Adding more processing chunks

Adding price, production, and area related processing
function updates
gz data updates (per recent gcamdata); also consistent with this package

DESCRIPTION

@@ -1,40 +1,12 @@
 Package: gcamdata
 Type: Package
-Title: Build the GCAM Input Datasets
-Version: 5.1
-Date: 2019-07-06
-Authors@R: c(  person("Russell", "Horowitz", 
-		email = "[email protected]",   
-		role = c("cre","aut"),
-		comment = c(ORCID = "0000-0002-0270-3127")),
-  person("Ben", "Bond-Lamberty", role = c( "aut"), comment = c(ORCID = "0000-0001-9525-4633")),
-  person("Katherine", "Calvin",   role = "aut", comment = c(ORCID = "0000-0003-2191-4189")),
-  person("Ryna", "Cui",           role = "aut", comment = c(ORCID = "0000-0002-8531-4126")),
-  person("Kalyn", "Dorheim",      role = "aut", comment = c(ORCID = "0000-0001-8093-8397")),
-  person("Leyang", "Feng",        role = "aut"),
-  person("Jill", "Horing",        role = "aut", comment = c(ORCID = "0000-0003-2516-5533")),
-  person("Page", "Kyle",          role = "aut", comment = c(ORCID = "0000-0002-1257-8358")),
-  person("Robert", "Link",        role = "aut"),
-  person("Pralit", "Patel",       role = "aut", comment = c(ORCID = "0000-0003-3992-1061")),
-  person("Christopher", "Roney",  role = "aut", comment = c(ORCID = "0000-0003-0509-5259")),
-  person("Abigail", "Snyder",     role = "aut", comment = c(ORCID = "0000-0002-9034-9948")),
-  person("Aaron", "Staniszweski", role = "aut"),
-  person("Sean", "Turner",        role = "aut", comment = c(ORCID = "0000-0003-4400-9800")),
-  person("Matthew", "Binsted",    role = "aut", comment = c(ORCID = "0000-0002-5177-7253")),
-  person("Zarrar", "Khan",        role = "aut", comment = c(ORCID = "0000-0002-8147-8553")),
-  person("Corinne", "Hartin",     role = "ctb", comment = c(ORCID = "0000-0003-1834-6539")),
-  person("Rachel", "Hoesly",      role = "ctb"),
-  person("Mohamad", "Hejazi",     role = "ctb"),
-  person("Gokul", "Iyer",         role = "ctb"),
-  person("Sonny", "Kim",          role = "ctb"),
-  person("Yaling", "Liu",         role = "ctb"),
-  person("Haewon", "McJeon",      role = "ctb"),
-  person("Steve", "Smith",        role = "ctb"),
-  person("Stephanie", "Waldhoff", role = "ctb", comment = c(ORCID = "0000-0002-8073-0868")),
-  person("Marshall", "Wise",      role = "ctb"),
-  person("Leon", "Clarke",        role = c("rth", "ctb")),
-  person("Pacific Northwest National Laboratory", role = "cph"))
-Description: Build the GCAM XML input files.
+Title: Process FAO data for global agroeconomic modeling
+Version: 1.1
+Date: 2023-05-06
+Authors@R: c(person("Xin", "Zhao", email = "[email protected]", role = c("cre", "aut"), comment = c(0000-0002-1801-4393)),
+            person("Katherine", "Calvin", role = "aut", comment = c(ORCID = "0000-0003-2191-4189")),
+            person("Pacific Northwest National Laboratory", role = "cph"))
+Description: Clean and balance agricultural input and supply-utilization data.
 License: MIT + file LICENSE
 Depends: R (>= 3.1.2)
 Imports:

NAMESPACE

@@ -49,6 +49,7 @@ importFrom(dplyr,select)
 importFrom(dplyr,summarise)
 importFrom(dplyr,summarise_all)
 importFrom(dplyr,summarize)
+importFrom(dplyr,transmute)
 importFrom(dplyr,ungroup)
 importFrom(dplyr,vars)
 importFrom(grDevices,rainbow)
@@ -64,6 +65,7 @@ importFrom(tibble,is_tibble)
 importFrom(tibble,tibble)
 importFrom(tidyr,complete)
 importFrom(tidyr,drop_na)
+importFrom(tidyr,fill)
 importFrom(tidyr,gather)
 importFrom(tidyr,nesting)
 importFrom(tidyr,replace_na)

R/module-helpers.R

@@ -716,8 +716,8 @@ FAO_AREA_DISAGGREGATE_HIST_DISSOLUTION <-
 #' @param .DF Input data frame
 #' @param SUDAN2012_BREAK If T break Sudan before 2012 based on 2013- 2016 data
 #' @param SUDAN2012_MERGE If T merge South Sudan into Sudan
-#' @param .FAO_AREA_CODE_COL
-#' @param .AREA_COL
+#' @param .FAO_AREA_CODE_COL Name of col of area
+#' @param .AREA_COL Name of col of area code
 #'
 #' @return data with historical periods of dissolved region disaggregated to small pieces.
 
@@ -842,7 +842,7 @@ FAO_AREA_DISAGGREGATE_HIST_DISSOLUTION_ALL <- function(.DF,
 
   if (all_of(.AREA_COL) %in% names(.DF0)) {
     .DF2 %>%# Get area back
-      left_join(.DF0 %>% distinct_at(vars(all_of(.AREA_COL), .FAO_AREA_CODE_COL)),
+      left_join(.DF0 %>% dplyr::distinct(across(c(.AREA_COL, .FAO_AREA_CODE_COL))) ,
                 by = .FAO_AREA_CODE_COL) -> .DF2
   }
 

R/xfaostat_L100_constants.R

@@ -3,4 +3,16 @@
 # General behavior constants ======================================================================
 
 # having issues with package check here
- DIR_RAW_DATA_FAOSTAT <- system.file("extdata", "aglu/FAO/FAOSTAT", package = "gcamdata")
+# comment this line out when building package
+  DIR_RAW_DATA_FAOSTAT <- system.file("extdata", "aglu/FAO/FAOSTAT", package = "gcamdata")
+
+
+
+
+
+  # used in Get_SUA_TEMPLATE and SUA_bal_adjust
+
+  c("Opening stocks", "Production", "Import",
+    "Export", "Processed", "Food", "Feed", "Seed", "Other uses", "Loss", "Closing stocks",
+    "Residuals", "Regional supply", "Regional demand", "Stock Variation") ->
+    Bal_element_new

R/xfaostat_L101_RawDataPreProcessing1.R

@@ -102,12 +102,12 @@ module_xfaostat_L101_RawDataPreProcessing1 <- function(command, ...) {
     # Using index to fill in missing across years
     PP1 %>%
       filter(element_code %in% c(5532, 5539)) %>%
-      select(area_code, area, item_code, item, element_code, element, year, value, unit) %>%
+      select(area_code, area, item_code, item, element, year, value) %>%
       # Not completing year and area here
       spread(element, value) %>%
       left_join(
         PP1 %>% filter(element_code %in% c(5532, 5539)) %>%
-          select(area_code, area, item_code, item, element_code, element, year, value, unit) %>%
+          select(area_code, area, item_code, item, element, year, value) %>%
           spread(element, value) %>%
           rename(pp_base = `Producer Price (USD/tonne)`,
                  pp_baseindex = `Producer Price Index (2014-2016 = 100)`) %>%
@@ -133,7 +133,7 @@ module_xfaostat_L101_RawDataPreProcessing1 <- function(command, ...) {
       add_comments("Preprocessed FAOSTAT producer prices") ->
       PP
 
-    rm(PP, PP1, PP2)
+    rm(PP1, PP2)
 
     # Food balance and Supply-Utilization-Account
 
@@ -156,7 +156,7 @@ module_xfaostat_L101_RawDataPreProcessing1 <- function(command, ...) {
       add_units("tonne") %>%
       add_comments("Preprocessed FAOSTAT SCL") ->
       FBS
-    rm(FBS, FBS1)
+    rm(FBS1)
 
 
     ## *[SCL] SUA: supply utilization accounting ----
@@ -185,7 +185,7 @@ module_xfaostat_L101_RawDataPreProcessing1 <- function(command, ...) {
        add_units("tonne") %>%
        add_comments("Preprocessed FAOSTAT SCL") ->
       SCL
-     rm(SCL, SCL1)
+     rm(SCL1)
 
 
     return_data(MODULE_OUTPUTS)

R/xfaostat_L101_RawDataPreProcessing2.R

@@ -46,11 +46,6 @@ module_xfaostat_L101_RawDataPreProcessing2 <- function(command, ...) {
 
     QCL_area_code <- QCL_area_code_map %>% distinct(area_code) %>% pull()
 
-    # *[QCL] FAOSTAT Production and area ----
-
-    ## Load raw data
-    FAOSTAT_load_raw_data(DATASETCODE = "QCL", DATA_FOLDER = DIR_RAW_DATA_FAOSTAT)
-
 
     # Food balance and Supply-Utilization-Account
 
@@ -147,7 +142,7 @@ module_xfaostat_L101_RawDataPreProcessing2 <- function(command, ...) {
       FBSH_CB
 
     rm(SHELL_RATE_groundnuts, Mill_RATE_rice);
-    rm(FBSH_CB1, FBSH, CB, dup_item_code)
+    rm(FBSH_CB1, dup_item_code)
 
 
     # *[OA]: Population ----
@@ -166,7 +161,7 @@ module_xfaostat_L101_RawDataPreProcessing2 <- function(command, ...) {
       add_units("tonne") %>%
       add_comments("Preprocessed FAO OA") ->
       OA
-    rm(OA, OA1)
+    rm(OA1)
     rm(QCL_area_code)