Assignemnt 3: dplyr/gggplot2 Part II

Set Up

Install and load dplyr, probably via the tidyverse meta-package.

library(gapminder)
library(tidyverse)

## ── Attaching packages ──────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.2.1     ✔ purrr   0.3.2
## ✔ tibble  2.1.3     ✔ dplyr   0.8.3
## ✔ tidyr   1.0.0     ✔ stringr 1.4.0
## ✔ readr   1.3.1     ✔ forcats 0.4.0

## ── Conflicts ─────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(ggridges)

## 
## Attaching package: 'ggridges'

## The following object is masked from 'package:ggplot2':
## 
##     scale_discrete_manual

library(knitr)

Pick three of the six tasks below, and produce:

• a tibble, using dplyr as your data manipulation tool;
• an accompanying plot of data from the tibble, using ggplot2 as your visualization tool; and
• some dialogue about what your tables/figures show (doesn’t have to be much)

Relax about the following things:

• Your figure does not have to depict every single number from the data aggregation result. Use your judgement. It just needs to complement the table, add context, and allow for some sanity checking both ways.
• Tidying/reshaping is NOT your assignment. Many of your tables will be awkwardly shaped in the report. That’s OK.
• Table beauty is not a big deal. Simply printing to “screen” is fine.

I have chosen to do Task #2, #3 and #5.

Task Option #2

Get the maximum and minimum of GDP per capita for all continents.

min <- gapminder %>%
  group_by(continent) %>%
  summarize(GDP = min(gdpPercap), value = "min")

max <- gapminder %>%
  group_by(continent) %>%
  summarize(GDP = max(gdpPercap), value = "max")

table <- rbind(min,max) %>% arrange(continent)

plot <- table %>%
  group_by(value) %>%
  ggplot(aes(continent,GDP, fill = value)) +
  geom_col(position="dodge") +
  scale_fill_discrete("", "Maximum GDP per capita", "Minimum GDP per capita") +
  ylab("GDP per capita") +
  xlab("Continent") +
  ggtitle("Maximum and Minimum GDP per capita") + 
  theme(text = element_text(size=18))

• In the figures below, the maximum and minimum GDP per capita for all continents is depicted. In the ed bars are the maximum, while in the blue bars are the minimum.
• Looking at this plot, Asia not only has the highest maximum GDP per capita, but also the largest difference between the minimum and maximum.

continent	GDP	value
Africa	241.1659	min
Africa	21951.2118	max
Americas	1201.6372	min
Americas	42951.6531	max
Asia	331.0000	min
Asia	113523.1329	max
Europe	973.5332	min
Europe	49357.1902	max
Oceania	10039.5956	min
Oceania	34435.3674	max

Task Option #3

Look at the spread of GDP per capita within the continents.

table <- gapminder %>% 
  filter(year > 1980)

plot <- table %>%
  ggplot(aes(gdpPercap, continent)) +
  geom_density_ridges(scale = 0.9) +
  ggtitle("Spread of GDP from 1980-2007") + 
  theme(text = element_text(size=18)) +
  xlab("GDP per capita") +
  ylab("Continent")

• In the figures below, the spread of GDP per capita within each continent from 1980-2007 is depicted.
• The table has been truncated to 9 rows as there are too many to show side by side with the plot.
• While Asia has the highest maximum GDP per capita as demonstrated with the previous plot, in this plot, Africa has the highest peak around a GDP per capita of 2000, while Europe has the widest spread of GDP per capita.

country	continent	year	lifeExp	pop	gdpPercap
Afghanistan	Asia	1982	39.854	12881816	978.0114
Afghanistan	Asia	1987	40.822	13867957	852.3959
Afghanistan	Asia	1992	41.674	16317921	649.3414
Afghanistan	Asia	1997	41.763	22227415	635.3414
Afghanistan	Asia	2002	42.129	25268405	726.7341
Afghanistan	Asia	2007	43.828	31889923	974.5803
Albania	Europe	1982	70.420	2780097	3630.8807
Albania	Europe	1987	72.000	3075321	3738.9327
Albania	Europe	1992	71.581	3326498	2497.4379

Task Option #5

How is life expectancy changing over time on different continents?

table <- gapminder %>%
  group_by(continent, year) %>%
  summarize(avglifeExp = mean(lifeExp))

plot <- table %>%
  ggplot(aes(year,avglifeExp, colour = continent)) +
  geom_line() +
  ggtitle("Mean Life Expectancy from 1952-2007") + 
  theme(text = element_text(size=18)) +
  xlab("Year") +
  ylab("Average Life Expectancy")

• In the figures below, the mean life expectancy from 1952 to 2007 for each continent is depicted.
• The table has been truncated to 9 rows as there are too many to show side by side with the plot.
• Africa has the steepest slope, representing the most drastic increase in life expectancy, but ends up plateauing near the end.
• Americas and Asia share a similar slope and trend, while so do Oceania and Europe.
• However, Oceania experiences the biggest dip in life expectancy (from 1960 to 1980), and Africa experiences the second dip (after 2000).

continent	year	avglifeExp
Africa	1952	39.13550
Africa	1957	41.26635
Africa	1962	43.31944
Africa	1967	45.33454
Africa	1972	47.45094
Africa	1977	49.58042
Africa	1982	51.59287
Africa	1987	53.34479
Africa	1992	53.62958

Optional

Get table and figure side-by-side.

• Attribution: Following the suggested guide, I was able to get the plots and tables side by side, but had to truncate the tables to maintain aesthetics.
• The plots and tables only appear side by side if the window size is sufficient for this to occur.
• Some tables had to be truncated to 9 rows as there are too many to show side by side with the plots
• I am aware that tables can be printed (messily) to console, but the two column wrapping only seems to work with kable() due to the .table tag in the CSS stylesheet.