adjust xml conversion script to get the actual values..

dev/dev_unhcr_programme.Rmd

@@ -85,12 +85,12 @@ ping_ollama()
 
 ## Show donors 
 
- *  Who are the __main donors by country__ in terms of number of     projects and/or total budget?   
+ *  Who are the __main donors by country__ in terms of transaction?   
 
 ```{r function-show_donors, echo=FALSE, message=FALSE, warning=FALSE}
 #' show_donors
 #'
-#' @description Who are the main donors by country in terms of number of projects and/or total budget? 
+#' @description Who are the main donors by country in terms of transaction? 
 #' 
 #' @param year year to select starting from 2016 - could be one year or a list
 #' @param programme_lab A character vector corresponding to the name of the programme.
@@ -113,6 +113,8 @@ show_donors <- function(year,
                         ctr_name = NULL,
                         transaction_type_name = "Incoming Commitment"  ) {
   
+  ## Check year is after or equal 2016
+  
   
   # Check if only one argument is passed 
   if (!is.null(programme_lab) && !is.null(iati_identifier_ops)) {
@@ -186,9 +188,11 @@ show_donors <- function(year,
 
 ```{r examples-show_donors, message=FALSE, warning=FALSE, fig.retina = 2, fig.width = 8, fig.asp = 0.618, fig.align = "center",  out.width = "90%"}
 
-knitr::kable( codeTransactionType |> dplyr::select(name,  description) )
+knitr::kable(iati::dataTransaction |>
+                dplyr::select( transaction_type_name, transaction_type_description) |>
+                dplyr::distinct() )
 
-show_donors(year = 2018,
+show_donors(year = 2022,
            programme_lab = "The Americas",
            transaction_type_name = "Incoming Commitment" )
 
@@ -503,7 +507,9 @@ show_partnership <- function( year,
                   participating_org_type_name, 
                   participating_org_role_name) |>
      tidyr::pivot_wider(names_from = participating_org_role_name, 
-              values_from = participating_org_eng )
+              values_from = participating_org_eng ,
+              values_fn = list) |>
+    dplyr::select( - Accountable)
   
   df3 <- df    |>
     dplyr::select(participating_org_eng, 

inst/build.R

@@ -10,12 +10,22 @@ iati_file <- file_temp()
 # https://reporting.unhcr.org/files/IATI/UNHCR-Activities-2020.xml
 # https://reporting.unhcr.org/files/IATI/UNHCR-Activities-2023.xml
 
-download.file('https://reporting.unhcr.org/files/IATI/UNHCR-Activities-2022.xml', 
+#' list_iati <- c("http://reporting.unhcr.org/files/IATI/UNHCR-Activities-2016.xml",
+#'                "http://reporting.unhcr.org/files/IATI/UNHCR-Activities-2017.xml",
+#'                "http://reporting.unhcr.org/files/IATI/UNHCR-Activities-2018.xml",
+#'                "http://reporting.unhcr.org/files/IATI/UNHCR-Activities-2019.xml",
+#'                "http://reporting.unhcr.org/files/IATI/UNHCR-Activities-2020.xml",
+#'                "http://reporting.unhcr.org/files/IATI/UNHCR-Activities-2021.xml",
+#'                "http://reporting.unhcr.org/files/IATI/UNHCR-Activities-2022.xml",
+#'                "http://reporting.unhcr.org/files/IATI/UNHCR-Activities-2023.xml"
+#'                )
+
+download.file('https://reporting.unhcr.org/files/IATI/UNHCR-Activities-2021.xml', 
               iati_file, 
               quiet = TRUE)
 
 # create folder -----------------------------------------------------------
-folder_name = "data-raw-2022"
+folder_name = "data-raw-2021"
 dir_create(folder_name) 
 
 # list tasks --------------------------------------------------------------

inst/source/tasks/1_extract_data/iati_result.R

@@ -1,38 +1,110 @@
 iati_result <- function(xml_iati) {
-# xml subset --------------------------------------------------------------
-
+# xml subset Extraction:--------------------------------------------------------------
+#   The function starts by extracting a subset of XML data related to results.
+#  It looks for all nodes with the name iati-activity/result/indicator using xml_find_all.
+#  The result is stored in the notesets_indicator variable.
+
+
 notesets_indicator <- xml_iati %>% 
   xml_find_all('.//iati-activity/result/indicator') |> 
   map(xml_children)
 
 
-# extract data ------------------------------------------------------------
+# Data Extraction and Transformation:------------------------------------------------------------
+
+# The function then processes each indicator node in the notesets_indicator subset.
 df_result <- map_dfr(notesets_indicator, function(i) {
+
+  # For each indicator, it extracts relevant information into a tibble (data frame): 
   tibble(
-    iati_identifier = tryCatch(i|> xml_parent() |> xml_parent() |> xml_parent() |> xml_find_all("iati-identifier") |> xml_text(), error = function(e){ NA_character_}),
-    result_type = tryCatch(i |> xml_parent() |> xml_parent() |> xml_attr("type"), error = function(e){ NA_character_}),
-    result_aggregation_status = tryCatch(i |> xml_parent() |> xml_parent() |> xml_attr("aggregation-status"), error = function(e){ NA_character_}),
-    result_title = i |>  xml_parent() |>  xml_parent() |> xml_find_first("title") |> xml_text(),
-    result_desc = i |>  xml_parent() |>  xml_parent() |> xml_find_first("description") |> xml_text(),
-    result_indicator_measure = i |>  xml_parent() |> xml_attr("measure"),
-    result_indicator_title = xml_text_by_name(i, ".", "title"),
-    result_indicator_desc = xml_text_by_name(i, ".", "description"),
+    # Tries to find the IATI identifier associated with the indicator.
+    iati_identifier = tryCatch(
+      i |> xml_parent() |> xml_parent() |> xml_parent() |> xml_find_all("iati-identifier") |> xml_text(),
+      error = function(e) {
+        NA_character_
+      }
+    ),
+    # Tries to extract the type of result (output, outcome, etc.).
+    result_type = tryCatch(
+      i |> xml_parent() |> xml_parent() |> xml_attr("type"),
+      error = function(e) {
+        NA_character_
+      }
+    ),
+    ## Applies for the whole results the indicator is linked to...
+    result_title = i |>  
+      xml_parent() |>  
+      xml_parent() |> 
+      xml_find_first("title") |> 
+      xml_text(),
+
+
+
+
+    ## metadata for the indicator itself..
+   #  result_aggregation_status = tryCatch(
+   #    i |> xml_parent() |> xml_parent() |> xml_attr("aggregation-status"),
+   #    error = function(e) {
+   #      NA_character_
+   #    }
+   #  ), 
+   #  result_ascending = tryCatch(
+   #    i |> xml_parent() |> xml_parent() |> xml_attr("ascending"),
+   #    error = function(e) {
+   #      NA_character_
+   #    }
+   #  ),
+   # # result_indicator_measure = i |>  xml_parent() |> xml_attr("measure"), 
+   #  result_measure = tryCatch(
+   #    i |> xml_parent() |> xml_parent() |> xml_attr("measure"),
+   #    error = function(e) {
+   #      NA_character_
+   #    }
+   #  ),
+
+   result_indicator_title = xml_text_by_name(i, ".", "title"),
+   result_indicator_measure = i |>  xml_parent() |> xml_attr("measure"),
+   result_indicator_aggregation_status = i |>  xml_parent() |> xml_attr("aggregation-status"),
+   result_indicator_ascending = i |>  xml_parent() |> xml_attr("ascending"),
+   result_indicator_reference_code = xml_child_attr_by_name(i, "reference", "code", 1),
+   result_indicator_reference_uri = xml_child_attr_by_name(i, "reference", "indicator-uri", 1),
+   result_indicator_reference_vocabulary = xml_child_attr_by_name(i, "reference", "vocabulary", 1),
+
+
+    ## Check baseline 
+    result_indicator_baseline_location_ref = xml_child_attr_by_name(i, "location", "ref"),
     result_indicator_baseline_value = xml_attr_by_name(i, ".", "baseline", "value"),
     result_indicator_baseline_year = xml_attr_by_name(i, ".", "baseline", "year"),
     result_indicator_baseline_date = xml_attr_by_name(i, ".", "baseline", "iso-date"),
-    result_indicator_baseline_location_ref = xml_child_attr_by_name(i, "location", "ref"),
+
     result_indicator_baseline_dimension_1 = xml_child_attr_by_name(i, "dimension", "name", 1),
     result_indicator_baseline_dimension_value_1 = xml_child_attr_by_name(i, "dimension", "value", 1),
-    result_indicator_baseline_dimension_2 = xml_child_attr_by_name(i,"dimension", "name", 2),
+    result_indicator_baseline_dimension_2 = xml_child_attr_by_name(i, "dimension", "name", 2),
     result_indicator_baseline_dimension_value_2 = xml_child_attr_by_name(i, "dimension", "value", 2),
+
+   ## Check period... 
+
+    ## First time for the period...
     result_indicator_period_start = xml_attr_by_name(i, "period-start", "period-start", "iso-date"),
     result_indicator_period_end = xml_attr_by_name(i, "period-end", "period-end", "iso-date"),
+
+    ## Value for target
     result_indicator_target_value = xml_attr_by_name(i, "target", "target", "value"),
     result_indicator_target_location_ref = xml_attr_by_name(i, "target/location", "location", "ref"),
     result_indicator_target_dimension_1 = xml_attr_by_name(i, "./target/dimension", "dimension", "name", 1),
     result_indicator_target_value_1 = xml_attr_by_name(i, "./target/dimension", "dimension", "value", 1),
     result_indicator_target_dimension_2 = xml_attr_by_name(i, "./target/dimension", "dimension", "name", 2),
-    result_indicator_target_value_2 = xml_attr_by_name(i, "./target/dimension", "dimension", "value", 2)
+    result_indicator_target_value_2 = xml_attr_by_name(i, "./target/dimension", "dimension", "value", 2),
+
+   ## Value for actual
+   result_indicator_actual_value = xml_attr_by_name(i, "actual", "actual", "value"),
+   result_indicator_actual_location_ref = xml_attr_by_name(i, "actual/location", "location", "ref"),
+   result_indicator_actual_dimension_1 = xml_attr_by_name(i, "./actual/dimension", "dimension", "name", 1),
+   result_indicator_actual_value_1 = xml_attr_by_name(i, "./actual/dimension", "dimension", "value", 1),
+   result_indicator_actual_dimension_2 = xml_attr_by_name(i, "./actual/dimension", "dimension", "name", 2),
+   result_indicator_actual_value_2 = xml_attr_by_name(i, "./actual/dimension", "dimension", "value", 2)
+
+
   )
 
 })