In Emaasit/ebolaCases: Exploring Election and Census Highly Informative Data Nationally for Australia

knitr::opts_chunk$set(fig.width = 6,
                      fig.height = 4,
                      fig.align='center',
                      dev = "png")

Introduction

eechidna (Exploring Election and Census Highly Informative Data Nationally for Australia) is an R package that makes it easy to look at the data from the 2011 Australian Census, and the 2013 Federal Election.

This vignette documents how to access the data from the 2011 Census. We show a few typical methods to explore the data.

2011 Census data

The data is loaded as abs2011 when you load eechidna. Let's look take a brief glimpse of the data.

library(eechidna)
library(plyr)
library(dplyr)

glimpse(abs2011)

Here we see that we have 150 observations and 35 variables.

Each observation is data pertaining to a particular federal electorate as described by http://www.aec.gov.au/profiles/.

Each column is now described here:

data_dictionary <- data_frame(
  Variable = c(
    "ID",
    "Electorate",
    "State",
    "Population",
    "Area",
    "MedianIncome",
    "Unemployed",
    "Bachelor",
    "Postgraduate",
    "Christianity",
    "Catholic",
    "Buddhism",
    "Islam",
    "Judaism",
    "NoReligion",
    "Age00_04",
    "Age05_14",
    "Age15_19",
    "Age20_24",
    "Age25_34",
    "Age35_44",
    "Age45_54",
    "Age55_64",
    "Age65_74",
    "Age75_84",
    "Age85plus",
    "BornOverseas",
    "Indigenous",
    "EnglishOnly",
    "OtherLanguageHome",
    "Married",
    "DeFacto",
    "FamilyRatio",
    "Internet", 
    "NotOwned"
    ), 
  Details = c(
    "Commonwealth Electoral District identifier",
    "Name of electorate",
    "State containing electorate",
    "Total population of electorate",
    "Area of electorate in square kilometres",
    "Median income of people within electorate",
    "Percentage of people unemployed",
    "Percentage of people whose highest qualification is a Bachelor degree",
    "Percentage of people whose highest qualification is a postgraduate degree",
    "Percentage of people affiliated with the Christian religion (of all denominations)",
    "Percentage of people affiliated with the Catholic denomimation.",
    "Percentage of people affiliated with the Buddhist religion.",
    "Percentage of people affiliated with the Islam religion.",
    "Percentage of people affiliated with the Jewish religion. ",
    "Percentage of people with no religion.",
    "Percentage of people aged 0-4.",
    "Percentage of people aged 5-9.",
    "Percentage of people aged 15-19.",
    "Percentage of people aged 20-24.",
    "Percentage of people aged 25-34.",
    "Percentage of people aged 35-44.",
    "Percentage of people aged 45-54.",
    "Percentage of people aged 55-64.",
    "Percentage of people aged 65-74.",
    "Percentage of people aged 75-84.",
    "Percentage of people aged 85 or higher.",
    "Percentage of people born outside Australia.",
    "Percentage of people who are Indigenous",
    "Percentage of people who speak only English",
    "Percentage of people who speak a language other than English at home",
    "Percentage of people who are married",
    "Percentage of people who are in a de facto marriage",
    "Total number of families to total number of people (times 100)",
    "Percentage of people with home internet",
    "Percentage of dwellings not owned (either outright or with a mortgage)")
) # close data_frame

library(knitr)
kable(data_dictionary)

So let's just look at some nice and simple plots using ggplot2.

Unemployment

library(ggplot2)

ggplot(data = abs2011,
       aes(x = Unemployed)) + 
  geom_density(fill = "salmon", 
               bw = "SJ",
               colour = NA) + 
  geom_rug(colour = "salmon") +
  theme_minimal() +
  xlim(0, 12)

Unemployment by state

ggplot(data = abs2011,
       aes(x = reorder(State, -Unemployed),
           y = Unemployed,
           colour = State)) + 
  geom_boxplot() + 
  labs(x = "State",
       y = "% Unemployment") + 
  theme_minimal() + 
  theme(legend.position = "none") 

Age

ggplot(data = abs2011,
       aes(x = Age00_04)) +
   geom_density(fill = "steelblue",
               bw = "SJ",
               colour = NA) + 
  xlim(3,11) +
  geom_rug(colour = "steelblue") + 
  theme_minimal() +
  labs(x = "% Aged between 0 and 4")

ggplot(data = abs2011,
       aes(x = reorder(State, -Age00_04),
           y = Age00_04,
           colour = State)) +
  geom_boxplot() + 
  theme_minimal() +
  labs(x = "State",
       y = "% Aged between 0 and 4") +
  theme(legend.position = "none") + 
  coord_flip()

However, there are many age groups. To look at all of them at once, we can gather them into a dataframe ready for plotting using tidyr.

library(tidyr)

abs2011 %>%
  select(starts_with("Age"), 
         Electorate) %>%
  gather(key = "Age",
         value = "Percent_in_electorate",
         -Electorate) %>% 
  ggplot(data = .,
         aes(x = reorder(Age, - Percent_in_electorate),
             y = Percent_in_electorate,
             colour = Age)) +
  geom_boxplot() + 
  coord_flip() + 
  theme_minimal() + 
  theme(legend.position = "none") +
  labs(x = "Age Groups",
       y = "% in Electorate")

Income

ggplot(data = abs2011,
       aes(x = MedianIncome)) + 
  geom_density(fill = "salmon",
               bw = "SJ",
               colour = NA) + 
  xlim(250,1100) +
  geom_rug(colour = "salmon") + 
  theme_minimal()

Income by State

ggplot(data = abs2011,
       aes(x = reorder(State, -MedianIncome),
           y = MedianIncome,
           colour = State)) + 
  geom_boxplot() + 
  theme_minimal() + 
  theme(legend.position = "none") + 
  labs(x = "State")

If you're intersted in getting a sense of the distribution of the data, you can add in the points to get a bit more of a sense on the distribution.

ggplot(data = abs2011,
       aes(x = reorder(State, -MedianIncome),
           y = MedianIncome,
           colour = State)) + 
  geom_boxplot() + 
  geom_jitter(alpha = 0.35, 
              size = 2,
              width = 0.3) +
  theme_minimal() + 
  theme(legend.position = "none") + 
  labs(x = "State")

Education

Bachelor

ggplot(data = abs2011,
       aes(x = Bachelor)) +
  geom_density(fill = "salmon",
               bw = "SJ",
               colour = NA) + 
  geom_rug(colour = "salmon") + 
  theme_minimal() + 
  labs(x = "% of electorate with a Bachelor degree") +
  xlim(0, 30)

Bachelor by state

ggplot(data = abs2011,
       aes(x = reorder(State, -Bachelor),
           y = Bachelor,
           colour = State)) +
  geom_boxplot() +
  theme_minimal() +
  labs(x = "State") + 
  theme(legend.position = "none")

Bachelor and income

ggplot(data = abs2011,
       aes(x = Bachelor,
           y = MedianIncome)) + 
  geom_point(colour = "steelblue",
             alpha = 0.75) + 
  theme_minimal()

Postgraduate

ggplot(data = abs2011,
       aes(x = reorder(State, -Postgraduate),
           y = Postgraduate,
           colour = State)) +
  geom_boxplot() +
  theme_minimal() +
  labs(x = "State") + 
  theme(legend.position = "none")

Postgraduate and income

ggplot(data = abs2011,
       aes(x = Postgraduate,
           y = MedianIncome)) + 
  geom_point(colour = "steelblue",
             alpha = 0.75) + 
  theme_minimal()

Comparing income across Bachelors and postgraduate

abs2011 %>%
  select(Postgraduate,
         Bachelor,
         MedianIncome) %>% 
  gather(key = "Education",
         value = "Prop_Educated",
         -MedianIncome) %>%
ggplot(data = ,
       aes(x = Prop_Educated,
           y = MedianIncome,
           colour = Education)) + 
  geom_point() + 
  geom_smooth() +
  theme_minimal() +
  scale_color_brewer(type = "qual", palette = "Set1")
  # theme(legend.position = "bottom",
  #       legend.direction = "vertical")

Religion

Let's look at all of the religions

abs2011 %>%
  select(Christianity,
         Catholic,
         Buddhism,
         Islam,
         Judaism,
         NoReligion) %>%
  gather(key = "ReligionType",
         value = "Percent") %>%
  ggplot(data = .,
         aes(x = reorder(ReligionType, -Percent),
             y = Percent,
             colour = ReligionType)) + 
  geom_boxplot() + 
  theme_minimal() + 
  theme(legend.position = "none") +
  coord_flip() + 
  labs(x = "Religion")

Christianity by State

ggplot(data = abs2011,
       aes(x = reorder(State, -Christianity),
           y = Christianity,
           colour = State)) + 
  geom_boxplot() +
  theme_minimal() +
  theme(legend.position = "none") +
  coord_flip() + 
  labs(x = "State")

Internet

ggplot(data = abs2011,
       aes(x = Internet)) +
  geom_density(fill = "steelblue",
               bw = "SJ",
               colour = NA) + 
  geom_rug(colour = "steelblue") + 
  theme_minimal() + 
  labs(x = "% of electorate with Internet") +
  xlim(85, 100)

Internet by state

ggplot(data = abs2011,
       aes(x = reorder(State, -Internet),
           y = Internet,
           colour = State)) + 
  geom_boxplot() +
  theme_minimal() +
  theme(legend.position = "none") +
  coord_flip() + 
  labs(x = "State")

Emaasit/ebolaCases documentation built on May 6, 2019, 3:46 p.m.