Only look at Melbourne.

[R/project-au-taxstats.git] / AU-taxstats.R

diff --git a/AU-taxstats.R b/AU-taxstats.R
index bda1448b4102219f7a2f3c9d98d03c4a8cf012a9..728c943c07940bd9c7a0770ece8a28d48b219774 100644 (file)
--- a/AU-taxstats.R
+++ b/AU-taxstats.R
@@ -44,13 +44,18 @@ taxstats.sa3 <- merge(x = taxstats, y = sa3, by.x = "Postcode", by.y = "POA_CODE
 # Create a matrix of intersecting postal codes and SA3's
 
 POA_SAs <- st_intersects(x=sa3, y=POA, sparse=FALSE)
-taxstats.POA$incomeperearningcapita[is.na(taxstats.POA$incomeperearningcapita)] <- 0
-
+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$incomeperearningcapita <- as.vector(POA_SAs %*% as.matrix(taxstats.POA$incomeperearningcapita))
+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
+
+# As SA3s are still to narrow around cities compared to in the country,
+# let's simply look at Melbourne
 
-ggplot(sa3) +
+ggplot(dplyr::filter(sa3, data.table::`%like%`(GCC_NAME16, "Melbourne") )) +
   geom_sf(aes(fill = incomeperearningcapita, color = incomeperearningcapita)) +
   scale_fill_viridis("incomeperearningcapita") +
   scale_color_viridis("incomeperearningcapita")