Xinxin Yang's avatar
capri visualization package
Xinxin Yang committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 
# Script: filter different markets( just for cake oil market and sugar, cereals...)

#' function reads balance detailed, split it into "biofuels" and "non-biofuels"
#'
#' @param balance_detailed A data frame.
#' @param p_biofuels boolean.
#' @return links
#' @export
#'
prelinks <- function(balance_detailed, p_biofuels = TRUE){
  # balance_detailed <- balance_detailed_Scenario

  # add variable key, itemName and color from products
  balance_detailed <- left_join(balance_detailed, products[,c(2,3,9)], by = c(".i4" = "key"))

  # rename new variable
  colnames(balance_detailed)[13] <- "Commodities"
  colnames(balance_detailed)[1] <- "key"

  balance_detailed$Commodities <- sub("\\[.*?\\]", "", balance_detailed$Commodities)


  library(magrittr)
  # prod_list_fullname <- balance_detailed %>% select(Commodities) %>% extract2(1)

  # remove character begin with [ and end with ]
  # prod_list_fullname <- gsub("\\[.*?\\]", "", prod_list_fullname)
  # p_biofuels = T

  if (p_biofuels){
    selected_list = c("Rape seed",
                      "Soya seed",
                      "Sunflower seed",
                      "Rape seed oil",
                      "Soya oil",
Xinxin Yang's avatar
update  
Xinxin Yang committed
36 
                      "Sunflower seed oil",
Xinxin Yang's avatar
capri visualization package
Xinxin Yang committed
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 
                      "Soya cake",
                      "Sunflowe seed cake",
                      "Rape seed cake",
                      "Destilled dried grains from bio-ethanol processing",
                      "Pulses",
                      "Bio ethanol")
  }else{
    selected_list = c("Wheat","Grain maize","Barley", "Other cereals","Poultry meat",
                      "Sugar", "Fish and other acquatic products", "Rice milled")
  }

  #
  balance_detailed_ <- balance_detailed %>% as.data.frame()
  balance_detailed_selected <-  filter(balance_detailed_, balance_detailed_[,13] %in% selected_list)

  as_tibble(balance_detailed_selected)

  #rename "Destilled dried grains from bio-ethanol processing" -> "DDGS"
  # balance_detailed_selected <- balance_detailed_selected %>%
  #   mutate(Commodities = ifelse(Commodities!="Destilled dried grains from bio-ethanol processing",Commodities,"DDGS"))


  # filter
  balance_detailed_all <- balance_detailed_selected %>%
    select(-.i1)  %>% # remove region
    select(-.i5)  %>% # remove year: 2030
    select(-interv_ch)  %>%
    group_by(Commodities) %>%
    summarise_at(vars(supply:exports),sum,na.rm=TRUE)

  library(magrittr)
  prod_list_fullname <- balance_detailed_selected %>% select(Commodities) %>% extract2(1)

  #print(prod_list_fullname)
  vars_to_run <- prod_list_fullname


  left_side <- c("supply","imports")

  links_list <- list()
  #nodes_list <- list()

  vars_to_run <- vars_to_run[!vars_to_run %in%
                               c("Soya oil",
                                 "Soya cake",
                                 "Rape seed oil",
                                 "Rape seed cake",
Xinxin Yang's avatar
update  
Xinxin Yang committed
84 
                                 "Sunflower seed oil",
Xinxin Yang's avatar
capri visualization package
Xinxin Yang committed
85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 
                                 "Sunflowe seed cake",
                                 "Bio ethanol",
                                 "Destilled dried grains from bio-ethanol processing"
                               )]
  # "Rape seed"      "Sunflower seed" "Soya seed"      "Pulses"
  for (i in vars_to_run){

    data_df <- reshape2::melt(balance_detailed_all)

    data_df_1 <- data_df %>% filter(Commodities == i)
    data_df_1_l <- data_df_1  %>% filter(variable %in% left_side )
    data_df_1_r <- data_df_1  %>% filter(!variable %in% left_side)
    data_df_1_l_agg <- data_df_1_l %>% group_by(Commodities) %>% summarise(value=sum(value))
    data_df_1_l_agg$variable <- paste0(i)


    first <- merge(data_df_1_l,data_df_1_l_agg,by="Commodities",all=TRUE)

    first <- first[,c("variable.x","variable.y","value.x")]
    colnames(first)[3] <- "value"


    second <- merge(data_df_1_l_agg,data_df_1_r,by="Commodities",all=TRUE)
    second <- second[,c("variable.x","variable.y","value.y")]
    colnames(second)[3] <- "value"

    if (p_biofuels){
      if (i != "Pulses"){
        if (i == "Soya seed") {produced  = c("Soya oil","Soya cake")}
        else if (i == "Rape seed") {produced  = c("Rape seed oil","Rape seed cake") }
Xinxin Yang's avatar
update  
Xinxin Yang committed
115 
        else if (i == "Sunflower seed") {produced  = c("Sunflower seed oil","Sunflowe seed cake") }
Xinxin Yang's avatar
capri visualization package
Xinxin Yang committed
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 
        else {print(i);break}

        data_df_proc_help <- balance_detailed_all %>% filter(Commodities %in% produced)
        data_df_proc_help <- reshape2::melt(data_df_proc_help)
        data_df_proc_help <- data_df_proc_help %>% filter(variable== "supply" )
        data_df_proc_help$variable <- paste(data_df_proc_help$Commodities)

        data_df_proc_help$Commodities <- i
        colnames(data_df_proc_help) <- c("variable.x","variable.y","value")

        second <- rbind(second,data_df_proc_help)
        second <- second %>% filter(variable.y!="processing")

        data_df_proc_help <- balance_detailed_all %>% filter(Commodities %in% produced)
        data_df_proc_help <- reshape2::melt(data_df_proc_help)
        data_df_proc_help <- data_df_proc_help %>% filter(variable!="supply")
        colnames(data_df_proc_help) <- c("variable.x","variable.y","value")
        second <- rbind(second,data_df_proc_help)
        second_imports <- second %>% filter(variable.y=="imports")
        second <- second %>% filter(!variable.y=="imports")
        colnames(second_imports) <- c("variable.y","variable.x","value")
        second <- rbind(second,second_imports)
      }

    }

    combined <- rbind(first,second)
    links_list[[i]] <- combined


    links <- rbindlist(links_list)
    links <- unique(links)

  }

  if(p_biofuels){

    # links[grepl("Bio",variable.x) | grepl("Bio",variable.y)]
    setnames(links,old=c("variable.x","variable.y"),new=c("source","target"))
    # links[grepl("Bio",source) | grepl("Bio",target)]

    i <- c("Bio ethanol","Destilled dried grains from bio-ethanol processing")

    data_df_proc_help <- balance_detailed_all %>% filter(Commodities %in% i)
    data_df_proc_help <- reshape2::melt(data_df_proc_help)
    data_df_proc_help <- data_df_proc_help %>% filter(variable=="supply")
    data_df_proc_help$variable <- paste(data_df_proc_help$Commodities)

    data_df_proc_help$Commodities <- "biofuels"
    colnames(data_df_proc_help) <- c("variable.x","variable.y","value")

    data_df <- reshape2::melt(balance_detailed_all)

    data_df_1 <- data_df[data_df$Commodities %in% i,]
    data_df_1_l <- data_df_1[data_df_1$variable %in% left_side,]
    data_df_1_l$variable <- as.character(data_df_1_l$variable)
    data_df_1_l <- data_df_1_l %>% filter(variable!="supply")
    data_df_1_r <- data_df_1[!data_df_1$variable %in% left_side,]
    data_df_1_r$variable <- as.character(data_df_1_r$variable)
    data_df_1_l_agg <- data_df_1_l%>%group_by(Commodities) %>% summarise(value=sum(value))
    data_df_1_l_agg$variable <- paste0(i)
    first <- merge(data_df_1_l,data_df_1_l_agg,by="Commodities",all=TRUE)
    first <- first[,c("variable.x","variable.y","value.x")]
    colnames(first)[3] <- "value"
    second <- merge(data_df_1_l_agg,data_df_1_r,by="Commodities",all=TRUE)
    second <- second[,c("variable.x","variable.y","value.y")]
    colnames(second)[3] <- "value"
    second <- rbind(second,data_df_proc_help)


    second <- second %>% filter(!variable.y %in% c("processing","biofuels"))


    #nodes <- rbind(nodes,data.frame("name"=i))
    combined <- rbind(first,second)
    setnames(combined,old=c("variable.x","variable.y"),new=c("source","target"))

    links <- rbind(links,combined)

  }
  else{
    setnames(links,old=c("variable.x","variable.y"),new=c("source","target"))

  }