GDP Per Capita

An exploration and visualization of GDP per capita across countries within continents

Introduction

This is a visualization of the countries with the highest change in GDP per capita from 1952 to 2007

Data preparation

The dataset we will be using for this is gapminder. Let’s load required packages and the dataset itself

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.1     ✔ stringr   1.5.2
✔ ggplot2   4.0.0     ✔ tibble    3.3.0
✔ lubridate 1.9.4     ✔ tidyr     1.3.1
✔ purrr     1.1.0     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(gapminder)

Warning: package 'gapminder' was built under R version 4.5.3

gapminder <- gapminder

Now let’s create a function to calculate the change in gdp from 1952 to 2007 and select the number of highest gdp change countries we want to keep.

gdp_delta <- function(data, cont, top) {
  
  delta <- filter(data, 
            continent == cont,
            year %in% c(1952, 2007)) %>% 
  group_by(country) %>% 
  summarize(delta = abs(gdpPercap[year == 2007] - gdpPercap[year == 1952])) %>% 
  arrange(desc(delta)) %>% 
  select(country, delta) %>% 
  slice_head(n = top)
  
  countries <- delta$country
  
  g_trim <- data %>% filter(country %in% countries)
  
  left_join(g_trim, delta, by = "country")

}      

Now we’ll split the data by continents and calculate the changes within each continent.

Note that we’ll be keeping the data without the calculated change so that later we can plot all countries but only highlight the most changed ones.

# Asia

g_asia <- gapminder %>% filter(continent == "Asia")

gdp_asia <- gdp_delta(data = gapminder, cont = "Asia", top = 6)

# Americas

g_americas <- gapminder %>% filter(continent == "Americas")

gdp_americas <- gdp_delta(data = gapminder, cont = "Americas", top = 6)

# Africa

g_africa <- gapminder %>% filter(continent == "Africa")

gdp_africa <- gdp_delta(data = gapminder, cont = "Africa", top = 6)

# Europe

g_europe <- gapminder %>% filter(continent == "Europe")

gdp_europe <- gdp_delta(data = gapminder, cont = "Europe", top = 6)

# Oceania

g_oceania <- gapminder %>% filter(continent == "Oceania")

gdp_oceania <- gdp_delta(data = gapminder, cont = "Oceania", top = 6)

Plotting

Let’s make a separate line plot for each continent, highlighting the top 6 countries.

We’ll also add points to only the top 6 countries.

# Asia

 ggplot() +
  geom_line(
    data = g_asia,
    aes(x = year, y = gdpPercap, group = country),
    color = "grey",
    alpha = .3,
    linewidth = .5) +
  geom_point(
    data = gdp_asia,
    aes(x = year, y = gdpPercap, color = country),
    size = .5) +  
  geom_line(
    data = gdp_asia,
    aes(x = year, y = gdpPercap, color = country)) +
  labs(title = "Countries in Asia with the highest change in GDP from 1952 to 2007",
       subtitle = "All other countries in Asia shown in grey",
       x = "Year",
       y = "GDP per capita",
       color = "Country") +
    theme_minimal() 

# Americas

ggplot() +
  geom_line(
    data = g_americas,
    aes(x = year, y = gdpPercap, group = country),
    color = "grey",
    alpha = .3,
    linewidth = .5) +
  geom_point(
    data = gdp_americas,
    aes(x = year, y = gdpPercap, color = country),
    size = .5) +  
  geom_line(
    data = gdp_americas,
    aes(x = year, y = gdpPercap, color = country)) +
  labs(title = "Countries in the Americas with the highest change in GDP from 1952 to 2007",
       subtitle = "All other countries in the Americas shown in grey",
       x = "Year",
       y = "GDP per capita",
       color = "Country") +
    theme_minimal() 

# Africa

  ggplot() +
  geom_line(
    data = g_africa,
    aes(x = year, y = gdpPercap, group = country),
    color = "grey",
    alpha = .3,
    linewidth = .5) +
  geom_point(
    data = gdp_africa,
    aes(x = year, y = gdpPercap, color = country),
    size = .5) +  
  geom_line(
    data = gdp_africa,
    aes(x = year, y = gdpPercap, color = country)) +
  labs(title = "Countries in Africa with the highest change in GDP from 1952 to 2007",
       subtitle = "All other countries in Africa shown in grey",
       x = "Year",
       y = "GDP per capita",
       color = "Country") +
    theme_minimal() 

# Europe

ggplot() +
  geom_line(
    data = g_europe,
    aes(x = year, y = gdpPercap, group = country),
    color = "grey",
    alpha = .3,
    linewidth = .5) +
  geom_point(
    data = gdp_europe,
    aes(x = year, y = gdpPercap, color = country),
    size = .5) +  
  geom_line(
    data = gdp_europe,
    aes(x = year, y = gdpPercap, color = country)) +
  labs(title = "Countries in Europe with the highest change in GDP from 1952 to 2007",
       subtitle = "All other countries in Europe shown in grey",
       x = "Year",
       y = "GDP per capita",
       color = "Country") +
    theme_minimal()

# Oceania

ggplot() +
  geom_line(
    data = g_oceania,
    aes(x = year, y = gdpPercap, group = country),
    color = "grey",
    alpha = .3,
    linewidth = .5) +
  geom_point(
    data = gdp_oceania,
    aes(x = year, y = gdpPercap, color = country),
    size = .5) +  
  geom_line(
    data = gdp_oceania,
    aes(x = year, y = gdpPercap, color = country)) +
  labs(title = "Change in GDP from 1952 to 2007 in countries in Oceania",
       x = "Year",
       y = "GDP per capita",
       color = "Country") +
    theme_minimal()