R ggplot2 — The Grammar of Graphics

Learning Objectives

By the end of this tutorial, you will be able to:

• Build plots layer by layer using the grammar of graphics
• Create scatter plots, bar charts, histograms, and boxplots
• Customize aesthetics, scales, and themes
• Add annotations, labels, and facets
• Create publication-quality visualizations

The Grammar of Graphics

ggplot2 builds plots in layers:

library(ggplot2)

# Basic structure
ggplot(data, aes(x, y)) +
  geom_*() +
  scale_*() +
  labs() +
  theme()

Basic Plots

Scatter Plot

ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point()

# With color and size
ggplot(mtcars, aes(x = wt, y = mpg, color = factor(cyl), size = hp)) +
  geom_point(alpha = 0.7) +
  labs(title = "Car Weight vs MPG", color = "Cylinders", size = "Horsepower")

Bar Chart

# Count
ggplot(mtcars, aes(x = factor(cyl))) +
  geom_bar(fill = "steelblue")

# Values
ggplot(mtcars, aes(x = factor(cyl), y = mpg)) +
  geom_col(fill = "steelblue")

# Stacked
ggplot(mtcars, aes(x = factor(cyl), fill = factor(gear))) +
  geom_bar(position = "stack")

# Grouped
ggplot(mtcars, aes(x = factor(cyl), fill = factor(gear))) +
  geom_bar(position = "dodge")

Histogram

ggplot(mtcars, aes(x = mpg)) +
  geom_histogram(bins = 20, fill = "steelblue", color = "white")

# Density
ggplot(mtcars, aes(x = mpg)) +
  geom_density(fill = "steelblue", alpha = 0.5)

Boxplot

ggplot(mtcars, aes(x = factor(cyl), y = mpg)) +
  geom_boxplot(fill = "steelblue")

# Violin + Boxplot
ggplot(mtcars, aes(x = factor(cyl), y = mpg)) +
  geom_violin(fill = "steelblue", alpha = 0.5) +
  geom_boxplot(width = 0.1)

Line Plot

# Time series
ggplot(economics, aes(x = date, y = unemploy)) +
  geom_line(color = "steelblue") +
  labs(title = "US Unemployment Over Time")

Aesthetics Mapping

# Color
ggplot(mtcars, aes(x = wt, y = mpg, color = factor(cyl))) +
  geom_point()

# Fill
ggplot(mtcars, aes(x = factor(cyl), fill = factor(cyl))) +
  geom_bar()

# Size
ggplot(mtcars, aes(x = wt, y = mpg, size = hp)) +
  geom_point(alpha = 0.5)

# Shape
ggplot(mtcars, aes(x = wt, y = mpg, shape = factor(cyl))) +
  geom_point()

# Alpha (transparency)
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point(alpha = 0.3)

# Manual aesthetics (not mapped from data)
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point(color = "red", size = 3, shape = 16)

Geometric Objects

Common Geoms

# Points
geom_point()

# Lines
geom_line()
geom_path()

# Bars
geom_bar()
geom_col()

# Histograms
geom_histogram()
geom_density()

# Boxplots
geom_boxplot()
geom_violin()

# Error bars
geom_errorbar()
geom_pointrange()

# Text
geom_text()
geom_label()

# Smooth
geom_smooth(method = "lm")
geom_smooth(method = "loess")

# Jitter
geom_jitter()

Combining Geoms

ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE)

ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point(alpha = 0.5) +
  geom_smooth(method = "lm", color = "red")

Facets

# Facet by single variable
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  facet_wrap(~cyl)

# Facet by two variables
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  facet_grid(gear ~ cyl)

# Free scales
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  facet_wrap(~cyl, scales = "free")

# Labeller
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  facet_wrap(~cyl, labeller = label_both)

Scales

# Continuous scales
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  scale_x_continuous(limits = c(0, 6), breaks = seq(0, 6, 1)) +
  scale_y_continuous(limits = c(0, 40), breaks = seq(0, 40, 10))

# Log scale
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  scale_x_log10() +
  scale_y_log10()

# Color scales
ggplot(mtcars, aes(x = wt, y = mpg, color = factor(cyl))) +
  geom_point() +
  scale_color_manual(values = c("4" = "red", "6" = "blue", "8" = "green"))

# Viridis
ggplot(mtcars, aes(x = wt, y = mpg, color = hp)) +
  geom_point() +
  scale_color_viridis_c()

# Brewer
ggplot(mtcars, aes(x = wt, y = mpg, color = factor(cyl))) +
  geom_point() +
  scale_color_brewer(palette = "Set1")

Labels and Annotations

# Labels
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  labs(
    title = "Car Weight vs MPG",
    subtitle = "From mtcars dataset",
    x = "Weight (1000 lbs)",
    y = "Miles per Gallon",
    caption = "Data from R datasets"
  )

# Annotations
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  annotate("text", x = 5, y = 35, label = "Some text") +
  annotate("rect", xmin = 3, xmax = 5, ymin = 15, ymax = 25, alpha = 0.2) +
  annotate("segment", x = 2, xend = 4, y = 10, yend = 20, color = "red")

Themes

# Built-in themes
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  theme_minimal()

ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  theme_bw()

ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  theme_classic()

# Custom theme
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  theme(
    plot.title = element_text(size = 16, face = "bold"),
    axis.title = element_text(size = 12),
    legend.position = "bottom",
    panel.grid.minor = element_blank()
  )

# ggrepel for non-overlapping labels
library(ggrepel)
ggplot(mtcars, aes(x = wt, y = mpg, label = rownames(mtcars))) +
  geom_point() +
  geom_text_repel()

Save Plots

# Save last plot
ggsave("plot.png", width = 8, height = 6, dpi = 300)
ggsave("plot.pdf", width = 8, height = 6)
ggsave("plot.svg", width = 8, height = 6)

Practical Examples

Example 1: Dashboard Plot

library(dplyr)
library(ggplot2)

# Create plot
p <- mtcars |>
  mutate(cyl = factor(cyl)) |>
  ggplot(aes(x = wt, y = mpg, color = cyl, size = hp)) +
  geom_point(alpha = 0.7) +
  geom_smooth(method = "lm", se = FALSE, linetype = "dashed") +
  labs(
    title = "Car Performance Analysis",
    subtitle = "Weight vs Fuel Efficiency",
    x = "Weight (1000 lbs)",
    y = "Miles per Gallon",
    color = "Cylinders",
    size = "Horsepower"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"),
    legend.position = "right"
  )

ggsave("car_analysis.png", p, width = 10, height = 6)

Practice Exercises

Exercise 1: Diamond Prices

Create a visualization of diamond prices by cut, colored by clarity.

Solution

library(ggplot2)

ggplot(diamonds, aes(x = cut, y = price, fill = clarity)) +
  geom_boxplot() +
  labs(
    title = "Diamond Prices by Cut and Clarity",
    x = "Cut",
    y = "Price ($)"
  ) +
  theme_minimal()

Key Takeaways

• ggplot2 builds plots in layers — data, aesthetics, geometry, scales, themes
• aes() maps data to visual properties — x, y, color, size, shape
• Geoms determine plot type — point, bar, line, histogram, boxplot
• Facets create subplots — facet_wrap() and facet_grid()
• Scales control mapping — continuous, discrete, color, size
• Themes control appearance — fonts, gridlines, legends
• Use ggsave() to save — PNG, PDF, SVG formats

Next: Learn about R Statistical Functions — descriptive statistics.