gets value = 1.
# - If forage crops are represented as well as food crops they have to be merged to the food crop;
# That means they should get the same procin name but then get the different procout ("wheat_feed" or so)
print(new_procin, n=33)
print(new_procin, n=33)
# A tibble: 33 x 6
# crop_cifos proc_raw proc_in proc_out value dietary_products
# <chr> <chr> <chr> <chr> <dbl> <chr>
# 1 grass_pasture grass_pasture grass_pasture grass_pasture 1 Roughage
# 2 beetfor beetfor beetfor beetfor 1 Sugar beet
# 3 cabbagefor cabbagefor cabbagefor cabbagefor 1 Vegetables, Other
# 4 carrotfor carrotfor carrotfor carrotfor 1 Vegetables, Other
# 5 cloverfor cloverfor cloverfor cloverfor 1 Roughage
# 6 fornesfor fornesfor fornesfor fornesfor 1 Vegetables, Other
# 7 legumenesfor legumenesfor legumenesfor legumenesfor 1 Pulses, Other and products
# 8 maizefor maizefor maizefor maizefor 1 Maize and products
# 9 oilseedfor oilseedfor oilseedfor oilseedfor 1 Soyabean Oil
# 10 ryefor ryefor ryefor ryefor 1 Rye and products
# 11 seed_cotton seed_cotton seed_cotton seed_cotton 1 Fibres
# 12 swedefor swedefor swedefor swedefor 1 Sugar beet
# 13 tobacco tobacco tobacco tobacco 1 Tobacco
# 14 turnipfor turnipfor turnipfor turnipfor 1 Sugar beet
# 15 vegfor vegfor vegfor vegfor 1 Vegetables, Other
# 16 grass_pasture grass_pasture grass_pasture grass_pasture 1 Roughage
# 17 grass_arable grass_arable grass_arable grass_arable 1 Roughage
# 18 grass_rangeland grass_rangeland grass_rangeland grass_rangeland 1 Roughage
# 19 cassava Cassava Cassava Cassava 1 Cassava and products
# 20 cocoa_beans Cocoa beans Cocoa beans Cocoa beans 1 Cocoa Beans and products
# 21 coconuts Coconuts Coconuts Coconuts 1 Coconuts - Incl Copra
# 22 cow_peas_dry Cow peas, dry Cow peas, dry Cow peas, dry 1 Pulses, Other and products
# 23 pearl_millet Millet Millet Millet 1 Millet and products
# 24 oil_palm_fruit Oil palm fruit Oil palm fruit Oil palm fruit 1 Palm kernels
# 25 plantains Plantains Plantains Plantains 1 Plantains
# 26 sorghum Sorghum Sorghum Sorghum 1 Sorghum and products
# 27 sugar_cane Sugar cane Sugar cane Sugar cane 1 Sugar cane
# 28 sweet_potatoes Sweet potatoes Sweet potatoes Sweet potatoes 1 Sweet potatoes
# 29 tea Tea Tea Tea 1 Tea
# 30 yams Yams Yams Yams 1 Vegetables, Other
# 31 other_crops Chilies and peppers, green Chilies and peppers, green Chilies and peppers, green 1 Pulses, Other and products
# 32 other_fibres Flax fiber and tow Flax fiber and tow Flax fiber and tow 1 Fibres
# 33 other_tubers Yautia Yautia Yautia 1 Vegetables, Other
# Processing hardcode -----------------------------------------------------
proc_new = tibble("crop_cifos" = NA, "proc_raw" = NA, "proc_in" = NA, "proc_out" = NA, "value" = NA, "dietary_products" = NA) %>%
# Cocoa -- Source: from Technical Conversion Factors for Agricultural Commodities (http://countrystat.org/resources/documents/tcf.pdf)
# Assumptions: we just look at chocolate production from cocoa comodity tree up to 2nd level
# level: second level where available.
add_row(crop_cifos = "cocoa_beans" , proc_raw = "Cocoa beans" , proc_in = "cocoa_for_chocolate", proc_out = "cocoa_butter", value = 0.47 *.8, dietary_products = "Cocoa Beans and products") %>%
add_row(crop_cifos = "cocoa_beans" , proc_raw = "Cocoa beans" , proc_in = "cocoa_for_chocolate", proc_out = "cocoa_powder_cake", value = 0.53 *.8, dietary_products = "Cocoa Beans and products") %>%
add_row(crop_cifos = "cocoa_beans" , proc_raw = "Cocoa beans" , proc_in = "cocoa_for_chocolate", proc_out = "cocoa_husks", value = 0.2, dietary_products = "Cocoa Beans and products") %>%
drop_na() %>%
# Coconut -- Source: from Technical Conversion Factors for Agricultural Commodities (http://countrystat.org/resources/documents/tcf.pdf)
# Assumptions: It adds not up to 1 due to water loss
# levels: second level where available, no data for copra only!
add_row(crop_cifos = "coconuts" , proc_raw = "coconuts" , proc_in = "coconuts_dessicatedin", proc_out = "coconuts_dessicated", value = 0.20, dietary_products = "Coconuts - Incl Copra") %>%
add_row(crop_cifos = "coconuts" , proc_raw = "coconuts" , proc_in = "coconuts_copra", proc_out = "coconuts_oil_copra", value = 0.21*0.64, dietary_products = "Coconut Oil") %>%
add_row(crop_cifos = "coconuts" , proc_raw = "coconuts" , proc_in = "coconuts_copra", proc_out = "coconuts_cake_copra", value = 0.21*0.36, dietary_products = "Coconuts - Incl Copra") %>%
# Cassava -- Source: from Technical Conversion Factors for Agricultural Commodities (http://countrystat.org/resources/documents/tcf.pdf); adjusted commodity tree.
# Levels: only one level in tcf doc!
add_row(crop_cifos = "cassava" , proc_raw = "cassava" , proc_in = "cassava_flourin", proc_out = "cassava_flour", value = 0.3, dietary_products = "Cassava and products") %>%
add_row(crop_cifos = "cassava" , proc_raw = "cassava" , proc_in = "cassava_tapiocain", proc_out = "cassava_tapioca", value = 0.2, dietary_products = "Cassava and products") %>%
add_row(crop_cifos = "cassava" , proc_raw = "cassava" , proc_in = "cassava_dryin", proc_out = "cassava_dry", value = 0.35, dietary_products = "Cassava and products") %>%
add_row(crop_cifos = "cassava" , proc_raw = "cassava" , proc_in = "cassava_starchin", proc_out = "cassava_starch", value = 0.25, dietary_products = "Cassava and products") %>%
# Pearl millet -- Source: from Technical Conversion Factors for Agricultural Commodities (http://countrystat.org/resources/documents/tcf.pdf); adjusted commodity tree; fractions from "cereals/millet"
# levels: only one level
add_row(crop_cifos = "pearl_millet" , proc_raw = "pearl_millet" , proc_in = "pearl_millet_flourin", proc_out = "pearl_millet_flour", value = 0.86, dietary_products = "Millet and products") %>%
add_row(crop_cifos = "pearl_millet" , proc_raw = "pearl_millet" , proc_in = "pearl_millet_flourin", proc_out = "pearl_millet_bran", value = 0.10, dietary_products = "Millet and products") %>%
add_row(crop_cifos = "pearl_millet" , proc_raw = "pearl_millet" , proc_in = "pearl_millet_beerin", proc_out = "pearl_millet_beer", value = 4.5, dietary_products = "Millet and products") %>%
# Oil palm -- Source: from Technical Conversion Factors for Agricultural Commodities (http://countrystat.org/resources/documents/tcf.pdf); adjusted commodity tree; fractions from "OIL PALM FRUIT"
# Assumption: oil_palm_kernels_fibre is just the difference of the sum of the listed categories to 1.
# Both kernels and fruits are always both processed
add_row(crop_cifos = "oil_palm_fruit" , proc_raw = "oil_palm_fruit" , proc_in = "oil_palm_fruitin", proc_out = "oil_palm_fruits_oil", value = 0.19, dietary_products = "Palm Oil") %>%
add_row(crop_cifos = "oil_palm_fruit" , proc_raw = "oil_palm_fruit" , proc_in = "oil_palm_fruitin", proc_out = "oil_palm_kernels_cake", value = 0.46*0.06, dietary_products = "Palm kernels") %>%
add_row(crop_cifos = "oil_palm_fruit" , proc_raw = "oil_palm_fruit" , proc_in = "oil_palm_fruitin", proc_out = "oil_palm_kernels_oil", value = 0.53*0.06, dietary_products = "Palmkernel Oil") %>%
# plantains -- tables from countries. Assumptions: the whole plantain is to be kept whole! Question: Is that a fair assumption?
add_row(crop_cifos = "plantains" , proc_raw = "plantains" , proc_in = "plantains", proc_out = "plantains", value = 1, dietary_products = "Plantains") %>%
# sorghum -- adjusted commodity table "Sorghum"
# levels, only level 1 used (level 2 does not make)
add_row(crop_cifos = "sorghum" , proc_raw = "sorghum" , proc_in = "sorghum_flourin", proc_out = "sorghum_flour", value = 0.9, dietary_products = "Sorghum and products") %>%
add_row(crop_cifos = "sorghum" , proc_raw = "sorghum" , proc_in = "sorghum_flourin", proc_out = "sorghum_bran", value = 0.08, dietary_products = "Sorghum and products") %>%
add_row(crop_cifos = "sorghum" , proc_raw = "sorghum" , proc_in = "sorghum_beerin", proc_out = "sorghum_beer", value = 4.85, dietary_products = "Sorghum and products") %>% #on first level
# sugar_cane
# add_row(crop_cifos = "sugar_cane" , proc_raw = "sugar_cane" , proc_in = "sugar_cane", proc_out = "beverage_non_alc", value = 0.13*0.5, dietary_products = "Sugar cane") %>%
# add_row(crop_cifos = "sugar_cane" , proc_raw = "sugar_cane" , proc_in = "sugar_cane", proc_out = "beverage_dist_alc", value = 0.13*0.5, dietary_products = "Sugar cane") %>%
add_row(crop_cifos = "sugar_cane" , proc_raw = "sugar_cane" , proc_in = "sugar_canein", proc_out = "sugar_raw", value = 0.11, dietary_products = "Sugar (Raw Equivalent)") %>%
add_row(crop_cifos = "sugar_cane" , proc_raw = "sugar_raw" , proc_in = "for_sugar_white", proc_out = "sugar_white", value = 0.935, dietary_products = "Sugar (Raw Equivalent)") %>% # 2nd level of sugar raw
# add_row(crop_cifos = "sugar_cane" , proc_raw = "sugar_raw" , proc_in = "for_sugar_white", proc_out = "sugar_factorylime", value = 1-0.935, dietary_products = "Sugar (Raw Equivalent)") %>% # 2nd level of sugar raw
add_row(crop_cifos = "sugar_cane" , proc_raw = "sugar_cane" , proc_in = "sugar_canein", proc_out = "sugarcane_molasse", value = 0.05, dietary_products = "Sugar cane") %>%
add_row(crop_cifos = "sugar_cane" , proc_raw = "sugar_cane" , proc_in = "sugar_canein", proc_out = "sugarcane_bagasse", value = 0.25, dietary_products = "Sugar cane") %>%
#sweet_potatoes -- commodity tree
add_row(crop_cifos = "sweet_potatoes" , proc_raw = "sweet_potatoes" , proc_in = "sweet_potatoe_flourin", proc_out = "sweet_potatoe_flour", value = 0.25, dietary_products = "Sweet potatoes") %>%
add_row(crop_cifos = "sweet_potatoes" , proc_raw = "sweet_potatoes" , proc_in = "sweet_potatoe_starchin", proc_out = "sweet_potatoe_starch", value = 0.2, dietary_products = "Sweet potatoes") %>%
# tea --
add_row(crop_cifos = "tea" , proc_raw = "tea" , proc_in = "teain", proc_out = "tea_leave", value = 1, dietary_products = "Tea (including mate)") %>%
# yams --
# 1 . level only (other tubers)
add_row(crop_cifos = "yams" , proc_raw = "yams" , proc_in = "yams_flourin", proc_out = "yams_flour", value = 0.25, dietary_products = "Roots, Other") %>%
add_row(crop_cifos = "yams" , proc_raw = "yams" , proc_in = "yams_dryin", proc_out = "yams_dry", value = 0.3, dietary_products = "Roots, Other") %>%
# other_crops --
add_row(crop_cifos = "other_crops" , proc_raw = "chilies_and_peppers_green" , proc_in = "chilies_and_peppers_green", proc_out = "chilies_and_peppers_green", value = 0.9, dietary_products = "Pulses, Other and products") %>% # Commodity tree, from Egypt "Chillies, green"
# other_fibres -- cotton fibre fractions
add_row(crop_cifos = "other_fibres" , proc_raw = "flax_fiber_and_tow" , proc_in = "flax_fiber_and_tow", proc_out = "flax_fiber_and_tow", value = 0.33, dietary_products = "Fibres") %>%
# other_tubers
# 1 . level only (other tubers)
add_row(crop_cifos = "other_tubers" , proc_raw = "other_tubers" , proc_in = "other_tubers_flourin", proc_out = "other_tubers_flour", value = 0.25, dietary_products = "Roots, Other") %>%
add_row(crop_cifos = "other_tubers" , proc_raw = "other_tubers" , proc_in = "other_tubers_dryin", proc_out = "other_tubers_dry", value = 0.3, dietary_products = "Roots, Other") %>%
# cotton - cotton fibre fractions
add_row(crop_cifos = "seed_cotton" , proc_raw = "seed_cotton" , proc_in = "seed_cotton_fibresin", proc_out = "seed_cotton_fibres", value = 0.33, dietary_products = "Fibres") %>%
# tobacco
add_row(crop_cifos = "tobacco" , proc_raw = "tobacco" , proc_in = "tobacco_leavesin", proc_out = "tobacco_leaves", value = 1, dietary_products = "Tobacco") %>%
# Chick peas
# Levels: all pulses only one level
add_row(crop_cifos = "chick_peas" , proc_raw = "chick_peas" , proc_in = "chickpea_vegetablein", proc_out = "chickpea_vegetable", value = 0.95, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "chick_peas" , proc_raw = "chick_peas" , proc_in = "chickpea_flourin", proc_out = "chickpea_flour", value = 0.72, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "chick_peas" , proc_raw = "chick_peas" , proc_in = "chickpea_flourin", proc_out = "chickpea_bran", value = 0.23, dietary_products = "Pulses, Other and products") %>%
# Beans dry
# Levels: all pulses only one level
add_row(crop_cifos = "beans_dry" , proc_raw = "beans_dry" , proc_in = "beans_dry_vegetable", proc_out = "beans_dry_vegetable", value = 0.95, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "beans_dry" , proc_raw = "beans_dry" , proc_in = "beans_dry_flourin", proc_out = "beans_dry_flour", value = 0.72, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "beans_dry" , proc_raw = "beans_dry" , proc_in = "beans_dry_flourin", proc_out = "beans_dry_bran", value = 0.23, dietary_products = "Pulses, Other and products") %>%
# Other pulses
# Levels: all pulses only one level
add_row(crop_cifos = "other_pulses" , proc_raw = "other_pulses" , proc_in = "other_pulses_vegetable", proc_out = "other_pulses_vegetable", value = 0.95, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "other_pulses" , proc_raw = "other_pulses" , proc_in = "other_pulses_flourin", proc_out = "other_pulses_flour", value = 0.72, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "other_pulses" , proc_raw = "other_pulses" , proc_in = "other_pulses_flourin", proc_out = "other_pulses_bran", value = 0.23, dietary_products = "Pulses, Other and products") %>%
# lentils
# Levels: all pulses only one level
add_row(crop_cifos = "lentils" , proc_raw = "lentils" , proc_in = "lentils_vegetable", proc_out = "lentils_vegetable", value = 0.95, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "lentils" , proc_raw = "lentils" , proc_in = "lentils_flourin", proc_out = "lentils_flour", value = 0.72, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "lentils" , proc_raw = "lentils" , proc_in = "lentils_flourin", proc_out = "lentils_bran", value = 0.23, dietary_products = "Pulses, Other and products") %>%
# pigeon_peas
# Levels: all pulses only one level
add_row(crop_cifos = "pigeon_peas" , proc_raw = "pigeon_peas" , proc_in = "pigeon_peas_vegetable", proc_out = "pigeon_peas_vegetable", value = 0.95, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "pigeon_peas" , proc_raw = "pigeon_peas" , proc_in = "pigeon_peas_flourin", proc_out = "pigeon_peas_flour", value = 0.72, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "pigeon_peas" , proc_raw = "pigeon_peas" , proc_in = "pigeon_peas_flourin", proc_out = "pigeon_peas_bran", value = 0.23, dietary_products = "Pulses, Other and products") %>%
# cow_peas_dry
# Levels: all pulses only one level
add_row(crop_cifos = "cow_peas_dry" , proc_raw = "cow_peas_dry" , proc_in = "cow_peas_dry_vegetable", proc_out = "cow_peas_dry_vegetable", value = 0.95, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "cow_peas_dry" , proc_raw = "cow_peas_dry" , proc_in = "cow_peas_dry_flourin", proc_out = "cow_peas_dry_flour", value = 0.72, dietary_products = "Pulses, Other and products") %>%
add_row(crop_cifos = "cow_peas_dry" , proc_raw = "cow_peas_dry" , proc_in = "cow_peas_dry_flourin", proc_out = "cow_peas_dry_bran", value = 0.23, dietary_products = "Pulses, Other and products") %>%
# groundnuts - commodity tree
#1 level
add_row(crop_cifos = "groundnuts" , proc_raw = "groundnuts_in_shell" , proc_in = "groundnuts_shellin", proc_out = "groundnut_shelled", value = 0.7, dietary_products = "Groundnuts (Shelled Eq)") %>%
add_row(crop_cifos = "groundnuts" , proc_raw = "groundnuts_in_shell" , proc_in = "groundnuts_shellin", proc_out = "groundnut_shell", value = 0.3, dietary_products = "Groundnuts (Shelled Eq)") %>%
# 2nd level
add_row(crop_cifos = "groundnuts" , proc_raw = "groundnut_shelled" , proc_in = "groundnuts_oilin", proc_out = "groundnut_oil", value = 0.43, dietary_products = "Groundnut Oil") %>%
add_row(crop_cifos = "groundnuts" , proc_raw = "groundnut_shelled" , proc_in = "groundnuts_oilin", proc_out = "groundnut_cake", value = 0.54, dietary_products = "Groundnut Oil") %>%
add_row(crop_cifos = "groundnuts" , proc_raw = "groundnut_shelled" , proc_in = "groundnuts_butterin", proc_out = "groundnut_butter", value = 0.85, dietary_products = "Groundnuts (Shelled Eq)") %>%
# Other cereals - commodity tree
add_row(crop_cifos = "other_cereals" , proc_raw = "other_cereals" , proc_in = "other_cereals_flourin", proc_out = "other_cereals_flour", value = 0.8, dietary_products = "Cereals, Other") %>%
add_row(crop_cifos = "other_cereals" , proc_raw = "other_cereals" , proc_in = "other_cereals_flourin", proc_out = "other_cereals_bran", value = 0.2, dietary_products = "Cereals, Other") %>%
add_row(crop_cifos = "other_cereals" , proc_raw = "other_cereals" , proc_in = "other_cereals_wholein", proc_out = "other_cereals_whole", value = 1, dietary_products = "Cereals, Other") %>%
# other_oil_crops - commodity tree (tables)
# 1 level
add_row(crop_cifos = "other_oil_crops" , proc_raw = "olives" , proc_in = "olive_tablein", proc_out = "olive_table", value = 1, dietary_products = "Olives (including preserved)") %>%
add_row(crop_cifos = "other_oil_crops" , proc_raw = "olives" , proc_in = "olive_oilin", proc_out = "olive_oil", value = 0.25, dietary_products = "Olive Oil") %>% #virgine and residue oil mixed! Therfore 5% more oil
add_row(crop_cifos = "other_oil_crops" , proc_raw = "olives" , proc_in = "olive_oilin", proc_out = "olive_cake", value = 0.35, dietary_products = "Olives (including preserved)") %>%
# temperate_fruit - assumption: Whole fruit is used and no losses occur
add_row(crop_cifos = "temperate_fruit" , proc_raw = "temperate_fruit" , proc_in = "temperate_fruit_whole", proc_out = "temperate_fruit_whole", value =mean(c(0.5, 0.35,0.29, 0.25)) , dietary_products = "Apples and products") %>% #tcf fao, fractions from apples, plums, apricots, raisins
add_row(crop_cifos = "temperate_fruit" , proc_raw = "temperate_fruit" , proc_in = "temperate_fruit_juice", proc_out = "temperate_fruit_juice", value = mean(c(0.22, 0.75)) , dietary_products = "Apples and products") %>% #tcf fao, taken from apple, raisins
add_row(crop_cifos = "temperate_fruit" , proc_raw = "temperate_fruit" , proc_in = "temperate_fruit_juice", proc_out = "temperate_fruit_pulp", value = mean(c(0.4)) , dietary_products = "Apples and products") %>% #not in fao. taken from apple
# tropical_fruits - assumption: Whole fruit is used and no losses occur
add_row(crop_cifos = "tropical_fruits" , proc_raw = "tropical_fruits" , proc_in = "tropical_fruits_whole", proc_out = "tropical_fruits_whole", value = mean(c(0.65,0.52)), dietary_products = "Oranges, Mandarines") %>% #tcf fao(canned), orange canned, pineapples
add_row(crop_cifos = "tropical_fruits" , proc_raw = "tropical_fruits" , proc_in = "tropical_fruits_juice", proc_out = "tropical_fruits_juice", value = mean(c(0.1,0.1,0.2)), dietary_products = "Oranges, Mandarines") %>%#tcf fao, mean of oranges, mango, pineapple
add_row(crop_cifos = "tropical_fruits" , proc_raw = "tropical_fruits" , proc_in = "tropical_fruits_juice", proc_out = "tropical_fruits_pulp", value = mean(c(0.4,0.55)), dietary_products = "Oranges, Mandarines") %>%#tcf fao, mean of oranges, mango
#Adding more details to existing crops:
# other_vegetables
add_row(crop_cifos = "other_vegetables" , proc_raw = "cabbages" , proc_in = "cabbage_whitein", proc_out = "cabbage_white", value = 0.65, dietary_products = "Vegetables, Other") %>%
# red_vegetables
add_row(crop_cifos = "red_vegetables" , proc_raw = "carrots" , proc_in = "carrot_winterin", proc_out = "carrot_winter", value = 0.65, dietary_products = "Vegetables, Other") %>%
# green_vegetables
add_row(crop_cifos = "green_vegetables" , proc_raw = "spinach" , proc_in = "spinachin", proc_out = "spinach", value = 0.65, dietary_products = "Vegetables, Other") %>%
# Maize - commodity tree
# 2 levels
add_row(crop_cifos = "maize" , proc_raw = "maize_flour" , proc_in = "maize_flourin", proc_out = "maize_flour", value = 0.82, dietary_products = "Maize and products") %>%
add_row(crop_cifos = "maize" , proc_raw = "maize_flour" , proc_in = "maize_flourin", proc_out = "maize_bran", value = 0.11, dietary_products = "Maize and products") %>% #for feed
add_row(crop_cifos = "maize" , proc_raw = "maize_flour" , proc_in = "maize_flourin", proc_out = "maize_germ", value = 0.06, dietary_products = "Maize and products") %>%
add_row(crop_cifos = "maize" , proc_raw = "maize_germ" , proc_in = "maize_oilin", proc_out = "maize_cake", value = 0.52, dietary_products = "Maize and products") %>%
add_row(crop_cifos = "maize" , proc_raw = "maize_germ" , proc_in = "maize_oilin", proc_out = "maize_oil", value = 0.45, dietary_products = "Maize Germ Oil") %>%
# Grass crops
## grass_arable - Prefereably this should represent a grass type like lollium ssp.
add_row(crop_cifos = "grass_arable" , proc_raw = "grass_arable" , proc_in = "grass_arable_dry", proc_out = "grass_arable_hay", value = 0.88, dietary_products = "Roughage") %>% # Timothy (Phleum pratense), hay (feedepedia)
add_row(crop_cifos = "grass_arable" , proc_raw = "grass_arable" , proc_in = "grass_arable_fresh", proc_out = "grass_arable_fresh", value = (1-0.86), dietary_products = "Forage and silage, grasses nes") %>% # Source: https://doi.org/10.1111/j.1469-8137.1994.tb04036.x - I take the upper bound
add_row(crop_cifos = "grass_arable" , proc_raw = "grass_arable" , proc_in = "grass_arable_silage", proc_out = "grass_arable_silage", value = 0.308, dietary_products = "Roughage") %>% #, silage (feedepedia)
## grass_pasture - Source: https://www.feedipedia.org/node/16886; Surrogate specie: Timothy grass (Phleum pratense)
add_row(crop_cifos = "grass_pasture" , proc_raw = "grass_pasture" , proc_in = "grass_pasture_dry", proc_out = "grass_pasture_hay", value = 0.88, dietary_products = "Roughage") %>% #Timothy (Phleum pratense), hay (feedepedia)
add_row(crop_cifos = "grass_pasture" , proc_raw = "grass_pasture" , proc_in = "grass_pasture_fresh", proc_out = "grass_pasture_fresh", value = 0.27, dietary_products = "Forage and silage, grasses nes") %>% # Timothy (Phleum pratense), aerial part, fresh, (feedepedia)
add_row(crop_cifos = "grass_pasture" , proc_raw = "grass_pasture" , proc_in = "grass_pasture_silage", proc_out = "grass_pasture_silage", value = 0.308, dietary_products = "Roughage") %>% #Timothy grass (Phleum pratense) silage, (feedepedia)
## grass_rangeland -
add_row(crop_cifos = "grass_rangeland" , proc_raw = "grass_rangeland" , proc_in = "grass_rangeland_fresh", proc_out = "grass_rangeland_fresh", value = 0.30, dietary_products = "Forage and silage, grasses nes") %>% # Source: https://doi.org/10.1111/j.1469-8137.1994.tb04036.x - I take the lower bound
## alfalfafor
# grass_pasture - Source: Source: https://www.feedipedia.org/node/275
add_row(crop_cifos = "alfalfafor" , proc_raw = "alfalfafor" , proc_in = "alfalfafor_dry", proc_out = "alfalfafor_hay", value = 0.894, dietary_products = "Forage and silage, legumes") %>% #Alfalfa, hay, (feedepedia)
add_row(crop_cifos = "alfalfafor" , proc_raw = "alfalfafor" , proc_in = "alfalfafor_fresh", proc_out = "alfalfafor_fresh", value = 0.199, dietary_products = "Forage and silage, legumes") %>% #Alfalfa fresh (feedepedia)
add_row(crop_cifos = "alfalfafor" , proc_raw = "alfalfafor" , proc_in = "alfalfafor_silage", proc_out = "alfalfafor_silage", value = 0.308, dietary_products = "Forage and silage, legumes") %>% #Alfalfa, silage (feedepedia)
# cloverfor - Source: https://www.feedipedia.org/node/246
add_row(crop_cifos = "cloverfor" , proc_raw = "cloverfor" , proc_in = "cloverfor_dry", proc_out = "cloverfor_hay", value = 0.894, dietary_products = "Roughage") %>% # Alfalfa, hay, (feedepedia)
add_row(crop_cifos = "cloverfor" , proc_raw = "cloverfor" , proc_in = "cloverfor_fresh", proc_out = "cloverfor_fresh", value = 0.19, dietary_products = "Forage and silage, legumes") %>% #Red clover (Trifolium pratense), aerial part, fresh (feedepedia)
add_row(crop_cifos = "cloverfor" , proc_raw = "cloverfor" , proc_in = "cloverfor_silage", proc_out = "cloverfor_silage", value = 0.277, dietary_products = "Roughage") %>% #Red clover (Trifolium pratense), silage (feedepedia)
# ryefor - Source: https://www.feedipedia.org/node/385
# According to FAO this might relate to fast growing grass which is covered by grass already -- https://www.fao.org/es/faodef/fdef11e.htm -- RYE GRASS FOR FORAGE Italian ryegrass (Lolium multiflorum); English, perennial ryegrass (L. perenne) (feedepedia)
add_row(crop_cifos = "ryefor" , proc_raw = "ryefor" , proc_in = "ryefor_freshin", proc_out = "ryefor_fresh", value = 0.16, dietary_products = "Forage and silage, legumes") %>% # Reference: Feedipedia: Rye, aerial part, fresh (feedepedia)
add_row(crop_cifos = "ryefor" , proc_raw = "ryefor" , proc_in = "ryefor_dryin", proc_out = "ryefor_hay", value = 0.92, dietary_products = "Forage and silage, legumes") %>% # Reference: Feedipedia: Rye straw (feedepedia)
add_row(crop_cifos = "ryefor" , proc_raw = "ryefor" , proc_in = "ryefor_silage", proc_out = "ryefor_silage", value = 0.277, dietary_products = "Forage and silage, legumes") %>% # #Red clover (Trifolium pratense), silage (feedepedia)
# fornesfor
add_row(crop_cifos = "fornesfor" , proc_raw = "fornesfor_feed" , proc_in = "fornesfor_feedin", proc_out = "fornesfor_plant", value = 0.65, dietary_products = "Forage products") %>% #comes from cabbage
# beetfor - Source: https://www.feedipedia.org/node/534
add_row(crop_cifos = "beetfor" , proc_raw = "beetfor_feed" , proc_in = "beetfor_feedin", proc_out = "beetfor_leaves", value = 0.179, dietary_products = "Forage products") %>% # Beet leaves, fresh
add_row(crop_cifos = "beetfor" , proc_raw = "beetfor_feed" , proc_in = "beetfor_feedin", proc_out = "beetfor_root", value = 0.161, dietary_products = "Forage products") %>% # Beet root, fodder type, fresh
# cabbagefor
add_row(crop_cifos = "cabbagefor" , proc_raw = "cabbagefor_feed" , proc_in = "cabbagefor_feedin", proc_out = "cabbagefor_plant", value = 0.65, dietary_products = "Forage products") %>%
# carrotfor - Source: https://www.feedipedia.org/node/539
add_row(crop_cifos = "carrotfor" , proc_raw = "carrotfor_feed" , proc_in = "carrotfor_feedin", proc_out = "carrots_fresh", value = 0.107 , dietary_products = "Forage products") %>% # Beet leaves, fresh
add_row(crop_cifos = "carrotfor" , proc_raw = "carrotfor_feed" , proc_in = "carrotfor_feedin", proc_out = "carrots_tops_fresh", value = 0.164, dietary_products = "Forage products") %>% # Beet root, fodder type, fresh
# legumenesfor - Source: https://www.feedipedia.org/node/4926 --> Faba Bean taken as a proxy
# Levels: all pulses only one level
add_row(crop_cifos = "legumenesfor" , proc_raw = "legumenesfor_feed" , proc_in = "legumenesfor_feedin", proc_out = "legumenesfor_bean", value = 0.866 , dietary_products = "Forage and silage, legumes") %>% # Faba bean (Vicia faba), all cultivars
add_row(crop_cifos = "legumenesfor" , proc_raw = "legumenesfor_feed" , proc_in = "legumenesfor_feedin", proc_out = "legumenesfor_straw", value = 0.194 , dietary_products = "Forage and silage, legumes") %>% # Faba bean (Vicia faba), aerial part, fresh
# maizefor - https://www.feedipedia.org/node/13883 AND commodity tree FAO
add_row(crop_cifos = "maizefor" , proc_raw = "maize_whole_feed" , proc_in = "maize_silagein", proc_out = "maize_silage", value = 0.325, dietary_products = "Forage products") %>% # Reference: Maize silage, dry matter 30-35% from https://www.feedipedia.org/node/12871
add_row(crop_cifos = "maizefor" , proc_raw = "maize_whole_feed" , proc_in = "maize_oilin", proc_out = "maize_oil", value = 0.45*0.06, dietary_products = "Forage products") %>% # Reference: Commodidty tree fao same as with humans
add_row(crop_cifos = "maizefor" , proc_raw = "maize_whole_feed" , proc_in = "maize_oil", proc_out = "maize_cake", value = 0.52*0.06, dietary_products = "Forage products") %>% # Reference: Commodidty tree fao same as with humans
# oilseedfor - from Commodity tree (Soyabeans taken as a proxy)
add_row(crop_cifos = "oilseedfor" , proc_raw = "oilseedfor" , proc_in = "oilseedfor_for_oil", proc_out = "oilseedfor_for_oil", value = 0.19, dietary_products = "Forage products") %>% # Reference: Soyabean tcf
add_row(crop_cifos = "oilseedfor" , proc_raw = "oilseedfor" , proc_in = "oilseedfor_for_oil", proc_out = "oilseedfor_cake", value = 0.71, dietary_products = "Forage products") %>% # Reference:Soyabean tcf
add_row(crop_cifos = "oilseedfor" , proc_raw = "oilseedfor" , proc_in = "oilseedfor_for_oil", proc_out = "oilseedfor_hulls", value = 0.07, dietary_products = "Forage products") %>% # Reference: Soyabean tcf
# swedefor - https://www.feedipedia.org/node/534
add_row(crop_cifos = "swedefor" , proc_raw = "swedefor_feed" , proc_in = "swedefor_feedin", proc_out = "swedefor_leave", value = 0.179, dietary_products = "Forage products") %>% # Beet leaves, fresh
add_row(crop_cifos = "swedefor" , proc_raw = "swedefor_feed" , proc_in = "swedefor_feedin", proc_out = "swedefor_root", value = 0.161, dietary_products = "Forage products") %>% # Beet root, fodder type, fresh
# turnipfor - https://www.feedipedia.org/node/534
add_row(crop_cifos = "turnipfor" , proc_raw = "turnipfor_feed" , proc_in = "turnipfor_feedin", proc_out = "turnipfor_leave", value = 0.179, dietary_products = "Forage products") %>% # Beet leaves, fresh
add_row(crop_cifos = "turnipfor" , proc_raw = "turnipfor_feed" , proc_in = "turnipfor_feedin", proc_out = "turnipfor_root", value = 0.161, dietary_products = "Forage products") %>% # Beet root, fodder type, fresh
# vegfor
add_row(crop_cifos = "vegfor" , proc_raw = "vegfor_feed" , proc_in = "vegfor_feedin", proc_out = "vegfor_whole", value = 0.65, dietary_products = "Forage products") %>%
# Here I change the existing processing products that are not according to FAO tcf document
# Barley from fao tcf document
add_row(crop_cifos = "barley" , proc_raw = "barley" , proc_in = "barley_for_pearlin", proc_out = "barley_pearl", value = 0.72*0.55, dietary_products = "Barley and products") %>% #
add_row(crop_cifos = "barley" , proc_raw = "barley" , proc_in = "barley_for_pearlin", proc_out = "barley_flour", value = 0.72*.45, dietary_products = "Barley and products") %>% #
add_row(crop_cifos = "barley" , proc_raw = "barley" , proc_in = "barley_for_pearlin", proc_out = "barley_bran", value = 0.19, dietary_products = "Barley and products") %>% #
add_row(crop_cifos = "barley" , proc_raw = "barley" , proc_in = "barley_for_pearlin", proc_out = "barley_hulls", value = 0.07, dietary_products = "Barley and products") %>% #
# add_row(crop_cifos = "barley" , proc_raw = "barley" , proc_in = "barley_for_malt", proc_out = "barley_maltculms", value = 0.24, dietary_products = "Barley and products") %>% #
add_row(crop_cifos = "barley" , proc_raw = "barley" , proc_in = "barley_for_malt", proc_out = "barley_malt", value = 0.73, dietary_products = "Barley and products") %>% #
# add_row(crop_cifos = "barley" , proc_raw = "barley_malt" , proc_in = "for_beer", proc_out = "brewers_grain", value = 8, dietary_products = "Barley and products") %>% #
add_row(crop_cifos = "barley" , proc_raw = "barley_malt" , proc_in = "for_beer", proc_out = "barley_beer", value = 8*0.8, dietary_products = "Barley and products") %>% #
# Barley for feed
add_row(crop_cifos = "barley" , proc_raw = "barley_malt" , proc_in = "barley_feed", proc_out = "grain_barley", value = 0.98, dietary_products = "Barley and products") %>% #
#Wheat- tcf table
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_for_wholemeal", proc_out = "wheat_wholemeal", value = 0.85, dietary_products = "Wheat and products") %>%
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_for_wholemeal", proc_out = "wheat_wholemeal_germ", value = 0.01, dietary_products = "Wheat and products") %>%
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_for_wholemeal", proc_out = "wheat_feedmeal", value = 0.02, dietary_products = "Wheat and products") %>% #
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_flour", proc_out = "wheat_germ", value = 0.02, dietary_products = "Wheat and products") %>% #ref: slightly adjusted from tcf FAO so that it adds up to 88% DM
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_flour", proc_out = "wheat_flour", value = 0.75, dietary_products = "Wheat and products") %>%
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_flour", proc_out = "wheat_branh", value = 0.11, dietary_products = "Wheat and products") %>%
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_feed", proc_out = "grain_wheat", value = 0.88, dietary_products = "Wheat and products") %>% #wheat harvested ca 12 %DM
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_flourba", proc_out = "wheat_flour", value = 0.73, dietary_products = "Wheat and products") %>%
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_flourba", proc_out = "wheat_feedmeal", value = 0.02, dietary_products = "Wheat and products") %>%
add_row(crop_cifos = "wheat" , proc_raw = "wheat" , proc_in = "wheat_flourba", proc_out = "wheat_brana", value = 0.12, dietary_products = "Wheat and products") %>% #
# Rapeseed- tcf table
add_row(crop_cifos = "rapeseed" , proc_raw = "rapeseed" , proc_in = "rapeseed_oil", proc_out = "rapeseed_oil", value = 0.38, dietary_products = "Rape and Mustard Oil") %>%
add_row(crop_cifos = "rapeseed" , proc_raw = "rapeseed" , proc_in = "rapeseed_oil", proc_out = "rapeseed_cake", value = 0.6, dietary_products = "Rape and Mustardseed") %>%
# potatoes - tcf table
add_row(crop_cifos = "potatoes" , proc_raw = "potatoes" , proc_in = "potatoes_whole", proc_out = "potatoes_dry", value = 0.17, dietary_products = "Potatoes and products") %>%
add_row(crop_cifos = "potatoes" , proc_raw = "potatoes" , proc_in = "potatoes_whole", proc_out = "tuber_peel", value = 0.02, dietary_products = "Potatoes and products") %>%
add_row(crop_cifos = "potatoes" , proc_raw = "potatoes" , proc_in = "potatoes_flour", proc_out = "potatoes_flour", value = 0.2, dietary_products = "Potatoes and products") %>%
add_row(crop_cifos = "potatoes" , proc_raw = "potatoes" , proc_in = "potatoes_flour", proc_out = "tuber_peel", value = 0.02, dietary_products = "Potatoes and products") %>%
add_row(crop_cifos = "potatoes" , proc_raw = "potatoes" , proc_in = "potatoes_starch", proc_out = "potatoes_starch", value = 0.19, dietary_products = "Potatoes and products") %>%
add_row(crop_cifos = "potatoes" , proc_raw = "potatoes" , proc_in = "potatoes_starch", proc_out = "tuber_peel", value = 0.02, dietary_products = "Potatoes and products") %>%
# Soybeans - tcf table if not otherwise stated
add_row(crop_cifos = "soybeans" , proc_raw = "soybeans" , proc_in = "soyabean_for_oil", proc_out = "soyabean_oil", value = 0.19, dietary_products = "Soyabean Oil") %>%
add_row(crop_cifos = "soybeans" , proc_raw = "soybeans" , proc_in = "soyabean_for_oil", proc_out = "soyabean_cake", value = 0.71, dietary_products = "Soyabeans") %>%
add_row(crop_cifos = "soybeans" , proc_raw = "soybeans" , proc_in = "soyabean_for_oil", proc_out = "soyabean_hulls", value = 0.07, dietary_products = "Soyabeans") %>%
add_row(crop_cifos = "soybeans" , proc_raw = "soybeans" , proc_in = "soyabean_for_table", proc_out = "soyabean_table", value = 0.71, dietary_products = "Soyabeans") %>% #ref: Ollie
add_row(crop_cifos = "soybeans" , proc_raw = "soybeans" , proc_in = "soyabean_for_table", proc_out = "soyabean_hulls", value = 0.07, dietary_products = "Soyabeans") %>% #ref: Ollie
# feed
add_row(crop_cifos = "soybeans" , proc_raw = "soybeans_feed" , proc_in = "soyabean_for_feed", proc_out = "soyabean_feed_oil", value = 0.19, dietary_products = "Soyabean Oil") %>%
add_row(crop_cifos = "soybeans" , proc_raw = "soybeans_feed" , proc_in = "soyabean_for_feed", proc_out = "soyabean_feed_cake", value = 0.71, dietary_products = "Soyabeans") %>%
add_row(crop_cifos = "soybeans" , proc_raw = "soybeans_feed" , proc_in = "soyabean_for_feed", proc_out = "soyabean_feed_hulls", value = 0.07, dietary_products = "Soyabeans") %>%
# sunflower - tcf fao
add_row(crop_cifos = "sunflower" , proc_raw = "sunflower_seed" , proc_in = "sunflower_seed", proc_out = "sunflower_oil", value = 0.41, dietary_products = "Soyabean Oil") %>%
add_row(crop_cifos = "sunflower" , proc_raw = "sunflower_seed" , proc_in = "sunflower_for_oil", proc_out = "sunflower_cake", value = 0.47, dietary_products = "Soyabeans") %>%
add_row(crop_cifos = "sunflower" , proc_raw = "sunflower_seed" , proc_in = "sunflower_for_oil", proc_out = "sunflower_hulls", value = 0.07, dietary_products = "Soyabeans") %>% #ref from ollie (old proccessing sheet)
# Paddy Rice - tcf fao
# husked rice
add_row(crop_cifos = "rice" , proc_raw = "rice" , proc_in = "rice_husk", proc_out = "rice_husked", value = 0.77, dietary_products = "Rice (Milled Equivalent)") %>%
add_row(crop_cifos = "rice" , proc_raw = "rice" , proc_in = "rice_husk", proc_out = "rice_hulls", value = 0.25, dietary_products = "Rice (Milled Equivalent)") %>%
# 2nd stage
add_row(crop_cifos = "rice" , proc_raw = "rice_husked" , proc_in = "rice_husked_milled", proc_out = "rice_husked_milled", value = 0.9, dietary_products = "Rice (Milled Equivalent)") %>%
add_row(crop_cifos = "rice" , proc_raw = "rice_husked" , proc_in = "rice_husked_milled", proc_out = "rice_bran", value = 0.15, dietary_products = "Rice (Milled Equivalent)") %>%
# Milled paddy rice
add_row(crop_cifos = "rice" , proc_raw = "rice" , proc_in = "rice_paddy_milled", proc_out = "rice_paddy_milled", value = 0.67, dietary_products = "Rice (Milled Equivalent)") %>%
add_row(crop_cifos = "rice" , proc_raw = "rice" , proc_in = "rice_paddy_milled", proc_out = "hulls_paddy_milled", value = 0.25, dietary_products = "Rice (Milled Equivalent)") %>%
add_row(crop_cifos = "rice" , proc_raw = "rice" , proc_in = "rice_paddy_milled", proc_out = "bran_paddy_milled", value = 0.8, dietary_products = "Rice (Milled Equivalent)") %>%
# 2nd stage for bran oil/cake
add_row(crop_cifos = "rice" , proc_raw = "bran_paddy_milled" , proc_in = "rice_bran_oil", proc_out = "rice_bran_oil", value = 0.80, dietary_products = "Ricebran Oil") %>%
add_row(crop_cifos = "rice" , proc_raw = "bran_paddy_milled" , proc_in = "rice_bran_oil", proc_out = "rice_bran_cake", value = 0.14, dietary_products = "Ricebran Oil") %>%
# coffee - feedepedia -> https://www.feedipedia.org/node/549
add_row(crop_cifos = "arabica_coffee" , proc_raw = "coffee_green" , proc_in = "coffee_green", proc_out = "coffee_roasted", value = 0.8, dietary_products = "Coffee and products") %>%
add_row(crop_cifos = "arabica_coffee" , proc_raw = "coffee_green" , proc_in = "coffee_green", proc_out = "coffee_hulls", value = 0.2, dietary_products = "Cocoa Beans and products") %>%#fraction comes from the cocoa husk. Could be improbved
# Sesame
add_row(crop_cifos = "sesame" , proc_raw = "sesame" , proc_in = "sesame_seed", proc_out = "sesame_oil", value = 0.42, dietary_products = "Sesameseed Oil") %>% #ref from old processing sheet
add_row(crop_cifos = "sesame" , proc_raw = "sesame" , proc_in = "sesame_seed", proc_out = "sesame_cake", value = 0.57, dietary_products = "Sesame seed") %>%
# Banana
add_row(crop_cifos = "bananas" , proc_raw = "bananas" , proc_in = "bananas", proc_out = "bananas", value = 1, dietary_products = "Bananas") %>% #ref from old processing sheet
# Sugar beets - tcf fao
add_row(crop_cifos = "sugar_beet" , proc_raw = "sugar_beet" , proc_in = "for_sugar_refined", proc_out = "sugarbeet_toptails", value = 0.1, dietary_products = "Sugar beet") %>% #no reference
add_row(crop_cifos = "sugar_beet" , proc_raw = "sugar_beet" , proc_in = "for_sugar_refined", proc_out = "sugarbeet_pulp", value = 0.07, dietary_products = "Sugar beet") %>%
add_row(crop_cifos = "sugar_beet" , proc_raw = "sugar_beet" , proc_in = "for_sugar_refined", proc_out = "sugarbeet_molasses", value = 0.04, dietary_products = "Sugar beet") %>%
add_row(crop_cifos = "sugar_beet" , proc_raw = "sugar_beet" , proc_in = "for_sugar_refined", proc_out = "sugar_refined", value = 0.935*0.14, dietary_products = "Sugar (Raw Equivalent)") %>%
# Treenuts
add_row(crop_cifos = "treenuts" , proc_raw = "walnuts" , proc_in = "walnuts", proc_out = "walnuts", value = 0.04, dietary_products = "Nuts and products") %>%
add_row(crop_cifos = "treenuts" , proc_raw = "walnuts" , proc_in = "walnuts", proc_out = "nut_shell", value = 0.04, dietary_products = "Nuts and products")
# Pulling crops that are updated
vec_proc_new = proc_new %>% distinct_at(vars(crop_cifos)) %>% pull(crop_cifos)
# # Anti joim
# dat_proc_old = dat_complete %>% anti_join(., vec_proc_new)
#
# Creating the final processing sheet
dat_proc_new = dat_complete %>%
dplyr::filter(!crop_cifos %in% vec_proc_new,
!proc_out == "sugarbeet_toptails") %>%
bind_rows(.,proc_new) %>%
mutate(dietary_products = ifelse(proc_out == "Sugar_raw" & proc_raw == "Sugar beets" |
proc_out == "sugar_raw" & proc_raw == "sugar_cane",
"Sugar (Raw Equivalent)", dietary_products)) %>%
dplyr::mutate(across(c("crop_cifos":"proc_out"), tolower)) %>%
dplyr::mutate(proc_raw = gsub("\\,", "", proc_raw),
proc_raw = gsub(" ", "_", proc_raw),
proc_raw = case_when(
proc_raw %in% (dat_proc_new %>% pull(proc_out)) &
proc_raw != proc_out~ proc_raw,
TRUE ~ crop_cifos))
dat_proc_new %>% write_csv("Input_data/dat_proc_new.csv")
# dat = read_csv("Input_data/dat_proc_new.csv")
# Adding the animal part to the processing
# Downloading the FAO stat Food balance sheet
# FoodBalanceSheetFAO = get_faostat_bulk("FBS", "Input_data") #downloads the data bulk from faostat
# FoodBalanceSheetFAO
dat_proc_asf =
Processing_sheet %>% dplyr::select(-c(6,7)) %>%
clean_names() %>% rename(proc_raw = pro_raw) %>%
slice(269:363) %>%
dplyr::mutate(dietary_products= case_when(proc_raw == "Milk" ~ "Milk - Excluding Butter",
TRUE ~ dietary_products),
dietary_products= case_when(proc_out == "Butter" ~ "Butter, Ghee",
TRUE ~ dietary_products),
dietary_products= case_when(dietary_products == "Fish (Calculated CiFoS)" ~ "Fish, Seafood",
TRUE ~ dietary_products),
proc_out = case_when(proc_out == "Butter_Milk" ~ "Butter_milk",
TRUE ~ proc_out)) #this was written with a uppercase here and a lower case in the food losses sheet
Processing_sheet_final = bind_rows(dat_proc_new %>% dplyr::select(-crop_cifos),dat_proc_asf)
write_csv(Processing_sheet_final, "Input_data/processing_sheet.csv")
# Human nutrition sheet ---------------------------------------------------
# Human nutrtion sheet
dat_humnutr = read_excel("Input_data/Copy of European_CiFoS_model_data_ANITANov21.xlsx", sheet = "Human_Nutr")
# Checking what is missing in the humann nutrition shheet so that we can add what is missing from the RIVM sheet
dat_humnutr_cifos = dat_humnutr %>% janitor::row_to_names(2) %>% janitor::clean_names() %>%
dplyr::filter(!family %in% c("Dairy", "Fish", "Meat", "Egg")) %>% mutate(product_lc = tolower(product))
# write_csv(dat_humnutr_cifos, "Input_data/dat_humnutr_cifos.csv")
dat_humnutr_cifos %>%
dplyr::select(c(4:5), product_lc) %>%
right_join(., (dat_proc_newdat_humnutr_cifos),
by = c("product_lc"="proc_out")) %>%
dplyr::filter(is.na(product)) %>%
dplyr::anti_join(., dat_procout_demi, by = c("product_lc"="product")) %>%
dplyr::anti_join(.,dat_map_old_new_procout,by = c("product"="new_procout"))
# write_csv(proc_out_new, "Input_data/proc_out_new.csv")
# Checking the overlap of updated processing sheet with demis nutritional sheet
dat_procout_demi = read_csv("Input_data/demi_human_food.csv") %>%
filter(!product=="g" &
!product =="barley_maltculms") %>%
dplyr::select(c(4:5), product)
dat_procout_to_find_demi = dat_procout_all %>% dplyr::filter(is.na(original_id)) %>%# this needs to be checked for in the old human nutrition sheet
write_csv("Input_data/humNutr_demitofind.csv")
# Manual Mapping Human Nutrition ------------------------------------------
# Careful -- Manual mapping -- Which procout is in the old human nutrition sheet that was not detected by the join above. Also mapping for non-human food procouts
dat_map_old_new_procout =
read_csv("Input_data/map_old_new_procout_2.csv") %>%
dplyr::filter(food_cat == "food" & is.na(old_procout))
# These prcouts are neither in the old processing sheet nor in demis sheet
proc_out_missing =
dat_proc_new %>% dplyr::select(proc_out, dietary_products) %>%
dplyr::left_join(., dat_humnutr_cifos %>% select(product_lc, product) , by = c("proc_out" ="product_lc")) %>%
dplyr::left_join(.,dat_map_old_new_procout,by = c("proc_out"="new_procout")) %>%
dplyr::left_join(., dat_procout_demi, by = c("proc_out"="product")) %>%
dplyr::filter(is.na(original_id)) %>%
# dplyr::filter(!is.na(dietary_products)) %>%
dplyr::filter(food_cat == "food") %>%
distinct_at(vars(proc_out))
# new procout added from demi's sheet
# Food waste crops
food_psf_new = read_csv("Input_data/food_sheet_demi_distinct.csv") %>%
slice(-1) %>%
dplyr::select(-c(2,3,4,41)) %>%
rename(na_2 = `na...19`,
na = `na...5`) %>%
type.convert() %>%
mutate(epa = as.numeric(epa),
dha = as.numeric(dha ),
cholestrol = as.numeric(cholestrol ),
i =as.numeric(i),
a = as.numeric(a) ,
b12 = as.numeric(b12),
d = as.numeric(d),
e = as.numeric(e),
vit_k = as.numeric(vit_k)) %>%
drop_na(product) %>%
filter(!product == "groundnut_shelled") %>%
select(-raw_cooked , -na)
vec_food_new = food_psf_new %>% pull(product)
# These are the procouts from the old sheet that we matched the new procouts
food_old_match =
read_csv("Input_data/map_old_new_procout_2.csv") %>%
dplyr::filter(food_cat == "food" & !is.na(old_procout)) %>%
left_join(dat_humnutr_cifos, by = c("old_procout"="product"))%>%
type.convert() %>%
group_by(new_procout) %>%
summarise_if(is.numeric, mean, na.rm=T ) %>%
mutate(raw_nevo = "agg",
cooked_nevo = "agg",
na = "Food",
family = "NA",
product = new_procout) %>%
relocate(product, .before = "weight") %>%
relocate(family, .before = "product") %>%
relocate( na, .before = "family") %>%
relocate(cooked_nevo, .before = "na") %>%
relocate(raw_nevo, .before = "cooked_nevo") %>%
select(-new_procout,-family , -na,-raw_nevo ,-cooked_nevo) %>%
filter(!product %in% vec_food_new)
# procout asf
food_asf = dat_humnutr %>% janitor::row_to_names(2) %>% janitor::clean_names() %>%
dplyr::filter(family %in% c("Dairy", "Fish", "Meat", "Egg")) %>%
mutate(product_lc = tolower(product)) %>%
type.convert() %>%
select(-product_lc,-family , -na, -cooked_nevo, -raw_nevo)
# Combining all dfs
hum_nutr_all = bind_rows(food_old_match, food_psf_new, food_asf)
# check = full_join(hum_nutr_all, proc_new, by = c("product"="proc_out"))
write_csv(hum_nutr_all, "Input_data/hum_nutr_all.csv")
# Animal nutrition new ----------------------------------------------------
# Cifos sheet
dat_animnutr = readxl::read_excel("Input_data/Copy of European_CiFoS_model_data_ANITANov21.xlsx", sheet = "Animal_Nutr")
# %>% janitor::row_to_names(1)
# Which procouts are needed?
# Checking what is missing in the humann nutrition shheet so that we can add what is missing from the RIVM sheet
dat_animal_nutr_cifos = dat_animnutr %>%
janitor::row_to_names(1) %>%
janitor::clean_names() %>%
mutate(product_lc = tolower(product)) %>%
relocate(product_lc, .before = "product")
dat_animal_nutr_cifos %>% colnames(.) %>% as_tibble() %>%
write_csv("Input_data/dat_animal_cifos.csv")
dat_miss_animal = dat_animal_nutr_cifos %>%
# dplyr::select(c(4:5), product_lc) %>%
right_join(., (dat_proc_new %>% dplyr::select(proc_out, dietary_products)),
by = c("product_lc"="proc_out"))%>%
dplyr::filter(is.na(product))
# Substract the procouts that are already in the old animalnutrient file
# Manual mapping: Which crops that are missing in the join above are already in the old animal nutrition sheet?
# File used as input:
# write_csv(dat_miss_animal %>% dplyr::select(product_lc, product), "Input_data/dat_miss_animal.csv")
mapd_animnutr_missing = read_csv("Input_data/dat_miss_animal_out_mapd.csv")
# Missing animal procouts that need to be added from various sources
proc_out_anim_miss_tbl = mapd_animnutr_missing %>%
dplyr::filter(feed %in% c("feed", "grass") &
is.na(proc_out_old_animsheet)) %>%
dplyr::select(-proc_out_old_animsheet)
proc_out_anim_miss_vec = proc_out_anim_miss_tbl %>% pull(proc_out_new_missing)
# Function that does all the foratting, cacluation and extraction of the cvb data from downloaded excel files
FunAnimDatExtract = function(dat, cvb_code, cvb_name, product){
# function that subsets the cvb data sheets based on the row headers (caution: indexed subsetting did not work due to differences in rownumbers between sheets)
FunSubsetCVB = function(dat, char_upper, char_lower, suffix_char=NULL){
table_subset = cvb_table[which.max(cvb_table$nutrient == char_upper) : which.max(cvb_table$nutrient == char_lower), ,drop = FALSE]
table_subset = table_subset %>% dplyr::filter(nutrient != char_lower & nutrient != char_upper)
table_subset = table_subset %>% mutate(nutrient= paste(nutrient, suffix_char, sep = "")) %>% dplyr::filter(!unit == "kcal/kg - in DM")
return(table_subset)
}
# cvb_table = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 23 57 PM.xlsx", col_names = F) #%>%
cvb_table = dat %>% rename(nutrient = ...1,
fresh = ...2,
dm = ...3,
unit = ...4) %>%
filter(if_any(everything(), ~ !is.na(.)))
# Creating the subsets
weende = FunSubsetCVB(dat = cvb_table, char_upper = "Weende analysis", char_lower = "Minerals and trace elements", suffix_char = NULL)
mineral = FunSubsetCVB(dat = cvb_table, char_upper = "Minerals and trace elements", char_lower = "Fermentation products", suffix_char = NULL)
ferment = FunSubsetCVB(dat = cvb_table, char_upper = "Fermentation products", char_lower = "Digestibility coefficients ruminants", suffix_char = NULL)
digest_rum = FunSubsetCVB(dat = cvb_table, char_upper = "Digestibility coefficients ruminants", char_lower = "Digestibility coefficients pigs", suffix_char = "r")
digest_rum2 = FunSubsetCVB(dat = cvb_table, char_upper = "DVE/OEB 2007", char_lower = "Feeding values ruminants", suffix_char = "r")
digest_pig = FunSubsetCVB(dat = cvb_table, char_upper = "Digestibility coefficients pigs", char_lower = "Digestibility coefficients roosters and laying hens",suffix_char = "p")
digest_lay = FunSubsetCVB(dat = cvb_table, char_upper = "Digestibility coefficients roosters and laying hens", char_lower = "Digestibility coefficients broilers",suffix_char = "l")
digest_bro = FunSubsetCVB(dat = cvb_table, char_upper = "Digestibility coefficients broilers", char_lower = "Digestibility coefficients rabbits", suffix_char = "b")
feeding_rum = FunSubsetCVB(dat = cvb_table, char_upper = "Feeding values ruminants", char_lower = "Feeding values rabbits", suffix_char = "r")
feeding_lay = FunSubsetCVB(dat = cvb_table, char_upper = "Feeding values roosters/laying hens", char_lower = "Feeding values broilers", suffix_char = "l")
feeding_bro = FunSubsetCVB(dat = cvb_table, char_upper = "Feeding values roosters/laying hens", char_lower = "Feeding values broilers", suffix_char = "b")
feeding_bro = FunSubsetCVB(dat = cvb_table, char_upper = "Feeding values broilers", char_lower = "Feeding values pigs", suffix_char = "b")
feeding_pig = FunSubsetCVB(dat = cvb_table, char_upper = "Feeding values pigs", char_lower = "Standardized digestibility coefficients amino acids pigs", suffix_char = "p")
amino_acids_pigs = FunSubsetCVB(dat = cvb_table, char_upper = "Standardized digestible amino acid contents pigs", char_lower = "Apparent digestible amino acid contents pigs", suffix_char = "p")
amino_acids_bro = FunSubsetCVB(dat = cvb_table, char_upper = "Standardized digestible amino acid contents poultry", char_lower = "Fatty acids", suffix_char = "b")
amino_acids_lay = FunSubsetCVB(dat = cvb_table, char_upper = "Standardized digestible amino acid contents poultry", char_lower = "Fatty acids", suffix_char = "l")
# Combining the data
dat_comb_cvb = bind_rows(weende,mineral,ferment,digest_rum,digest_rum2, digest_pig,digest_lay,digest_bro,
feeding_rum, feeding_lay,feeding_bro,feeding_pig,amino_acids_pigs,amino_acids_bro,amino_acids_lay)
# matching the data
dat_cvb_final =
read_csv("Input_data/dat_animal_cifos_cvb_map.csv") %>%
dplyr::select(c(1:4)) %>%
dplyr::left_join(dat_comb_cvb, by = c("adj_col_cvb"="nutrient"))%>%
dplyr::rename(
content = dm,
unit = unit,
nutrient = cifos_cols) %>%
dplyr::select(nutrient,content) %>%
tidyr::pivot_wider(names_from = nutrient,
values_from = content) %>%
dplyr::mutate(cvb_code = !!cvb_code,
cvb_name = !!cvb_name,
product = !!product) %>%
relocate(cvb_name, .after = cvb_code) %>%
relocate(cvb_code, .before = DM) %>%
relocate(cvb_name, .after = cvb_code) %>%
relocate(product, .after = cvb_name) %>%
clean_names() %>%
dplyr::mutate(origin = "co-product",
family = NA) %>%
relocate(origin, .before = product) %>%
relocate(family, .before = 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)),
# #[F.H12] ME (kJ/kg) from cvb feed table 2018
# me = case_when(
# sug > 80 ~ round((15.90 * dcp + 37.66 * dcfat + 13.81 * dcf + 14.64 *dnfe - 0.63 * sug)/1000,1),
# sug <= 80 ~ round((15.90 * dcp + 37.66 * dcfat + 13.81 * dcf + 14.64 *dnfe - 0.63)/1000,1)),
#
# Calculating nitrogen from protein
n = cp/6.25)
}
# Extract and format from cvb feed calculator: https://vvdb.cvbdiervoeding.nl/Manage/Tools/VwCalc.aspx
{
soyabean_hulls = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 23 57 PM.xlsx", col_names = F) %>% #CF 320-360 g/kg
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "soyabean_hulls")
soyabean_feed_hulls = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 23 57 PM.xlsx", col_names = F) %>% #CF 320-360 g/kg
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "soyabean_feed_hulls")
coconuts_cake_copra = read_xlsx("Input_data/CVB_procout/Copra cake (3015.401)_12_15_2021 6 35 06 PM.xlsx", col_names = F) %>% #CFAT > 100g/kg
FunAnimDatExtract(cvb_code = "3015.401" ,
cvb_name = "Copra cake",
product = "coconuts_cake_copra")
cow_peas_bran = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 44 56 PM.xlsx", col_names = F) %>% #CF 320-360 g/kg
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "cow_peas_dry_bran")
pearl_millet_bran = read_excel("Input_data/CVB_procout/Rice bran meal, solvent extracted (1003.416).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1003.416" ,
cvb_name = "Rice bran meal",
product = "pearl_millet_bran")
oil_palm_kernels_cake = read_xlsx("Input_data/CVB_procout/Palm kernel expeller (3001.401)_12_15_2021 6 54 41 PM.xlsx", col_names = F) %>% #CF >180 g/kg
FunAnimDatExtract(cvb_code = "3001.401" ,
cvb_name = "Palm kernel expeller",
product = "oil_palm_kernels_cake")
sorghum_bran = read_xlsx("Input_data/CVB_procout/Rice bran meal, solvent extracted (1003.416).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1003.416" ,
cvb_name = "Rice bran meal",
product = "sorghum_bran")
bagasse = read_xlsx("Input_data/CVB_procout/Sugarbeet pulp, pressed, ensiled (4004.244).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4004.244" ,
cvb_name = "Sugarbeet pulp",
product = "sugarcane_bagasse")
chickpea_bran = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 44 56 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "chickpea_bran")
beans_dry_bran =read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 44 56 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "beans_dry_bran")
other_pulses_bran = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 44 56 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "other_pulses_bran")
lentils_bran = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 44 56 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "lentils_bran")
pigeon_peas_bran = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 44 56 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "pigeon_peas_bran")
cow_peas_dry_bran = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 44 56 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "cow_peas_dry_bran")
groundnut_cake = read_xlsx("Input_data/CVB_procout/Groundnut expeller (2013.401).xlsx", col_names = F) %>% #partly dehulled CF75 - 145 g/kg
FunAnimDatExtract(cvb_code = "2013.401" ,
cvb_name = "Groundnut expeller",
product = "groundnut_cake")
# other_cereals_bran = read_xlsx("Input_data/CVB_procout/Rice bran meal, solvent extracted (1003.416).xlsx", col_names = F) %>%
# FunAnimDatExtract(cvb_code = "1003.416" ,
# cvb_name = "Rice bran meal",
# product = "other_cereals_bran")
olive_cake = read_xlsx("Input_data/CVB_procout/Sunflower seed meal, solvent extracted (3003.407).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "3003.407" ,
cvb_name = "Sunflower seed meal, solvent extracted",
product = "olive_cake")
maize_bran = read_xlsx("Input_data/CVB_procout/Maize bran (1002.108).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1002.108" ,
cvb_name = "Maize bran",
product = "maize_bran")
maize_cake = read_xlsx("Input_data/CVB_procout/Maize germs expeller (1002.417).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1002.417" ,
cvb_name = "Maize germs expeller",
product = "maize_cake")
maize_silage = read_xlsx("Input_data/CVB_procout/Maize silage (5008.602).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5008.602" ,
cvb_name = "Maize silage",
product = "maize_silage")
grass_rangeland_fresh = read_xlsx("Input_data/CVB_procout/Grass hay, a) poor quality (5010.701).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.701" ,
cvb_name = "Grass hay, a) poor quality",
product = "grass_rangeland_fresh")
grass_pasture_fresh = read_xlsx("Input_data/CVB_procout/Grass hay, b) average quality (5010.702).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.702" ,
cvb_name = "Grass hay, b) average quality",
product = "grass_pasture_fresh")
grass_arable_fresh = read_xlsx("Input_data/CVB_procout/Grass hay, c) good quality (5010.703).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.703" ,
cvb_name = "Grass hay, c) good quality",
product = "grass_arable_fresh")
alfalfafor_fresh = read_xlsx("Input_data/CVB_procout/Lucerne (alfalfa), hay (5004.606).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5004.606" ,
cvb_name = "Lucerne (alfalfa), hay",
product = "alfalfafor_fresh")
cloverfor_fresh = read_xlsx("Input_data/CVB_procout/Clover red, hay (5003.606).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5003.606" ,
cvb_name = "Clover red, hay",
product = "cloverfor_fresh")
beetfor_leaves = read_xlsx("Input_data/CVB_procout/Sugarbeet leaves, fresh (4004.642).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4004.642" ,
cvb_name = "Sugarbeet leaves, fresh",
product = "beetfor_leaves")
beetfor_root = read_xlsx("Input_data/CVB_procout/Fodderbeets, fresh (4005.000).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4005.000" ,
cvb_name = "Fodderbeets, fresh",
product = "beetfor_root")
cabbagefor_plant = read_xlsx("Input_data/CVB_procout/Cabbage (red_white_sav.), fresh (6023.000).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "6023.000" ,
cvb_name = "Cabbage (red_white_sav.), fresh",
product = "cabbagefor_plant")
# carrots_fresh = read_xlsx("Input_data/CVB_procout/Carrots (4006.000).xlsx", col_names = F) %>%
# FunAnimDatExtract(cvb_code = "4006.000" ,
# cvb_name = "Carrots",
# product = "carrots_fresh")
carrots_tops_fresh = read_xlsx("Input_data/CVB_procout/Sugarbeet leaves with tops, fresh (4004.647).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4004.647" ,
cvb_name = "Sugarbeet leaves with tops, fresh",
product = "carrots_tops_fresh")
turnipfor_leave = read_xlsx("Input_data/CVB_procout/Sugarbeet leaves, fresh (4004.642).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4004.642" ,
cvb_name = "Sugarbeet leaves, fresh",
product = "turnipfor_leave")
turnipfor_root = read_xlsx("Input_data/CVB_procout/Cabbage (turnip cabbage), fresh (4012.000).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4012.000" ,
cvb_name = "Cabbage (turnip cabbage), fresh",
product = "turnipfor_root")
swedefor_leave = read_xlsx("Input_data/CVB_procout/Sugarbeet leaves, fresh (4004.642).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4004.642" ,
cvb_name = "Sugarbeet leaves, fresh",
product = "swedefor_leave")
swedefor_root = read_xlsx("Input_data/CVB_procout/Fodderbeets, fresh (4005.000).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4005.000" ,
cvb_name = "Fodderbeets, fresh",
product = "swedefor_root")
legumenesfor_straw = read_xlsx("Input_data/CVB_procout/Bean straw (Phaseolus) (2001.508).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "2001.508" ,
cvb_name = "Bean straw (Phaseolus)",
product = "legumenesfor_straw")
# legumenesfor_bean = read_xlsx("Input_data/CVB_procout/Field beans (Vicia faba) ensiled (5001.602).xlsx", col_names = F) %>%
# FunAnimDatExtract(cvb_code = "5001.602" ,
# cvb_name = "Bean straw (Phaseolus)",
# product = "legumenesfor_bean")
# vegfor_whole = read_xlsx("Input_data/CVB_procout/Cabbage (red_white_sav.), fresh (6023.000).xlsx", col_names = F) %>%
# FunAnimDatExtract(cvb_code = "6023.000" ,
# cvb_name = "Cabbage (red_white_sav.), fresh",
# product = "vegfor_whole")
# ryefor_fresh = read_xlsx("Input_data/CVB_procout/Rye (1007.000).xlsx", col_names = F) %>%
# FunAnimDatExtract(cvb_code = "1007.000" ,
# cvb_name = "Rye",
# product = "ryefor_fresh")
fornesfor_plant =read_xlsx("Input_data/CVB_procout/Fodderbeets, fresh (4005.000).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4005.000" ,
cvb_name = "Fodderbeets, fresh",
product = "fornesfor_plant")
# Added after revision
coconuts_oil_copra = read_xlsx("Input_data/CVB_procout/Fat_oil, Coconut oil (3015.421)_1_18_2022 1 41 16 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "3015.421" ,
cvb_name = "Fat_oil, Coconut oil",
product = "coconuts_oil_copra")
cassava_starch = read_xlsx("Input_data/CVB_procout/Tapioca starch (4008.201)_1_18_2022 2 41 14 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4008.201" ,
cvb_name = "Tapioca starch",
product = "cassava_starch")
cassava_tapioca = read_xlsx("Input_data/CVB_procout/Tapioca, dried (4008.611)_1_18_2022 1 55 24 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4008.611" ,
cvb_name = "Tapioca, dried",
product = "cassava_tapioca")
cassava_dry = read_xlsx("Input_data/CVB_procout/Tapioca, dried (4008.611)_1_18_2022 1 55 24 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4008.611" ,
cvb_name = "Tapioca, dried",
product = "cassava_dry")
cassava_flour = read_xlsx("Input_data/CVB_procout/Tapioca, dried (4008.611)_1_18_2022 1 55 24 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4008.611" ,
cvb_name = "Tapioca, dried",
product = "cassava_flour")
pearl_millet_flour = read_xlsx("Input_data/CVB_procout/Millet, (pearl millet) (1013.000)_1_18_2022 2 01 23 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1013.000" ,
cvb_name = "Millet, (pearl millet)",
product = "pearl_millet_flour")
oil_palm_kernels_oil = read_xlsx("Input_data/CVB_procout/Fat_oil, Palm oil, chemically refined (3001.437).xlsx", col_names = F)%>%
FunAnimDatExtract(cvb_code = "3001.421" ,
cvb_name = "Palmkernel oil, chemically refined",
product = "oil_palm_kernels_oil")
oil_palm_fruits_oil = read_xlsx("Input_data/CVB_procout/Fat_oil, Palm oil, chemically refined (3001.437).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "3001.437" ,
cvb_name = "Palm oil, chemically refined",
product = "oil_palm_fruits_oil")
sorghum_flour = read_xlsx("Input_data/CVB_procout/Sorghum (1008.000)_1_18_2022 2 24 03 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1008.000" ,
cvb_name = "Sorghum",
product = "sorghum_flour")
sugarcane_molasse = read_xlsx("Input_data/CVB_procout/Molasses, sugarcane (7002.210).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "7002.210" ,
cvb_name = "Molasses, sugarcane",
product = "sugarcane_molasse")
sweet_potatoe_flour = read_xlsx("Input_data/CVB_procout/Sweet potatoes, dried (4007.611)_1_18_2022 2 30 17 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4007.611" ,
cvb_name = "Sweet potatoes, dried",
product = "sweet_potatoe_flour")
sweet_potatoe_starch = read_xlsx("Input_data/CVB_procout/Potato starch, dried (4001.201)_1_18_2022 2 32 03 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4001.201" ,
cvb_name = "Potato starch, dried",
product = "sweet_potatoe_starch")
beans_dry_vegetable = read_xlsx("Input_data/CVB_procout/Feed beans, heat treated (2001.616)_1_18_2022 2 56 41 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "2001.616" ,
cvb_name = "Feed beans, heat treated",
product = "beans_dry_vegetable")
other_tubers_flour = read_xlsx("Input_data/CVB_procout/Sweet potatoes, dried (4007.611)_1_18_2022 2 30 17 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4007.611" ,
cvb_name = "Sweet potatoes, dried",
product = "other_tubers_flour")
other_tubers_dry = read_xlsx("Input_data/CVB_procout/Sweet potatoes, dried (4007.611)_1_18_2022 2 30 17 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "4007.611" ,
cvb_name = "Sweet potatoes, dried",
product = "other_tubers_dry")
groundnut_oil = read_xlsx("Input_data/CVB_procout/Fat_oil, Groundnut oil (2013.421)_1_18_2022 3 08 32 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "2013.421" ,
cvb_name = "Fat_oil, Groundnut oil",
product = "groundnut_oil")
groundnut_butter = read_xlsx("Input_data/CVB_procout/Fat_oil, Groundnut oil (2013.421)_1_18_2022 3 08 32 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "2013.421" ,
cvb_name = "Fat_oil, Groundnut oil",
product = "groundnut_butter")
temperate_fruit_pulp = read_xlsx("Input_data/CVB_procout/Citrus pulp (6022.305)_1_18_2022 3 10 48 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "6022.305" ,
cvb_name = "Citrus pulp",
product = "temperate_fruit_pulp")
tropical_fruits_pulp = read_xlsx("Input_data/CVB_procout/Citrus pulp (6022.305)_1_18_2022 3 10 48 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "6022.305" ,
cvb_name = "Citrus pulp",
product = "tropical_fruits_pulp")
maize_germ = read_xlsx("Input_data/CVB_procout/Maize germs (1002.102)_1_18_2022 3 14 58 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1002.102" ,
cvb_name = "Maize germs",
product = "maize_germ")
maize_germ = read_xlsx("Input_data/CVB_procout/Maize germs (1002.102)_1_18_2022 3 14 58 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1002.102" ,
cvb_name = "Maize germs",
product = "maize_germ")
maize_oil = read_xlsx("Input_data/CVB_procout/Fat_oil, Maize oil (1002.421)_1_18_2022 3 16 25 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1002.421" ,
cvb_name = "Fat_oil, Maize oil",
product = "maize_oil")
grass_arable_hay = read_xlsx("Input_data/CVB_procout/Grass hay, c) good quality (5010.703)_1_18_2022 3 20 24 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.703" ,
cvb_name = "Grass hay, c) good quality",
product = "grass_arable_hay")
grass_arable_silage = read_xlsx("Input_data/CVB_procout/Grass silage, a) clay soil, before 21 June (5010.140).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.140" ,
cvb_name = "Grass silage, a) clay soil, before 21 June",
product = "grass_arable_silage")
grass_pasture_hay = read_xlsx("Input_data/CVB_procout/Grass hay, b) average quality (5010.702)_1_18_2022 3 24 59 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.702" ,
cvb_name = "Grass hay, b) average quality",
product = "grass_pasture_hay")
grass_pasture_silage = read_xlsx("Input_data/CVB_procout/Grass silage, j) average (5010.170)_1_18_2022 3 34 20 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.170" ,
cvb_name = "Grass silage, j) average",
product = "grass_pasture_silage")
alfalfafor_silage = read_xlsx("Input_data/CVB_procout/Lucerne (alfalfa), ensiled (5004.602)_1_18_2022 3 51 44 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5004.602" ,
cvb_name = "Lucerne (alfalfa), ensiled",
product = "alfalfafor_silage")
alfalfafor_hay = read_xlsx("Input_data/CVB_procout/Lucerne (alfalfa), hay (5004.606)_1_18_2022 3 51 06 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5004.606" ,
cvb_name = "Lucerne (alfalfa), hay",
product = "alfalfafor_hay")
cloverfor_hay = read_xlsx("Input_data/CVB_procout/Clover red, hay (5003.606)_1_18_2022 3 52 43 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5003.606" ,
cvb_name = "Clover red, hay",
product = "cloverfor_hay")
cloverfor_silage= read_xlsx("Input_data/CVB_procout/Clover red, ensiled (5003.602)_1_18_2022 3 53 06 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5003.602" ,
cvb_name = "Clover red, ensiled",
product = "cloverfor_silage")
cloverfor_silage= read_xlsx("Input_data/CVB_procout/Clover red, ensiled (5003.602)_1_18_2022 3 53 06 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5003.602" ,
cvb_name = "Clover red, ensiled",
product = "cloverfor_silage")
wheat_wholemeal_germ= read_xlsx("Input_data/CVB_procout/Wheat germs (1010.102)_1_18_2022 4 10 25 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "1010.102" ,
cvb_name = "Wheat germs",
product = "wheat_wholemeal_germ")
oilseedfor_hulls = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 23 57 PM.xlsx", col_names = F) %>% #CF 320-360 g/kg
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "oilseedfor_hulls")
barley_hulls = read_xlsx("Input_data/CVB_procout/Oats husk meal (1004.111)_1_18_2022 4 13 11 PM.xlsx", col_names = F) %>% #CF 320-360 g/kg
FunAnimDatExtract(cvb_code = "1004.111" ,
cvb_name = "Oats husk meal",
product = "barley_hulls")
other_pulses_bran = read_xlsx("Input_data/CVB_procout/Soya bean hulls (3012.505)_12_15_2021 6 23 57 PM.xlsx", col_names = F) %>% #CF 320-360 g/kg
FunAnimDatExtract(cvb_code = "3012.505" ,
cvb_name = "Soya bean hulls",
product = "other_pulses_bran")
# Grass from monfreda
ryefor_fresh = read_xlsx("Input_data/CVB_procout/Grass hay, c) good quality (5010.703).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.703" ,
cvb_name = "Grass hay, c) good quality",
product = "ryefor_fresh")
ryefor_silage = read_xlsx("Input_data/CVB_procout/Grass silage, a) clay soil, before 21 June (5010.140).xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.140" ,
cvb_name = "Grass silage, a) clay soil, before 21 June",
product = "ryefor_silage")
ryefor_dry = read_xlsx("Input_data/CVB_procout/Grass hay, c) good quality (5010.703)_1_18_2022 3 20 24 PM.xlsx", col_names = F) %>%
FunAnimDatExtract(cvb_code = "5010.703" ,
cvb_name = "Grass hay, c) good quality",
product = "ryefor_hay")
}
# Combining all feeds
dat_anim = bind_rows(soyabean_hulls, coconuts_cake_copra, cow_peas_bran, pearl_millet_bran,
oil_palm_kernels_cake,sorghum_bran, bagasse,chickpea_bran,
beans_dry_bran,lentils_bran, pigeon_peas_bran, cow_peas_dry_bran, groundnut_cake,
# other_cereals_bran,
olive_cake, maize_bran, maize_cake,maize_silage, grass_rangeland_fresh,
grass_pasture_fresh,grass_arable_fresh, alfalfafor_fresh,
cloverfor_fresh, beetfor_leaves, beetfor_root, cabbagefor_plant,
# carrots_fresh,
carrots_tops_fresh,turnipfor_root,turnipfor_leave,swedefor_leave,swedefor_root, legumenesfor_straw,
#legumenesfor_bean, vegfor_whole, ryefor_fresh,
fornesfor_plant, coconuts_oil_copra, cassava_starch, cassava_tapioca,
cassava_dry, cassava_flour, pearl_millet_flour, oil_palm_kernels_oil,
oil_palm_fruits_oil,sorghum_flour, sugarcane_molasse, sweet_potatoe_flour,
sweet_potatoe_starch,beans_dry_vegetable, other_tubers_dry,
other_tubers_flour, groundnut_oil,groundnut_butter,
temperate_fruit_pulp,tropical_fruits_pulp,maize_germ,maize_oil,
grass_arable_hay, grass_arable_silage, grass_pasture_hay,grass_pasture_silage,
alfalfafor_silage, alfalfafor_hay, cloverfor_hay,cloverfor_silage,
soyabean_feed_hulls,wheat_wholemeal_germ,oilseedfor_hulls,barley_hulls,other_pulses_bran,
ryefor_fresh, ryefor_silage, ryefor_dry)
write_csv(dat_anim, "Input_Data/dat_anim.csv")
# Combining the feed crops that are still missing and the one downloaded from cvb
dat_miss_downl =
proc_out_anim_miss_tbl %>%
left_join(dat_anim, by = c("proc_out_new_missing" = "product")) %>%
filter(is.na(cvb_name)) %>%
dplyr::select(-feed) %>%
rename(product = proc_out_new_missing) %>%
relocate(product, .before = dm ) %>%
bind_rows(dat_anim,.) %>%
mutate(family = "notyet",
origin = "co-product")# %>%
# type.convert()
# Now we combine that df with the one that are in the old animal nutrition sheet
prod_vec = dat_miss_downl %>% pull(product)
dat_com_all = dat_animal_nutr_cifos %>% select(-product) %>%
rename(product = product_lc,
cvb_name = raw_nevo,
origin = na) %>%
relocate(cvb_code, .before = cvb_name) %>%
# type.convert(.)
dplyr::filter(!product %in% prod_vec) %>%
dplyr::mutate(origin = recode(origin, "Co-Product" = "co-product"))
# Copy paste the col format so the rbind works. Useful template: dfWrong[] <- mapply(FUN = as,dfWrong,sapply(dfCorrect,class),SIMPLIFY = FALSE)
dat_com_all[] <- mapply(FUN = as,dat_com_all,sapply(dat_miss_downl,class),SIMPLIFY = FALSE)
dat_comb_all = bind_rows(dat_com_all, dat_miss_downl )
# This contains all the NEW proc_outs
procnew_vec = proc_new %>% pull(proc_out)
# Co-products -------------------------------------------------------------
# Df for co-products - allprocouts for which we have data
dat_old_proc_crop_grass =
dat_animal_nutr_cifos %>%
right_join(., mapd_animnutr_missing %>%
filter(!proc_out_new_missing %in% "sugar_factorylime"),
by = c("product" = "proc_out_old_animsheet")) %>%
drop_na(product_lc) %>%
rename(origin = na) %>%
dplyr::select(-c("product_lc", "product","feed")) %>%
relocate(proc_out_new_missing, .before = "dm") %>%
rename(product = proc_out_new_missing)
# Pasting the formating
dat_old_proc_crop_grass[] <- mapply(FUN = as,dat_old_proc_crop_grass,sapply(dat_miss_downl,class),SIMPLIFY = FALSE)
dat_old_proc_crop_grass_sum =
dat_old_proc_crop_grass %>%
dplyr::group_by(raw_nevo, cvb_code , origin, family, product) %>%
dplyr::summarise_if(is.numeric, mean, na.rm = T) %>%
dplyr::mutate(origin = recode(origin, "Co-Product" = "co-product"),
origin = recode(origin, "Foodwaste" = "co-product"))
# All procouts that directly matched the new lower case procouts
dat_match_dir = dat_animal_nutr_cifos %>%
# dplyr::select(c(4:5), product_lc) %>%
right_join(., (dat_proc_new %>% dplyr::select(proc_out, dietary_products)),
by = c("product_lc"="proc_out"))%>%
dplyr::filter(!is.na(product)) %>%
dplyr::select(-c("product", "dietary_products")) %>%
dplyr::rename("product" = "product_lc") %>%
rename(origin = na) %>%
dplyr::mutate(origin = recode(origin, "Co-Product" = "co-product"),
origin = recode(origin, "Foodwaste" = "co-product"),
origin = recode(origin, "HarvestWaste" = "co-product"))
dat_match_dir[] <- mapply(FUN = as,dat_match_dir,sapply(dat_miss_downl,class),SIMPLIFY = FALSE)
# These are all the newly added procouts
dat_new_proc_crop_grass =
dat_miss_downl
# all co_products that are ASF (animal source food)
dat_fish_meat_milk = dat_animal_nutr_cifos %>%
dplyr::filter(family %in% c("Fish", "Milk", "Meat", "Egg", "Dairy")) %>%
dplyr::filter(na == "Co-Product") %>%
dplyr::select(-c("product_lc")) %>%
rename(origin = na) %>%
dplyr::mutate(origin = recode(origin, "Co-Product" = "co-product"))
dat_fish_meat_milk[] <- mapply(FUN = as,dat_fish_meat_milk,sapply(dat_miss_downl,class),SIMPLIFY = FALSE)
# Combining all the co-products
animal_coproducts = bind_rows(dat_old_proc_crop_grass_sum, dat_new_proc_crop_grass, dat_match_dir, dat_fish_meat_milk) %>%
dplyr::group_by(product) %>%
dplyr::summarise_if(is.numeric, mean, na.rm = T) %>%
dplyr::mutate(origin = "co-product",
raw_nevo = "crop_agg",
cvb_code = "crop_agg",
family = "none") %>%
relocate(product, .before = "dm") %>%
relocate(family, .before = "product") %>%
relocate(origin, .before = "family") %>%
relocate(cvb_code, .before = "origin") %>%
relocate(raw_nevo, .before = "cvb_code")
# Checking the consistency with all possible procouts
# Check consistency needded -> https://stackoverflow.com/questions/13774773/check-whether-values-in-one-data-frame-column-exist-in-a-second-data-frame
# A$C[!A$C %in% B$C] # returns all values of A$C that are NOT in B$C
animal_coproducts$product[!animal_coproducts$product %in% proc_new$proc_out]
# All new procouts are in the df
# HarvestWaste ------------------------------------------------------------
# Df for harvest waste - cvb data from every crop we have
crop_harvestwaste =
proc_new %>%
# dat_comb_all %>%
# left_join(., proc_new, by = c("product"="proc_out")) %>%
dplyr::select(-c(proc_raw, proc_in , value , dietary_products)) %>%
# distinct_at(vars(crop_cifos), .keep_all = T) %>%
left_join(., dat_comb_all , by=c("proc_out" = "product")) %>%
dplyr::group_by(crop_cifos) %>%
dplyr::summarise_if(is.numeric, mean, na.rm = T) %>%
dplyr::mutate(raw_nevo = "crop_agg",
cvb_code = "crop_agg",
origin = "harvest_waste",
family = "none",
product = crop_cifos) %>%
relocate(product, .before = "dm") %>%
relocate(family, .before = "product") %>%
relocate(origin, .before = "family") %>%
relocate(cvb_code, .before = "origin") %>%
relocate(raw_nevo, .before = "cvb_code") %>%
dplyr::select(-crop_cifos) %>%
dplyr::filter(!product %in% c("other_fibres", "seed_cotton", "tobacco",
"tea"))
# Validation: should be 59 crops minus the unedible crops: 55 crops included
# proc_new$crop_cifos[!proc_new$crop_cifos %in% crop$crop_cifos]
# proc_new$crop_cifos[!proc_new$crop_cifos %in% crop$crop_cifos]
# [1] "tea" "other_fibres" "seed_cotton" "tobacco"
# Harveste waste from ASF
asf_harvestwaste = dat_animal_nutr_cifos %>%
dplyr::filter(family %in% c("Fish", "Milk", "Meat", "Egg", "Dairy")) %>%
dplyr::filter(na == "HarvestWaste") %>%
dplyr::select(-c("product_lc")) %>%
rename(origin = na) %>%
dplyr::mutate(origin = recode(origin, "HarvestWaste" = "harvest_waste"))
# align formatting
asf_harvestwaste[] <- mapply(FUN = as,asf_harvestwaste,sapply(dat_miss_downl,class), SIMPLIFY = FALSE)
# Combining all the harvest waste
harvestwaste = bind_rows(crop_harvestwaste,asf_harvestwaste)
# FoodWaste ---------------------------------------------------------------
# Food waste crops - Food waste that matches directly with the co products from animal
foodwaste = hum_nutr_all %>%
distinct_at(vars(product), .keep_all = T)
foodwaste_vec = foodwaste %>% pull(product)
# foodwaste products that match coproducts animal
match_coprods_foodwaste = animal_coproducts %>%
dplyr::filter(product %in% foodwaste_vec) %>%
dplyr::mutate(origin = "foodwaste")
match_coprods_foodwaste[] <- mapply(FUN = as,match_coprods_foodwaste,sapply(dat_miss_downl,class), SIMPLIFY = FALSE)
# Tea
tea_food_waste =
dat_animal_nutr_cifos %>%
dplyr::filter(product %in% "Tea")%>%
dplyr::mutate(na = "foodwaste") %>%
select(-product_lc) %>%
rename(origin = na) %>%
mutate(product = recode(product, "Tea" = "tea_leave"))
tea_food_waste[] <- mapply(FUN = as,tea_food_waste,sapply(dat_miss_downl,class), SIMPLIFY = FALSE)
match_animal = dat_animal_nutr_cifos %>%
dplyr::filter(product %in% foodwaste_vec) %>%
dplyr::mutate(na = "foodwaste") %>%
select(-product_lc) %>%
rename(origin = na)
match_animal[] <- mapply(FUN = as,match_animal,sapply(dat_miss_downl,class), SIMPLIFY = FALSE)
match_rest = dat_animal_nutr_cifos %>%
dplyr::filter(product_lc %in% foodwaste_vec) %>%
dplyr::mutate(na = "foodwaste") %>%
select(-product) %>%
rename(product = product_lc)
match_rest[] <- mapply(FUN = as,match_rest,sapply(dat_miss_downl,class), SIMPLIFY = FALSE)
# Bind food waste
foodwaste_all = bind_rows(match_coprods_foodwaste,match_animal, match_rest,tea_food_waste) %>%
distinct_at(vars(product), .keep_all = T)
# Checking what is not in the coproducts
miss_foodwaste = foodwaste_all %>% full_join(.,foodwaste, by = "product")
# Full animal nutrition sheet ---------------------------------------------
animal_nutrition_all = bind_rows(harvestwaste, animal_coproducts, foodwaste_all) %>%
dplyr::select(-raw_nevo, -cvb_code, -family)
write_csv(animal_nutrition_all, "Input_data/animal_nutrition_all.csv")
read_csv("Input_data/animal_nutrition_all.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) %>%
rename(product = Prod)
loss_values = read_csv("Input_data/gusatvsson_loss_table.csv") %>%
rename(Fam_Gustavson = `...1`)
# Crops - from animal nutrition sheet (postharvest)
crop_loss = crop_harvestwaste %>% distinct_at(vars(product)) %>%
mutate(ProdCat = "crop",
product = product) %>%
relocate(product, .after = "ProdCat")%>%
distinct_at(vars(product), .keep_all = T)
# Co-product - from animal nutrition sheet
coproduct_loss = animal_coproducts %>% distinct_at(vars(product)) %>%
mutate(ProdCat = "co-product",
product = product) %>%
relocate(product, .after = "ProdCat")%>%
distinct_at(vars(product), .keep_all = T)
# Foodwaste - from Animal nutrition sheet
foodwaste_loss = foodwaste_all %>% distinct_at(vars(product)) %>%
mutate(ProdCat = "foodwaste",
product = product) %>%
relocate(product, .after = "ProdCat")%>%
distinct_at(vars(product), .keep_all = T)
# HarvestWaste
harvest_loss = crop_harvestwaste %>% distinct_at(vars(product)) %>%
mutate(ProdCat = "harvest_waste",
product = product) %>%
relocate(product, .after = "ProdCat")%>%
distinct_at(vars(product), .keep_all = T)
# Food - From human nutrtion sheet
food_loss = hum_nutr_all %>% distinct_at(vars(product)) %>%
mutate(ProdCat = "food",
product = product) %>%
relocate(product, .after = "ProdCat")%>%
distinct_at(vars(product), .keep_all = T)
other_losses = tibble(
ProdCat = "other",
product = c('flax_fiber_and_tow',
'seed_cotton_fibres',
'tobacco_leaves')
)
# Fish - from the old loss fraction sheet
fish_vec = c('Atlantic_herring',
'Atlantic_cod',
'Blue_whiting',
'Atlantic_mackerel',
'European_sprat',
'Haddock',
'Pollock',
'European_plaice',
'European_hake',
'Atlantic_horse_mackerel',
'Sandeels',
'Norway_pout',
'Norway_lobster',
'Northern_prawn',
'Ling',
'European_pilchard')
fish_loss = food_loss %>% filter(product == "alien") %>%
rbind(data.frame(product = fish_vec)) %>%
mutate(ProdCat = "fish",
product = product) %>%
relocate(product, .after = "ProdCat")%>%
distinct_at(vars(product), .keep_all = T)
# MeatMilkEggs -
milkmeategg_vec = c('Milk',
'Egg',
'Pig_LW',
'Dairy_LW',
'Beef_LW',
'Broiler_LW',
'Layer_LW',
'Salmon_LW',
'Tilapia_LW',
'Sheep_LW',
'Goat_LW')
mmegg_loss = food_loss %>% filter(product == "alien") %>%
rbind(data.frame(product = milkmeategg_vec)) %>%
mutate(ProdCat = "meatmilkeggs",
product = product) %>%
relocate(product, .after = "ProdCat")%>%
distinct_at(vars(product), .keep_all = T)
# Grass
grass_loss = proc_new %>% filter(grepl('grass', proc_out)) %>%
distinct(proc_out) %>%
mutate(ProdCat = "grass",
product = proc_out) %>%
relocate(product, .after = "ProdCat") %>%
select(-proc_out) %>%
distinct_at(vars(product), .keep_all = T)
loss_fraction_1 = bind_rows(crop_loss, coproduct_loss,foodwaste_loss,harvest_loss,
food_loss,fish_loss,mmegg_loss, grass_loss,other_losses)
# Fuzzy join
loss_frac_join = loss_fraction_1 %>% drop_na(product) %>% group_by(ProdCat) %>%
stringdist_left_join(dat_lossfrac_join %>% drop_na(product),
by = c("product"),
max_dist = 4) %>%
distinct_at(vars(ProdCat, product.x), .keep_all = T)
# write_csv(loss_frac_join, "Input_data/lossfraction_mapping_in.csv")
# MANUAL MAPPING required - I mapped the ProdFam and Fam_Gustavson from the old loss fraction sheet.
loss_frac_all = read_csv("Input_data/lossfraction_mapping_done.csv") %>%
dplyr::select(ProdCat, product.x,ProdFam,Fam_Gustavson) %>%
left_join(loss_values, by = "Fam_Gustavson") %>%
rename(Product = product.x,
Postharvest = `Postharvest handling & storage`,
ProcessingPackaging = `Processing and packaging`,
Distribution = Distribution ,
Consumption = Consumption ,
Feeding = Feeding) %>%
relocate(Product, .after = "Fam_Gustavson")
write_csv(loss_frac_all, "Input_data/loss_frac_all.csv")
# Consistency checks -----------------------------------------------------
# RULE: What is in the procout ani nutrition should be in the processing and the loss fraction sheet product
# A$C[!A$C %in% B$C] # returns all values of A$C that are NOT in B$C
# All values of animal nutrition that are not in loss fraction
animal_nutrition_all$product[!animal_nutrition_all$product %in% loss_frac_all$Product]
# NONE -->
# All values of human nutrition that are not in loss fraction
hum_nutr_all$product[!hum_nutr_all$product %in% loss_frac_all$Product]
# [1] "NONE" --> GOOD!
# All values of animal nutrition that are not in processing fraction
animal_coproducts$product[!animal_coproducts$product %in% Processing_sheet_final$proc_out]
# [1] None! Good
# All values of humanutrition that are not in processing sheet
hum_nutr_all$product[!hum_nutr_all$product %in% Processing_sheet_final$proc_out]
# None -- Good!
# All values that of processing that are not in loss fraction
Processing_sheet_final$proc_out[!Processing_sheet_final$proc_out %in% loss_frac_all$Product]
# None!
# All the values that are in the loss fraction but not in the processing
loss_frac_all$Product[!loss_frac_all$Product %in% rbind(Processing_sheet_final$proc_out, Processing_sheet_final$proc_raw)]
# NONE --> GOOOD!
# Fert_suitability sheet --------------------------------------------------
dat_fertsuitability = read_excel("Input_data/Copy of European_CiFoS_model_data_ANITANov21.xlsx", sheet = "Fert_Suitability") %>%
dplyr::rename(scenario=1,crop_cifos = 2)
table_fert_suit = dat_fertsuitability %>% distinct_at(vars(scenario), .keep_all = T) %>%
dplyr::select(-crop_cifos)
# List of all crops possible
crop_list = proc_new %>% distinct_at(vars(crop_cifos)) %>% pull()
scen_baseline = tibble(scenario = "Baseline",
crop_cifos = crop_list)
scen_circular = tibble(scenario = "Circular",
crop_cifos = crop_list)
fert_suit = bind_rows(scen_baseline, scen_circular) %>%
left_join(table_fert_suit, by= "scenario")
write_csv(fert_suit, "Input_data/fert_suitability.csv")
# Import sheet -----------------------------------------------------------
dat_ImportExport = read_excel("Input_data/Copy of European_CiFoS_model_data_ANITANov21.xlsx", sheet = "Import_Export") %>%
dplyr::select(c(1:3))
# Country map for subsetting EU
country_map_FAO_code = read.csv(here::here("Input_data", "Mappings", "dat_map_SPAM_GAUL_CIFOS_FAO.csv")) %>%
as_tibble() %>% dplyr::select(country_code_FAO, iso3_SPAM )
# EU28 - Subsetting -------------------------------------------------------
EU_iso3 = c("AUT","BEL", "BGR", "HRV", "CZE", "DNK", "EST","FIN", "FRA", "DEU", "GRC", "HUN", "IRL", "ITA","LVA",
"LTU", "LUX", "MLT", "NLD", "POL", "PRT","ROU", "SVK","SVN", "ESP", "SWE", "GBR", "CYP")
country_eu = country_map_FAO_code %>% filter(iso3_SPAM %in% EU_iso3) %>%
pull(country_code_FAO)
# country map
country_map_FAO_code_namecifos = read.csv(here::here("Input_data", "Mappings", "dat_map_SPAM_GAUL_CIFOS_FAO.csv")) %>%
as_tibble() %>% dplyr::select(country_code_FAO,name_cntr_CIFOS2021)
# Dietary products from the processing sheet
diet_prod_dist = Processing_sheet_final %>% distinct_at(vars(dietary_products))
# Downloading the FAO stat Food balance sheet
FoodBalanceSheetFAO = get_faostat_bulk("FBS", "Input_data") #downloads the data bulk from faostat
Baseline_import_export = FoodBalanceSheetFAO %>% as_tibble() %>%
dplyr::filter(year %in% c("2010":"2018"), #for a 3 year average
area_code %in% country_eu, #filtering for EU+UKD countries
element == "import_quantity" | element == "export_quantity") %>% # choosing import and export quantity in 1000 tonnes
dplyr::group_by(item, element) %>%
dplyr::summarise(value = sum(value)) %>%
dplyr::mutate(value = value *1000) %>% #converting to tonnes
pivot_wider(values_from = value,
names_from = element) %>%
rename(export_ton = export_quantity,
import_ton = import_quantity,
dietary_products=item) %>%
replace(is.na(.), 0) %>% #all the NA values (crops that are not grown or imported to the EU) are 0.
dplyr::filter(dietary_products %in% (diet_prod_dist %>% pull(dietary_products))) %>%
replace(is.na(.), 0) # The forage, fibre and tabacco crops that have no match in column item are set to 0 (no import export assumed)
write_csv(Baseline_import_export, "Input_data/Baseline_import_export.csv")
# Baseline production -------------------------------------------------------------
Baseline_production = FoodBalanceSheetFAO %>% as_tibble() %>%
dplyr::filter(year %in% c("2010":"2018"),
area_code %in% country_eu, #filtering for EU+UKD countries
element == "production" ) %>% # choosing import and export quantity in 1000 tonnes
dplyr::group_by(area_code, item, element) %>%
dplyr::summarise(value = sum(value)) %>%
dplyr::mutate(value = value *1000) %>% #converting to tonnes from 1000 tonnes
pivot_wider(values_from = value,
names_from = element) %>%
rename(dietary_products=item) %>%
replace(is.na(.), 0) %>% #all the NA values (crops that are not grown or imported to the EU) are 0.
dplyr::filter(dietary_products %in% (diet_prod_dist %>% pull(dietary_products))) %>%
replace(is.na(.), 0) %>% #The forage, fibre and
left_join(country_map_FAO_code_namecifos, by= c("area_code"="country_code_FAO")) %>%
ungroup() %>%
dplyr::select(name_cntr_CIFOS2021, dietary_products, production) %>%
dplyr::rename(production_t=production,
country_cifos = name_cntr_CIFOS2021)
write_csv(Baseline_production, "Input_data/Baseline_production.csv")
# validation %>%distinct_at(vars(country_cifos)) # all good - 28 countries
# Baseline_food_supply ----------------------------------------------------
Baseline_food_supply =
FoodBalanceSheetFAO %>% as_tibble() %>%
dplyr::filter(year %in% c("2010":"2018"), #for a year average
area_code %in% country_eu, #filtering for EU+UKD countries
element=='protein_supply_quantity__g_capita_day_')%>% # unit is in g/capita/day
dplyr::group_by(area_code, item, element) %>%
dplyr::summarise(value = sum(value)) %>%
pivot_wider(values_from = value,
names_from = element) %>%
rename(dietary_products=item) %>%
replace(is.na(.), 0) %>% #all the NA values (crops that are not grown or imported to the EU) are 0.
dplyr::filter(dietary_products %in% (diet_prod_dist %>% pull(dietary_products))) %>%
replace(is.na(.), 0) %>% #The forage, fibre and
left_join(country_map_FAO_code_namecifos, by= c("area_code"="country_code_FAO")) %>%
ungroup() %>%
dplyr::select(name_cntr_CIFOS2021, dietary_products,protein_supply_quantity__g_capita_day_) %>%
dplyr::rename(food_supply_gppp=protein_supply_quantity__g_capita_day_ ,
country_cifos = name_cntr_CIFOS2021)
write_csv(Baseline_food_supply, "Input_data/Baseline_food_supply.csv")
# Baseline animal number --------------------------------------------------
# Loading the animal production data sheet from FAO:
# Livestock_Crop = get_faostat_bulk("QCL", "Input_data") #downloads the data bulk from faostat
# Livestock_Crop %>% write_csv("Input_data/Livestock_Crop_QCL.csv")
Livestock_Crop = read_csv("Input_data/Livestock_Crop_QCL.csv")
Baseline_animal_number =
Livestock_Crop %>% as_tibble() %>%
dplyr::filter(year %in% c("2010":"2018"), #for a year average
area_code %in% country_eu, #filtering for EU+UKD countries
item %in% c('Beef and Buffalo Meat','Chickens', 'Meat, Poultry',"Pigs", 'Milk, whole fresh cow'),
element %in% c("producing_animals_slaughtered", "stocks","milk_animals")) #%>%
dplyr::group_by(area_code, item, element) %>%
dplyr::summarise(value = mean(value, na.rm=T)) #%>%
pivot_wider(values_from = value,
names_from = element) #%>%
rename(crops=item) %>%
replace(is.na(.), 0) %>% #all the NA values (crops that are not grown or imported to the EU) are 0.
dplyr::filter(crops %in% dat_crop_fao_cifos_vec) %>%
replace(is.na(.), 0) %>% #The forage, fibre and
left_join(country_map_FAO_code_namecifos, by= c("area_code"="country_code_FAO")) %>%
ungroup() %>%
dplyr::select(name_cntr_CIFOS2021, crops,area_harvested) %>%
dplyr::rename(area_harvested_ha=area_harvested,
country_cifos = name_cntr_CIFOS2021)
write_csv(Baseline_food_supply, "Input_data/Baseline_food_supply.csv")
# Baseline crop area ------------------------------------------------------
# Crop map
dat_crop_fao_cifos = dat_crop_final %>% dplyr::select(crop_cifos, crop_name_fao)
dat_crop_fao_cifos_vec = dat_crop_fao_cifos %>% drop_na() %>% pull(crop_name_fao)
Baseline_area_crop_ha = Livestock_Crop %>% as_tibble() %>%
dplyr::filter(year %in% c("2010":"2018"), #for a year average
area_code %in% country_eu, #filtering for EU+UKD countries
element=='area_harvested') %>% # unit is in ha
dplyr::group_by(area_code, item, element) %>%
dplyr::summarise(value = sum(value, na.rm=T)) %>%
pivot_wider(values_from = value,
names_from = element) %>%
rename(crops=item) %>%
replace(is.na(.), 0) %>% #all the NA values (crops that are not grown or imported to the EU) are 0.
dplyr::filter(crops %in% dat_crop_fao_cifos_vec) %>%
replace(is.na(.), 0) %>% #The forage, fibre and
left_join(country_map_FAO_code_namecifos, by= c("area_code"="country_code_FAO")) %>%
ungroup() %>%
dplyr::select(name_cntr_CIFOS2021, crops,area_harvested) %>%
dplyr::rename(area_harvested_ha=area_harvested,
country_cifos = name_cntr_CIFOS2021)
write_csv(Baseline_area_crop_ha, "Input_data/Baseline_area_crop_ha.csv")
# Crop_others sheet -------------------------------------------------------
# crop_other_old = read_excel("C:/Wolfram_Admin/GAMS/EU_model_frmSep21/cifos-model_eu/European_CiFoS_model_data.xlsx", sheet = "Crop_Other")
# crop_other_old %>% write_csv("Input_data/crop_other.csv")
crop_other_old = read_csv("Input_data/crop_other.csv")
# Crop map
crop_map = read_csv("Input_data/dat_crop_with_grass.csv")
crop_other_new =
crop_other_old %>% dplyr::select(-c(27:52, DM:HI)) %>%
dplyr::rename(crop_cifos_old = `...1`,
Rotation=`Rotation...26`) %>%
full_join(crop_map %>% dplyr::select(old_cifos_crop, crop_cifos), by = c("crop_cifos_old"="old_cifos_crop")) %>%
relocate(crop_cifos , .before = crop_cifos_old) %>%
relocate(arable, .after = Rotation) %>%
# dplyr::filter(!grepl("Grass", crop_cifos))
dplyr::mutate(crop_cifos = case_when(crop_cifos_old == "Grass_Managed_HQ" ~ "grass_arable",
crop_cifos_old == "Grass_Managed_MQ" ~ "grass_pasture",
crop_cifos_old == "Grass_Natural_MQ" ~ "grass_rangeland",
TRUE ~ crop_cifos)) %>%
dplyr::select(-crop_cifos_old, -code_spam2010) %>%
distinct_at(vars(crop_cifos),.keep_all = T) %>% drop_na(crop_cifos)
write_csv(crop_other_new, "Input_Data/crop_other_new.csv")
# cropnutr = read_excel('C:/Wolfram_Admin/GAMS/EU_model_frmSep21/cifos-model_eu/European_CiFoS_model_data.xlsx',sheet="CropNutr")
# write_csv(cropnutr,"Input_data/cropnutr_old")
cropnutr = read_csv("Input_data/cropnutr_old")
# match the new crops
cropnutr_new =
cropnutr %>% dplyr::rename(crop_cifos_old = `...1`) %>%
full_join(crop_map %>% dplyr::select(old_cifos_crop, crop_cifos), by = c("crop_cifos_old"="old_cifos_crop")) %>%
relocate(crop_cifos, .before = crop_cifos_old) %>%
dplyr::select(-crop_cifos_old)
write_csv(cropnutr_new, "Input_data/cropnutr_new.csv")
# CropFert_New NOT DONE! ------------------------------------------------------------
# CropFert_New = read_excel("C:/Wolfram_Admin/GAMS/EU_model_frmSep21/cifos-model_eu/European_CiFoS_model_data.xlsx", sheet = "CropFert_New")
# CropFert_New %>% write_csv("Input_data/CropFert_New.csv")
CropFert_New = read_csv("Input_data/CropFert_New.csv")
CropFert =
CropFert_New %>%
dplyr::rename(crop_cifos_old = `...1`) %>%
full_join(crop_map %>% select(old_cifos_crop, crop_cifos), by = c("crop_cifos_old"="old_cifos_crop")) %>%
relocate(crop_cifos , .before = crop_cifos_old) %>%
pivot_wider(names_from = CropNutr,
values_from = value)
write_csv(CropFert, "Input_data/cropfert_inter.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")
proc_sheet_crops = bind_rows(dat_proc_new ,dat_proc_asf) #%>% write_csv("Input_data/proc_sheet_crops.csv")
# Crops
crop_datmap = dat_proc_new %>% select(crop_cifos) %>% distinct_all()
write_csv(crop_datmap, "Input_data/crop_datmap.csv")
# ProcoutH and dietary products map
ProcOutH_dietProduct = Processing_sheet_final %>% distinct_at(vars(proc_out), .keep_all = T) %>%
dplyr::select(proc_out, dietary_products) %>%
dplyr::filter(proc_out %in%(hum_nutr_all %>% distinct_at(vars(product)) %>% pull())) %>%
rename(ProcOutH = proc_out)
write_csv(ProcOutH_dietProduct, "Input_data/ProcOutH_dietProduct.csv")
# ProcOutH only
ProcOutH =Processing_sheet_final %>% distinct_at(vars(proc_out), .keep_all = F) %>%
dplyr::select(proc_out) %>%
dplyr::filter(proc_out %in%(hum_nutr_all %>% distinct_at(vars(product)) %>% pull())) %>%
rename(ProcOutH = proc_out)
write_csv(ProcOutH_dietProduct, "Input_data/ProcOutH.csv")
# Crops and co-products (proc_outs)
crop_procouts = dat_proc_new %>%
dplyr::select(crop_cifos, proc_out) %>%
distinct_at(vars(crop_cifos,proc_out))
write_csv(crop_procouts, "Input_data/crop_procouts.csv")
# Livestock-Co_product
# livestock_procouts = dat_proc_asf %>%
# dplyr::select(crop_cifos, proc_out) %>%
# distinct_at(vars(crop_cifos,proc_out))
#
# write_csv(crop_procouts, "Input_data/crop_procouts.csv")
# Crops and co-products (proc_outs)
crop_procouts_diet_products = dat_proc_new %>%
dplyr::select(crop_cifos, proc_out,dietary_products) %>%
distinct_at(vars(crop_cifos,proc_out,dietary_products))
write_csv(crop_procouts_diet_products, "Input_data/crop_procouts_diet_products.csv")
# My excel
Crop_Map2 = read_excel("C:/Wolfram_Admin/GAMS/EU_model_frmSep21/cifos-model_eu/European_CiFoS_model_data.xlsx", sheet = "Data_Map")
# Crop_Map2 = read_excel("C:/Wolfram_Admin/GAMS/EU_model_frmSep21/cifos-model_eu/European_CiFoS_model_data.xlsx", sheet = "Data_Map")
# Crop_Map2 %>% write_csv("Input_data/crop_map_mine.csv")
Crop_Map2 =read_csv("Input_data/crop_map_mine.csv")
# This is the only map that is actually used in the model 30.01.22
diets_animal_crop_datamap =
Crop_Map2 %>% slice(121:210) %>%
dplyr::select(c(1:2)) %>% dplyr::rename(crop_cifos = `CROPS FAO...1`,
proc_out = `Co-Product...2`) %>%
filter(proc_out != 'Grass_Natural_LQ') %>%
full_join(dat_proc_asf %>% dplyr::select(proc_out, dietary_products)) %>%
distinct_all() %>%
bind_rows(.,dat_proc_new %>% select(c(crop_cifos,4,6)))
write_csv(animal_map, "Input_Data/diets_animal_crop_datamap.csv")
# crop_animal_co_prod_dietary
# Logic - Whole data in the database
# In yields, area, crop_other
# 1. Crops > FAO_crops
# # in processing sheet > remove everything that is not used in the model. All products can have a max of three functions(animal feed, human food, fertilizer)
# 2. FAO_crops > Proc_Raw (processing_sheet(ProcRaw matched with crops --> Only put in crops that get a value >> delete them))
# 3. Proc_raw > ProcIn (supply_sheets FAO)
# 4. ProcIn > ProcOut
# 5. ProcOutc > Dietary_product (group of the FAO >> that is matched to Food groups (Fruits, vegetables, fibres,...))
# # each Proc_out have to have a or many functions (feed, fertilizer, etc.)
# 6. Proc_out > Product (Human_Nutr sheet) # function: human food
# 7. Proc_out > Product (Animal_Nutr sheet) # function:animal feed
# 8. Proc_out > Prod (Loss_fraction_new sheet) # function: Proc_raw for fertilizer OR animal feed
# 9. Proc_out > column B (fert_suitability sheet)
# 10 . Dietary Products ("processing sheet") > Item("import sheet")
# 11. Item(import_sheet) > Dietary_product (processing fraction sheet) >> Everything that is imported in that country, everything that is exported
# Workflow
# Processing sheet: Make sure that we only have plant based products that are represented in the crops_coproduct
### If you do not find products in the sheet that are in the crop sheet (disaggregated) we need to find the "Value" and the nutritional content.
### Or report the assumptions >> Renee and Wendy and Demy could also help. Demy is wendy's friend and is the project assistant!
### Contact Hannah when your done with PF sheet.
# IMPORTANT: Naming: Crops > Just name it >> Use original name from SPAM and Monfreda
# Forage crops: Just assume processing fraction of 1
# Single mappings
# Check following.
## ProcOutH should be element of ProcOut
## Note: Animals ok. Crops not --> Update!
# IMPORT sheet: Already mapped!
# When you import your crop data in the processing.
# ProcOutH (cifos procout) > DietProd (FAO supply sheet) ## we can have four products to supply the
# DietProd (DataMap) > DietaryProducts (processing fration sheet)
# # Animals
# #Animal_yield sheet
# 1. Yields (column D row 2)
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment