IS428 - Assignment 4

Student ID: 01312830

What is the demographic distribution of residents’ property types across various age groups in Singapore (2019)?

1. Describe the major data and design challenges faced in accomplishing the task, and how you plan to overcome these challenges with a proposed sketched design. (3 marks)

#	Type	Description	Resolution
1	Design	Difficulty in getting initial visualization of gender vs TOD across age groups Facet wrap layout too cluttered and does not offer discernible insights	Explore alternative plots e.g. population pyramids Consider using colour gradient scheme to separate TOD instead of having individual plots for each TOD
2	Design / Data	Difficulty in distinguishing between each gender within a standard bar plot Both genders get summed up in the same side of the X Axis, thereby providing no distinguishing factor	Assign negative values to population count of one gender in order to separate graph into “Left” and “Right” sides Utilize coord_flip() in conjunction with the above
3	Design / Data	Default sorting for age bins is out of order E.g. 5-9 is in the middle of the plot Makes it difficult to accurately interpret demographic data on first glance	Utilize “mutate” and “factor” from dplyr library in order to manipulate data source label order
4	Design / Data	Default scaling for x-axis does not give an accurate representation of the actual numbers of the graph X-axis scale is extremely cluttered and unreadable, labels are cluttered together and hard to interpret	Experiment with different x-axis scles using scale_y_continuous attribute

Design Sketch Proposed

2. Provide step-by-step description on how the data visualisation was prepared by using gplot2 and other related R packages. (3 marks)

Step 1

1.1 Import Required Packages - tidyverse, dplyr, ggplot2 and dataset(using read_csv)

1.2 Add options(scipen=10000) to remove negative x-axis values for population pyramid

packages = c('tidyverse', 'dplyr', 'ggplot2')
for (p in packages){
  if(!require(p, character.only = T)){
  install.packages(p)
  }
  library(p, character.only = T)
}
library(ggplot2)
library(dplyr)
options(scipen=10000)
pop_data <- read_csv("data/respopagesextod2011to2020.csv")

Step 2

2.1 Create “males” and “females” dataframe using dplyr

2.2 For each gender’s dataframe, filter for time==‘2019’

2.3 Arrange data in ascending order according to “pop”

2.4 Using Mutate and Factor, arrange age groups in ascending order

males <- pop_data %>%
  filter(., Sex=='Males' & Time=='2019')%>%
  arrange(., Pop)%>%
  mutate(AG = factor(AG, levels=c("0_to_4","5_to_9", "10_to_14","15_to_19","20_to_24","25_to_29","30_to_34","35_to_39","40_to_44","45_to_49","50_to_54","55_to_59","60_to_64","65_to_69","70_to_74","75_to_79","80_to_84","85_to_89","90_and_over")))

females <- pop_data %>%
  filter(., Sex=='Females' & Time=='2019')%>%
  mutate(., Pop = Pop * -1)%>%
  arrange(., Pop)%>%
  mutate(AG = factor(AG, levels=c("0_to_4","5_to_9", "10_to_14","15_to_19","20_to_24","25_to_29","30_to_34","35_to_39","40_to_44","45_to_49","50_to_54","55_to_59","60_to_64","65_to_69","70_to_74","75_to_79","80_to_84","85_to_89","90_and_over")))

Step 3

3.1 Manipulate pop_data dataframe

3.2 Filter time == ‘2019’ and arrange data in ascending order, according to ‘pop’ variable

3.3 Using Mutate and Factor, arrange age groups in ascending order

pop_data <- pop_data %>%
  filter(., Time=='2019')%>%
  arrange(., Pop)%>%
  mutate(AG = factor(AG, levels=c("0_to_4","5_to_9", "10_to_14","15_to_19","20_to_24","25_to_29","30_to_34","35_to_39","40_to_44","45_to_49","50_to_54","55_to_59","60_to_64","65_to_69","70_to_74","75_to_79","80_to_84","85_to_89","90_and_over")))

Step 4

4.1 Insert geom_bar plot for males and females respectively

4.2 Set continuous y-axis scale and flip coordinates

4.3 Insert Data Labels and Data Source and Legends

ggplot(data=pop_data,aes(x=AG, fill=TOD)) + 
  
  geom_bar(data=females, aes(y=Pop), stat='identity')+
  geom_bar(data=males, aes(y=Pop), stat='identity')+
  scale_y_continuous(breaks=seq(-300000,300000,100000),labels=abs(seq(-300000,300000,100000)))+
  coord_flip()+
  xlab('Age Group') + 
  ylab('Females                                   Males \nPopulation Count') + 
  ggtitle('Population Pyramid - Age Groups vs Gender vs Type of Dwelling (2019)')+
  labs(fill = "Type of Dwelling")

Data Source: https://www.singstat.gov.sg/find-data/search-by-theme/population/geographic-distribution/latest-data

3. The final data visualization and a short description of not more than 350 words. The description must provide at least two useful information revealed by the data visualization. (4 marks)

Aim of data visualization: Illustrate the breakdown of Singapore’s Demographics, in terms of the following 3 categories: Age Group, Gender, Type of Dwelling

Description:

- A population pyramid has been used for the above-mentioned data visualization, with females on the left axis and males on the right axis.

- The age groups have been arranged bottom-up, in ascending order

- For every age group, a colour gradient is included to separate between different types of dwelling

- The Y-Axis represents the age group bins

- The X-Axis represents the population count per age group

Useful Information 1 - Ageing Population

The data visualization reveals an “beehive” shape, that is wider in the middle compared to the rest of the visualization, showing that majority of the population sits in the 30-34 -> 60-64 age groups. This shows that Singapore is experiencing an ageing population whereby an increasing proportion of its population will fall under the more senior age groups, thereby placing pressure on a shrinking Singaporean workforce that has to support the ageing population.

Useful Information 2 - Even Distribution of Type of Dwelling between Genders for all age groups

When looking at the distribution of type of dwelling, we can see that across all age groups, the gender split for type of dwellings is generally even throughout the age groups, with slightly more disparity when it comes to the higher / senior end of age groups.