3  Data Visualization with ggplot2

3.1 Learning Objectives

By the end of this chapter, you should be able to:

• Create basic scatterplots using ggplot2
• Map variables to aesthetics (color, size, shape)
• Use different geoms (points, smooth lines, histograms)
• Create facets to display subsets of data
• Customize plots for clear communication

---

3.2 Introduction to Data Visualization

This week we begin with visualization first, following R for Data Science (Ch. 2).
ggplot2 is part of the tidyverse and implements the grammar of graphics.
We will use the built-in mpg dataset for examples.

---

3.3 ggplot2 Basics

The template for a ggplot is:

ggplot(data = <DATA>) +
  <GEOM_FUNCTION>(mapping = aes(<MAPPINGS>))

3.3.1 Example: Scatterplot of engine size vs. highway mpg

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.2     ✔ tibble    3.2.1
✔ lubridate 1.9.4     ✔ tidyr     1.3.1
✔ purrr     1.0.4     
── 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

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, y = hwy))

---

3.3.2 In-Class Exercise 1

1. Create a scatterplot of cty (city mpg) vs. hwy (highway mpg).
   
2. What relationship do you see?
   
3. Try swapping x and y—does it change the interpretation?

---

3.3.3 Aesthetic Mappings

You can map variables to visual properties: color, size, shape, alpha.

3.3.4 Example: Color by class

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, y = hwy, color = class))

---

3.3.5 In-Class Exercise 2

• Modify the plot to map size to cyl (number of cylinders).
  
• Map shape to drv (drive type).
  
• Try using both color and shape in one plot.

---

3.4 Adding Geoms

The geom_point() function creates a scatterplot, but there are many geoms.

3.4.1 Example: Add a smoothing line

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, y = hwy)) +
  geom_smooth(mapping = aes(x = displ, y = hwy))

`geom_smooth()` using method = 'loess' and formula = 'y ~ x'

---

3.4.2 In-Class Exercise 3

• Add a geom_smooth() line to your plot from Exercise 1.
  
• Try setting se = FALSE to remove the confidence band.
  
• Change the color of the line manually.

---

3.5 Facets

Facets split the data into subplots based on a variable.

3.5.1 Example: Facet by drive type

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, y = hwy)) +
  facet_wrap(~ drv)

---

3.5.2 In-Class Exercise 4

• Use facet_wrap() to facet the plot by class.
  
• Try facet_grid(drv ~ cyl)—what do you observe?

---

3.6 Customizing Plots

You can add labels, titles, and themes to improve clarity.

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, y = hwy, color = class)) +
  labs(
    title = "Fuel Efficiency by Engine Size",
    x = "Engine Displacement (L)",
    y = "Highway MPG",
    color = "Car Class"
  ) +
  theme_minimal()

---

3.7 In-Class Challenge

Using the mpg dataset:

1. Make a scatterplot of displ vs hwy.
   
2. Map a third variable to color.
   
3. Add a smooth line and facet by drive type.
   
4. Add labels and use a clean theme.

---

3.8 Homework Preview

For Homework, you will:

• Use the mpg dataset (or another dataset of your choice).
  
• Create three plots:
  1. A scatterplot with at least one aesthetic mapping
  2. A faceted plot showing subsets of data
  3. A customized plot with titles, labels, and a theme
• Render your .qmd to PDF and submit on Canvas.

---

3.9 Next Steps

Next week, we begin data transformation using dplyr to manipulate data before plotting.