Population estimates for specific age groups

.gitignore

@@ -12,3 +12,6 @@ data/raw/*
 *.xls*
 *.RData
 *.rds
+
+# Ignore output
+output/

lastest-prerelease

@@ -0,0 +1 @@
+v0.0.1

scripts/collect-raw-municipality.R

@@ -140,7 +140,7 @@ file.remove(file_list)
 
 
 #------------------------------------------------------------------------------*
-# Collect data from 2000-2010 period ----
+# Collect data from 2011-2015 period ----
 #------------------------------------------------------------------------------*
 
 # Zip path
@@ -178,20 +178,40 @@ read_population_2011 <- function(file_path, skip = 3){
     # Report sheet (year)
     cat(" ", sheet)
 
-    fixes <- c(
+
+    #--------------------------------------------------------------------------*
+    # Fix parameters for specific files / sheets
+    #--------------------------------------------------------------------------*
+
+    # Fix individual skip parameters
+    fixes_skip <- c(
       "Totonicapan", "Suchitepequez", "Retalhuleu", "Quiche", "Alta Verapaz",
       "Peten", "Jutiapa", " Jalapa", "Chiquimula", "Izabal", "Santa Rosa"
     )
 
-    # Configuration exceptions
     skip <- case_when(
-      # department == "Santa Rosa" & sheet == "2012" ~ 4,
-      # department == "Santa Rosa" & sheet == "2015" ~ 5,
-      department %in% fixes & sheet == "2012" ~ 4,
-      department %in% fixes & sheet == "2015" ~ 5,
+      department %in% fixes_skip & sheet == "2012" ~ 4,
+      department %in% fixes_skip & sheet == "2015" ~ 5,
       TRUE ~ skip
     )
 
+    # Fix missing municipality names
+    fix_municipalities <- function(.data){
+      .data %>%
+        # Setup fixing rules
+        mutate(
+          municipality = case_when(
+            department == "Santa Rosa" & grepl("^X", municipality) ~ "Nueva Santa Rosa",
+            TRUE ~ municipality
+          )
+        ) %>%
+        return()
+    }
+
+    #--------------------------------------------------------------------------*
+    # Get data
+    #--------------------------------------------------------------------------*
+
     # Read file contents
     pop_sheet <- read_excel(
       path = file, sheet = sheet, skip = skip_lines , na = "?"
@@ -230,6 +250,8 @@ read_population_2011 <- function(file_path, skip = 3){
         ),
         department = department
       ) %>%
+      # Fix missingmunicipality names
+      fix_municipalities() %>%
       select(year, department, municipality, sex = sexo, age, population) %>%
       mutate(
         # Fix factors
@@ -568,12 +590,13 @@ pop_2016_2020 <- pop_2016_2020_predicted %>%
 population <- pop_2000_2015 %>%
   bind_rows(pop_2016_2020)
 
+processed_file <- "data/processed/gt_2000_2020_municipality_population.RData"
+
 # Save population data for use in R
 save(
-  population, file = "data/processed/gt_2000_2020_municipality_population.RData"
+  population, file = processed_file
 )
 
-
-
+cat(processed_file)
 
 # End of script