AU-taxstats.R

   1 install.packages("sf")
   2 library(sf)
   3 install.packages("devtools")
   4 devtools::install_github("tidyverse/ggplot2") # needed for geom_sf
   5 library(ggplot2)
   6 library(viridis)
   7
   8 # Obtain the tax dataset if not available yet
   9 if(!file.exists("data/taxstats2015individual06ataxablestatusstateterritorypostcode.csv"))
  10   download.file(url = "http://data.gov.au/dataset/5c99cfed-254d-40a6-af1c-47412b7de6fe/resource/90f7f4eb-2c44-4884-96c0-01060c820cfd/download/taxstats2015individual06ataxablestatusstateterritorypostcode.csv", destfile = "data/taxstats2015individual06ataxablestatusstateterritorypostcode.csv")
  11 # http://data.gov.au/dataset/5c99cfed-254d-40a6-af1c-47412b7de6fe/resource/d3189e9d-533a-4893-b6a1-758781083418/download/taxstats2015individual06btaxablestatusstateterritorypostcode.csv
  12
  13 # Obtain shapefile with Australian postal codes if not available yet
  14 if(!file.exists("data/1270055003_poa_2016_aust_shape.zip"))
  15   download.file(url = "http://www.abs.gov.au/ausstats/subscriber.nsf/log?openagent&1270055003_poa_2016_aust_shape.zip&1270.0.55.003&Data%20Cubes&4FB811FA48EECA7ACA25802C001432D0&0&July%202016&13.09.2016&Latest", destfile = "data/1270055003_poa_2016_aust_shape.zip")
  16 # Unzip it if not done already
  17 if(!file.exists("data/POA_2016_AUST.shp"))
  18   unzip(zipfile = "data/1270055003_poa_2016_aust_shape.zip", exdir = "data/")
  19
  20 taxstats <- read.csv("data/taxstats2015individual06ataxablestatusstateterritorypostcode.csv", stringsAsFactors = FALSE)
  21 taxstats <- dplyr::filter(taxstats, Taxable.status == "Taxable")
  22 POA <- st_read(dsn = "data/", layer = "POA_2016_AUST", stringsAsFactors = FALSE)
  23
  24 taxstats.POA <- merge(x = taxstats, y = POA, by.x = "Postcode", by.y = "POA_CODE16", all.y = TRUE)
  25
  26 taxstats.POA$incomeperearningcapita <- taxstats.POA$`Total.Income.or.Loss..` / taxstats.POA$Total.Income.or.Loss.no.
  27 # Postal codes turn out not to be too interesting, as they're way more granular around
  28 # big cities - making the high income postal codes invisible on the chart below
  29 ggplot(taxstats.POA) +
  30   geom_sf(aes(fill = incomeperearningcapita, color = incomeperearningcapita)) +
  31   scale_fill_viridis("incomeperearningcapita") +
  32   scale_color_viridis("incomeperearningcapita")
  33
  34 # Let's try by SA3
  35 if(!file.exists("data/1270055001_sa3_2016_aust_shape.zip"))
  36   download.file(url = "http://www.abs.gov.au/AUSSTATS/subscriber.nsf/log?openagent&1270055001_sa3_2016_aust_shape.zip&1270.0.55.001&Data%20Cubes&43942523105745CBCA257FED0013DB07&0&July%202016&12.07.2016&Latest", destfile = "data/1270055001_sa3_2016_aust_shape.zip")
  37
  38 if(!file.exists("data/SA3_2016_AUST.shp"))
  39   unzip(zipfile = "data/1270055001_sa3_2016_aust_shape.zip", exdir = "data/")
  40
  41 sa3 <- st_read(dsn = "data/", layer = "SA3_2016_AUST", stringsAsFactors = FALSE)
  42 taxstats.sa3 <- merge(x = taxstats, y = sa3, by.x = "Postcode", by.y = "POA_CODE16", all.y = TRUE)
  43
  44 # Create a matrix of intersecting postal codes and SA3's
  45
  46 POA_SAs <- st_intersects(x=sa3, y=POA, sparse=FALSE)
  47 taxstats.POA$incomeperearningcapita[is.na(taxstats.POA$incomeperearningcapita)] <- 0
  48
  49 # Perform matrix multiplication to obtain the income metrix per SA3
  50 # Total income will be incorrect, as the POAs intersect with multiple SA3s
  51 sa3$incomeperearningcapita <- as.vector(POA_SAs %*% as.matrix(taxstats.POA$incomeperearningcapita))
  52
  53 ggplot(sa3) +
  54   geom_sf(aes(fill = incomeperearningcapita, color = incomeperearningcapita)) +
  55   scale_fill_viridis("incomeperearningcapita") +
  56   scale_color_viridis("incomeperearningcapita")