Improve PCe mapping and add it to data export for Sci Data

Author: realxinzhao

.gitignore

@@ -48,5 +48,6 @@ inst/extdata/GCAM/aglu/FAO/GCAMFAOSTAT*
 # Developer
 paper
 developertemp
+data-raw/SciData/*
 
 #docs

R/yfaostat_Traceable_FBS_DataExport.R

@@ -21,13 +21,13 @@ module_yfaostat_Traceable_FBS_DataExport <- function(command, ...) {
     c(FILE = file.path(DIR_RAW_DATA_FAOSTAT, "Mapping_gcamdata_SUA_PrimaryEquivalent"),
       FILE = file.path(DIR_RAW_DATA_FAOSTAT, "Mapping_gcamdata_SUA_ItemCode"),
       FILE = file.path(DIR_RAW_DATA_FAOSTAT, "Mapping_gcamdata_FAO_iso_reg"),
-      FILE = file.path(DIR_RAW_DATA_FAOSTAT, "Mapping_gcamdata_SUA_ItemCode"),
       "L105.Bal_new_all",
       "L107.Traceable_FBS_PCe_2010Plus",
       "L107.Traceable_FBS_Food_Calorie_Macronutrient_2010Plus")
 
     MODULE_OUTPUTS <-
       c(CSV = "Metadata_GCAMFAOSTAT_Traceable_FBS",
+        CSV = "Nested_Mapping_SUA_To_Traceable_FBS",
         CSV = "SUA_2010_2022",
         CSV = "SUA_Food_Calorie_Macronutrient_2010_2022",
         CSV = "Traceable_FBS_PCe_2010_2022",
@@ -58,27 +58,72 @@ module_yfaostat_Traceable_FBS_DataExport <- function(command, ...) {
       # Helper functions ----
       Metadata_GCAMFAOSTAT_Traceable_FBS <- NULL
       add_to_output_meta <- function(.df,
-                                     .datasetname){
-
-        .df %>% gather_years() -> .df
-        if ("year" %in% names(.df)) {
-          YearRange = paste0(.df %>% distinct(year) %>% min," to ", .df %>% distinct(year) %>% max)
-        } else{
-          YearRange = "BaseYears"
+                                     .datasetname,
+                                     .skip_stat = FALSE){
+
+        if (.skip_stat == FALSE) {
+
+          .df %>% gather_years() -> .df
+          if ("year" %in% names(.df)) {
+            YearRange = paste0(.df %>% distinct(year) %>% min," to ", .df %>% distinct(year) %>% max)
+          } else{
+            YearRange = "BaseYears"
+          }
+
+          Metadata_GCAMFAOSTAT_Traceable_FBS %>%
+            bind_rows(
+              data.frame(dataset = .datasetname,
+                         nReg = .df %>% distinct(iso) %>% nrow,
+                         nItem = .df %>% distinct(item) %>% nrow,
+                         Years = YearRange)
+            ) -> .df1
+        } else {
+
+          Metadata_GCAMFAOSTAT_Traceable_FBS %>%
+            bind_rows(
+              data.frame(dataset = .datasetname)
+            ) -> .df1
         }
 
-        Metadata_GCAMFAOSTAT_Traceable_FBS %>%
-          bind_rows(
-            data.frame(dataset = .datasetname,
-                       nReg = .df %>% distinct(iso) %>% nrow,
-                       nItem = .df %>% distinct(item) %>% nrow,
-                       Years = YearRange)
-          ) -> .df1
-
         assign("Metadata_GCAMFAOSTAT_Traceable_FBS", .df1, envir = Curr_Envir)
       }
 
 
+      # * Mapping_PrimaryEquivalent_nested_SUA ----
+
+      Mapping_gcamdata_SUA_PrimaryEquivalent %>%
+        transmute(aggregated_PCe_item = APE_comm_Agg, PCe_item = APE_comm,
+                  nest_level, source_item0 = source_item, sink_item0 = sink_item) %>%
+        distinct() %>%
+        left_join_error_no_match(
+          Mapping_gcamdata_SUA_ItemCode %>%
+            distinct(source_item0 = item,  source_item_code = item_code, source_item = item_new_2024), by = "source_item0") %>%
+        left_join_error_no_match(
+          Mapping_gcamdata_SUA_ItemCode %>%
+            distinct(sink_item0 = item,  sink_item_code = item_code, sink_item = item_new_2024), by = "sink_item0") %>%
+        transmute(aggregated_PCe_item, PCe_item,
+                  nest_level, source_item, source_item_code, sink_item, sink_item_code) %>%
+        add_title("Nested_Mapping_SUA_To_Traceable_FBS") %>%
+        add_units("none") %>%
+        add_comments("gcamfaostat Export CSV") %>%
+        add_precursors(file.path(DIR_RAW_DATA_FAOSTAT, "Mapping_gcamdata_SUA_PrimaryEquivalent")) ->
+        Nested_Mapping_SUA_To_Traceable_FBS
+
+      output_csv_data(
+        gcam_dataset = Nested_Mapping_SUA_To_Traceable_FBS,
+        out_filename = "Nested_Mapping_SUA_To_Traceable_FBS",
+        col_type_nonyear = "ccicici",
+        title = "Mapping of SUA items to aggregated primary commodity equivalent products by level of nestings",
+        unit = "NA",
+        code = "NA",
+        description = "Data is compiled and generated by gcamfaostat.",
+        out_dir = DIR_OUTPUT_CSV,
+        GZIP = F)
+
+      add_to_output_meta(.df = Nested_Mapping_SUA_To_Traceable_FBS,
+                         "Nested_Mapping_SUA_To_Traceable_FBS", .skip_stat = TRUE)
+
+
       # Zeros were removed in all dataset in exporting to reduce size
       # We updated item names to the latest when applicable
 

inst/extdata/FAOSTAT/Mapping_gcamdata_SUA_PrimaryEquivalent.csv

@@ -331,7 +331,6 @@ Milk and products,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Milk,
 Milk and products,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow",Yoghurt,,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
 Milk and products,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Whey, fresh",,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
 Milk and products,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Cheese, whole cow milk",,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
-Milk and products,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Milk, skimmed cow",,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
 Milk and products,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow",Cream fresh,,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
 Milk and products,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Butter, cow milk",,"Butter, Ghee and products",0.739010126,0.857196004,TRUE
 Milk and products,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Ghee, butteroil of cow milk",,"Butter, Ghee and products",0.739010126,0.857196004,TRUE

inst/extdata/aglu/FAO/Mapping_SUA_PrimaryEquivalent.csv

@@ -326,7 +326,6 @@ Dairy,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Milk, whole conden
 Dairy,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow",Yoghurt,,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
 Dairy,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Whey, fresh",,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
 Dairy,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Cheese, whole cow milk",,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
-Dairy,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Milk, skimmed cow",,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
 Dairy,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow",Cream fresh,,Milk - (Excluding excluding Butter butter) and products,0.739010126,0.857196004,TRUE
 Dairy,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Butter, cow milk",,"Butter, Ghee and products",0.739010126,0.857196004,TRUE
 Dairy,"Milk, whole fresh cow",1,TRUE,"Milk, whole fresh cow","Ghee, butteroil of cow milk",,"Butter, Ghee and products",0.739010126,0.857196004,TRUE