X-Git-Url: http://git.vanrenterghem.biz/R/project-au-taxstats.git/blobdiff_plain/0957ee3cd1a3bf1a9c046c73ef8b0ef8b81b91d2..26a2a71b8ad239147ec5bc61915ec1237832bd87:/AU-taxstats.R

diff --git a/AU-taxstats.R b/AU-taxstats.R
index 728c943..1ca7b75 100644
--- a/AU-taxstats.R
+++ b/AU-taxstats.R
@@ -4,6 +4,8 @@ install.packages("devtools")
 devtools::install_github("tidyverse/ggplot2") # needed for geom_sf
 library(ggplot2)
 library(viridis)
+library(ggthemes)
+library(animation) # for saveGIF
 
 # Obtain the tax dataset if not available yet
 if(!file.exists("data/taxstats2015individual06ataxablestatusstateterritorypostcode.csv")) 
@@ -39,23 +41,44 @@ 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
+# Perform matrix multiplication to obtain the income metrics 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$TotalIncomeEarners
+sa3$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") )) +
+cities = c("Perth","Melbourne","Sydney","Adelaide","Brisbane")
+
+# Create a plot for each of these cities. This is wrapped in a function
+# for use by saveGIF
+
+plots <- function() {lapply(cities, function(x){
+ plot <- ggplot(dplyr::filter(sa3, data.table::`%like%`(GCC_NAME16, x) )) +
   geom_sf(aes(fill = incomeperearningcapita, color = incomeperearningcapita)) +
-  scale_fill_viridis("incomeperearningcapita") +
-  scale_color_viridis("incomeperearningcapita")
+  scale_fill_viridis(name = "",
+                     limits = c(min(sa3$incomeperearningcapita, na.rm = TRUE),max(sa3$incomeperearningcapita, na.rm = TRUE))) +
+  scale_color_viridis(name = "",
+                                limits = c(min(sa3$incomeperearningcapita, na.rm = TRUE),max(sa3$incomeperearningcapita, na.rm = TRUE))) +
+  coord_sf(datum = NA) + # Work around https://github.com/tidyverse/ggplot2/issues/2071 to remove gridlines
+  labs(title = paste0(x," \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())
+ print(plot)
+})
+}
+
+saveGIF(plots(),movie.name = "AUCitiesIncomeDistribution.gif", interval = 2, loop = 2)