Plot by postal codes.

diff --git a/AU-taxstats.R b/AU-taxstats.R
new file mode 100644 (file)
index 0000000..d5e3c82
--- /dev/null
+++ b/AU-taxstats.R
@@ -0,0 +1,32 @@
+install.packages("sf")
+library(sf)
+install.packages("devtools")
+devtools::install_github("tidyverse/ggplot2") # needed for geom_sf
+library(ggplot2)
+library(viridis)
+
+# Obtain the tax dataset if not available yet
+if(!file.exists("data/taxstats2015individual06ataxablestatusstateterritorypostcode.csv")) 
+  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")
+# http://data.gov.au/dataset/5c99cfed-254d-40a6-af1c-47412b7de6fe/resource/d3189e9d-533a-4893-b6a1-758781083418/download/taxstats2015individual06btaxablestatusstateterritorypostcode.csv
+
+# Obtain shapefile with Australian postal codes if not available yet
+if(!file.exists("data/1270055003_poa_2016_aust_shape.zip"))
+  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")
+# Unzip it if not done already
+if(!file.exists("data/POA_2016_AUST.shp")) 
+  unzip(zipfile = "data/1270055003_poa_2016_aust_shape.zip", exdir = "data/")
+
+taxstats <- read.csv("data/taxstats2015individual06ataxablestatusstateterritorypostcode.csv", stringsAsFactors = FALSE)
+taxstats <- dplyr::filter(taxstats, Taxable.status == "Taxable")
+POA <- st_read(dsn = "data/", layer = "POA_2016_AUST", stringsAsFactors = FALSE)
+
+taxstats.POA <- merge(x = taxstats, y = POA, by.x = "Postcode", by.y = "POA_CODE16", all.y = TRUE)
+
+taxstats.POA$incomeperearningcapita <- taxstats.POA$`Total.Income.or.Loss..` / taxstats.POA$Total.Income.or.Loss.no. 
+# Postal codes turn out not to be too interesting, as they're way more granular around 
+# big cities - making the high income postal codes invisible on the chart below
+ggplot(taxstats.POA) +
+  geom_sf(aes(fill = incomeperearningcapita, color = incomeperearningcapita)) +
+  scale_fill_viridis("incomeperearningcapita") +
+  scale_color_viridis("incomeperearningcapita")