R/plot_reg_prop_origin.R

In Edouard-Legoupil/unhcrdatapackage: UNHCR Population Statistics Database with Chart Library and Factsheet Template

# WARNING - Generated by {fusen} from /dev/dev_plot_Region.Rmd: do not edit by hand

#' Proportion of the population who are refugees, by country of origin 
#' 
#' The proportion of a country???s population who become refugees is SDG indicator 10.7.4 
#' it consistutes is a useful way to identify the countries of origin producing the most refugees relative to their number of inhabitants.
#' 
#' @param year Numeric value of the year (for instance 2020)
#' @param region Character value with the related UNHCR bureau - when left null, it will display the whole world
#' 
#' @importFrom ggplot2  ggplot  aes  coord_flip   element_blank element_line
#'             element_text expansion geom_bar geom_col geom_hline unit stat_summary
#'             geom_label geom_text labs  position_stack  scale_color_manual scale_colour_manual 
#'             geom_text
#'             scale_fill_manual scale_x_continuous scale_x_discrete  scale_y_continuous   sym theme 
#' @importFrom dplyr  desc select  case_when lag mutate group_by filter summarise ungroup
#'               pull distinct n arrange across slice left_join
#' @importFrom stringr str_replace               
#' @importFrom WDI WDI          
#' @importFrom forcats fct_reorder    
#' @importFrom unhcrthemes theme_unhcr
#' 
#' @return a ggplot2 object
#' 
#' @export
 
#' @examples
#' plot_reg_prop_origin(year = 2022,  region = "Americas")
plot_reg_prop_origin <- function(year = 2022,  region = "Americas"){
  

  ## World bank API to retrieve total population
  # wb_data <- wbstats::wb( indicator = c("SP.POP.TOTL", "NY.GDP.MKTP.CD",
  #                                     "NY.GDP.PCAP.CD", "NY.GNP.PCAP.CD"),
  #              startdate = 1990, 
  #              enddate = year, 
  #              return_wide = TRUE)
  # 
  # # Renaming variables for further matching
  # names(wb_data)[1] <- "iso_3"
  # names(wb_data)[2] <- "Year"
  
  wb_data <- WDI::WDI(country='all' ,
                      indicator=c("SP.POP.TOTL", "NY.GDP.MKTP.CD",
                                  "NY.GDP.PCAP.CD", "NY.GNP.PCAP.CD"),
                      start = 1990, 
                      end = year,
                      extra = TRUE)   
  # Renaming variables for further matching
  names(wb_data)[3] <- "iso3c"
  names(wb_data)[4] <- "Year"  
      
      
      wb_data$Year <- as.numeric(wb_data$Year)
  
  
  departed <- dplyr::left_join( x= ForcedDisplacementStat::end_year_population_totals_long, 
                                                     y= ForcedDisplacementStat::reference, 
                                                     by = c("CountryOriginCode" = "iso_3")) |> 
    dplyr::filter(Population.type  %in% c("REF","ASY","OIP") & 
           Year ==  year &
           UNHCRBureau  == region #&
           #!(is.na(UNHCRBureau))
           ) |>
    dplyr::group_by(CountryOriginName, CountryOriginCode) |>
    dplyr::summarise(Value2 = sum(Value) )  |>
    #mutate( value3 =  format_si(Value2))|>
    dplyr::mutate(CountryOriginName = stringr::str_replace(CountryOriginName, 
                                                           " \\(Bolivarian Republic of\\)", "")) |>
    
    ## Now merge with WB Data 
    dplyr::left_join(wb_data |> 
                       dplyr::select("SP.POP.TOTL","iso3c", "Year")|>
                       dplyr::filter(Year ==  year-1), 
                     by = c(  "CountryOriginCode" = "iso3c"    ))|>  
    dplyr::mutate(ref.part = round(Value2/(SP.POP.TOTL+Value2),4)  ) |>
    dplyr::arrange(desc(ref.part))|>
    head(10)  
  
p <- ggplot(departed,
                 aes( x= ref.part, forcats::fct_reorder(CountryOriginName, ref.part))) +
  
   geom_col(fill = "#0072BC") +
  
  # geom_col( fill = ifelse(departed$CountryOriginCode %in% c("VEN"), "#0072BC", "#CCCCCC")) +
  
  geom_label(aes(label = scales::label_percent(accuracy = .1)(ref.part) ),
             color = "black", hjust = "inward") +
  scale_x_continuous(labels = scales::label_percent(accuracy = .1)) +
  labs(x = NULL, 
       y = NULL,
       title = stringr::str_wrap(paste0("Number of refugees, asylum seekers & displaced across borders by country of origin in", region), 60),
       subtitle =    stringr::str_wrap( "Top 10 Countries, as a proportion of the national population of that country of origin (SDG indicator 10.7.4)", 80),
         caption = stringr::str_wrap("Source: UNHCR.org/refugee-statistics. \n Total count of population who have been recognized as refugees as a proportion of the total population of their country of origin, expressed per 100,000 population. Refugees refers to persons recognized by the Government and/or UNHCR, or those in a refugee-like situation.  Population refers to total resident population in a given country in a given year."), 100) +
  
     
  unhcrthemes::theme_unhcr(grid = "X", 
              axis = "y", 
              axis_title = "x",
              font_size = 14)  

return(p)
    
}