X-Git-Url: http://git.vanrenterghem.biz/R/project-au-taxstats.git/blobdiff_plain/0f950959cbac331187ccafaece1b834daf0a432a..a4d86b2c1b034830351c7d5d9e72a1acb2d36a29:/AU-taxstats.R

diff --git a/AU-taxstats.R b/AU-taxstats.R
index d5e3c82..76f9dcf 100644
--- a/AU-taxstats.R
+++ b/AU-taxstats.R
@@ -4,6 +4,7 @@ install.packages("devtools")
 devtools::install_github("tidyverse/ggplot2") # needed for geom_sf
 library(ggplot2)
 library(viridis)
+library(ggthemes)
 
 # Obtain the tax dataset if not available yet
 if(!file.exists("data/taxstats2015individual06ataxablestatusstateterritorypostcode.csv")) 
@@ -30,3 +31,42 @@ ggplot(taxstats.POA) +
   geom_sf(aes(fill = incomeperearningcapita, color = incomeperearningcapita)) +
   scale_fill_viridis("incomeperearningcapita") +
   scale_color_viridis("incomeperearningcapita")
+
+# Let's try by SA3
+if(!file.exists("data/1270055001_sa3_2016_aust_shape.zip")) 
+  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")
+
+if(!file.exists("data/SA3_2016_AUST.shp")) 
+  unzip(zipfile = "data/1270055001_sa3_2016_aust_shape.zip", exdir = "data/")
+
+sa3 <- st_read(dsn = "data/", layer = "SA3_2016_AUST", stringsAsFactors = FALSE)
+taxstats.sa3 <- merge(x = taxstats, y = sa3, by.x = "Postcode", by.y = "POA_CODE16", all.y = TRUE)
+
+# Create a matrix of intersecting postal codes and SA3's
+
+POA_SAs <- st_intersects(x=sa3, y=POA, sparse=FALSE)
+taxstats.POA$`Total.Income.or.Loss..`[is.na(taxstats.POA$`Total.Income.or.Loss..`)] <- 0
+taxstats.POA$`Total.Income.or.Loss.no.`[is.na(taxstats.POA$`Total.Income.or.Loss.no.`)] <- 0
+# Perform matrix multiplication to obtain the income metrix per SA3
+# Total income will be incorrect, as the POAs intersect with multiple SA3s
+sa3$TotalIncome <- as.vector(POA_SAs %*% as.matrix(taxstats.POA$`Total.Income.or.Loss..`))
+sa3$TotalIncomeEarners <- as.vector(POA_SAs %*% as.matrix(taxstats.POA$`Total.Income.or.Loss.no.`))
+sa3$incomeperearningcapita <- (sa3$TotalIncome / sa3$TotalIncomeEarners)/1000
+
+# As SA3s are still to narrow around cities compared to in the country,
+# let's simply look at Melbourne
+
+ggplot(dplyr::filter(sa3, data.table::`%like%`(GCC_NAME16, "Melbourne") )) +
+  geom_sf(aes(fill = incomeperearningcapita, color = incomeperearningcapita)) +
+  scale_fill_viridis(name = "") +
+  scale_color_viridis(name = "") +
+  coord_sf(datum = NA) + # Work around https://github.com/tidyverse/ggplot2/issues/2071 to remove gridlines
+  labs(title = "Melbourne \nincome distribution",
+       subtitle = "2014/15, in 1000s AUD",
+       caption = "\nSource: Australian Taxation Office") +
+  theme_economist() +
+  theme(legend.position = "bottom",
+        legend.text = element_text(angle = 45, hjust = 1, size = 8),
+        axis.text = element_blank(),
+        axis.ticks = element_blank()) 
+