# Load the packages 
library(dslabs)
library(tidyverse)  

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.2.1     ✔ readr     2.2.0
✔ forcats   1.0.1     ✔ stringr   1.6.0
✔ ggplot2   4.0.3     ✔ tibble    3.3.1
✔ lubridate 1.9.5     ✔ tidyr     1.3.2
✔ purrr     1.2.2     
── 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

Load the Data

# Load the gapminder dataset
data(gapminder)

head(gapminder)

              country year infant_mortality life_expectancy fertility
1             Albania 1960           115.40           62.87      6.19
2             Algeria 1960           148.20           47.50      7.65
3              Angola 1960           208.00           35.98      7.32
4 Antigua and Barbuda 1960               NA           62.97      4.43
5           Argentina 1960            59.87           65.39      3.11
6             Armenia 1960               NA           66.86      4.55
  population          gdp continent          region
1    1636054           NA    Europe Southern Europe
2   11124892  13828152297    Africa Northern Africa
3    5270844           NA    Africa   Middle Africa
4      54681           NA  Americas       Caribbean
5   20619075 108322326649  Americas   South America
6    1867396           NA      Asia    Western Asia

Prepare the Data

# Keep only the year 2011 so each country appears once
# Compute dollars per day
# Remove rows with missing values
gap_2011 <- gapminder %>%
  filter(year == 2011) %>%
  mutate(dollars_per_day = gdp / population / 365) %>%
  filter(!is.na(dollars_per_day), !is.na(life_expectancy))

Create the Base Plot

# Set up the plot
p <- ggplot(gap_2011, aes(x = dollars_per_day,
                          y = life_expectancy,
                          color = continent))

Add the Points

# Add a point for each country
p <- p + geom_point(aes(size = population), alpha = 0.7)

Set the Axis Scale

# Show the x-axis values with dollar signs
p <- p + scale_x_log10(labels = scales::dollar)

Choose Colors

# The legend title is set to "Continent"
p <- p + scale_color_manual(
  values = c("Africa"   = "red",
             "Americas" = "orange",
             "Asia"     = "forestgreen",
             "Europe"   = "blue",
             "Oceania"  = "purple"),
  name = "Continent"
)

# Control the point sizes and hide the population legend
p <- p + scale_size(range = c(2, 12), guide = "none")

Add Titles, Labels, and Caption

# Add a title, subtitle, axis labels, and the data source caption
p <- p + labs(
  title    = "Richer Countries Tend to Live Longer",
  subtitle = "Daily income vs. life expectancy by continent",
  x        = "Income per person per day (US dollars, log scale)",
  y        = "Life expectancy (years)",
  caption  = "Source: DS Labs (dslabs package, gapminder dataset)"
)

Apply a Theme

# Add a minimal theme
p <- p + theme_minimal(base_size = 13)

# bold title, gray subtitle, caption
p <- p + theme(
  plot.title      = element_text(face = "bold", size = 16),
  plot.subtitle   = element_text(color = "gray"),
  plot.caption    = element_text(face = "italic"),
  
)

Display the Graph

# Print the finished scatterplot
p

Interpretation

The graph shows a clear positive relationship: as daily income rises, life expectancy rises too, though the gains level off at higher incomes. African countries cluster at the lower left, with low income and shorter lives, while European countries cluster at the upper right. Asian and American countries fall in between and show the widest spread. Larger points, such as China and India, show that populous countries can sit anywhere on the income scale.