Foundations of
Data Science

Spring 2026 | Data 2 (399)
Jeffrey M. Girard | Lecture 05b

Roadmap

Combine layers of overlapping geometric objects
Learn aesthetic setting, mapping, and grouping

Setup

library(tidyverse)
data("mpg", package = "ggplot2")

glimpse(mpg)

Rows: 234
Columns: 11
$ manufacturer <chr> "audi", "audi", "audi", "audi", "audi", "audi", "audi", "…
$ model        <chr> "a4", "a4", "a4", "a4", "a4", "a4", "a4", "a4 quattro", "…
$ displ        <dbl> 1.8, 1.8, 2.0, 2.0, 2.8, 2.8, 3.1, 1.8, 1.8, 2.0, 2.0, 2.…
$ year         <int> 1999, 1999, 2008, 2008, 1999, 1999, 2008, 1999, 1999, 200…
$ cyl          <int> 4, 4, 4, 4, 6, 6, 6, 4, 4, 4, 4, 6, 6, 6, 6, 6, 6, 8, 8, …
$ trans        <chr> "auto(l5)", "manual(m5)", "manual(m6)", "auto(av)", "auto…
$ drv          <chr> "f", "f", "f", "f", "f", "f", "f", "4", "4", "4", "4", "4…
$ cty          <int> 18, 21, 20, 21, 16, 18, 18, 18, 16, 20, 19, 15, 17, 17, 1…
$ hwy          <int> 29, 29, 31, 30, 26, 26, 27, 26, 25, 28, 27, 25, 25, 25, 2…
$ fl           <chr> "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p", "p…
$ class        <chr> "compact", "compact", "compact", "compact", "compact", "c…

Layering

ggplot2 uses a layered grammar of graphics
- We can keep stacking geoms on top

Layering adds a lot of possibilities
- We can convey more complex ideas
- We can learn more about our data

But we can still describe these graphics
- Just describe each layer in turn
- And describe the layers’ ordering

The Smooth Geom

# Left: Point geom plots all the observations
ggplot(mpg, aes(x = displ, y = hwy)) + geom_point()
# Right: Smooth geom plots a local line-of-best-fit
ggplot(mpg, aes(x = displ, y = hwy)) + geom_smooth()

Overlapping the Layers

# Adding additional geoms stacks their layers on top
ggplot(mpg, aes(x = displ, y = hwy)) +
  geom_point() + 
  geom_smooth()

Economics Dataset

data("economics", package = "ggplot2")

glimpse(economics)

Rows: 574
Columns: 6
$ date     <date> 1967-07-01, 1967-08-01, 1967-09-01, 1967-10-01, 1967-11-01, …
$ pce      <dbl> 506.7, 509.8, 515.6, 512.2, 517.4, 525.1, 530.9, 533.6, 544.3…
$ pop      <dbl> 198712, 198911, 199113, 199311, 199498, 199657, 199808, 19992…
$ psavert  <dbl> 12.6, 12.6, 11.9, 12.9, 12.8, 11.8, 11.7, 12.3, 11.7, 12.3, 1…
$ uempmed  <dbl> 4.5, 4.7, 4.6, 4.9, 4.7, 4.8, 5.1, 4.5, 4.1, 4.6, 4.4, 4.4, 4…
$ unemploy <dbl> 2944, 2945, 2958, 3143, 3066, 3018, 2878, 3001, 2877, 2709, 2…

Line Geoms for Time Series

# Left
ggplot(economics, aes(x = date, y = unemploy)) + geom_point()
# Right
ggplot(economics, aes(x = date, y = unemploy)) + geom_line()

Adding Reference Lines

# Add a horizontal reference line at y=10000
ggplot(economics, aes(x = date, y = unemploy)) + 
  geom_hline(yintercept = 10000) +
  geom_line()

Aesthetics

Aesthetics control a geom’s appearance
- points: color, shape, size, …
- smooths: color, linetype, linewidth, …

There are two ways to control aesthetics:
- You can set it to a value
  - It will take on one value only
  - e.g., all points = red
- You can map it to a variable
  - It will take on different values
  - e.g., sedans = red, trucks = blue

Setting Color

# Set color inside geom_*() to apply it to all points
ggplot(mpg, aes(x = displ, y = hwy)) +
  geom_point(color = "blue")

Mapping Color

# Map color to a variable within aes() to have it vary
ggplot(mpg, aes(x = displ, y = hwy, color = class)) +
  geom_point()

Pitfall: Setting in aes

# Don't try to set an aesthetic inside aes()
ggplot(mpg, aes(x = displ, y = hwy, color = "blue")) + 
  geom_point()

Pitfall: Mapping in geom

# Don't try to map an aesthetic outside of aes()
ggplot(mpg, aes(x = displ, y = hwy)) + 
  geom_point(color = class)

Error in `geom_point()`:
! Problem while setting up geom aesthetics.
ℹ Error occurred in the 1st layer.
Caused by error in `list_sizes()`:
! `x$colour` must be a vector, not a primitive function.
ℹ Read our FAQ about scalar types (`?vctrs::faq_error_scalar_type`) to learn more.

Setting Shape

# Set the shape inside geom_*() to "triangle"
ggplot(mpg, aes(x = displ, y = hwy)) + 
  geom_point(shape = "triangle")

Mapping Shape

# Map shape to the drv variable inside aes()
ggplot(mpg, aes(x = displ, y = hwy, shape = drv)) + 
  geom_point()

Redundant Mapping

# Map both shape and color to the drv variable
ggplot(mpg, aes(x = displ, y = hwy, shape = drv, color = drv)) + 
  geom_point()

Other Useful Aesthetics

size
- Geoms: point, text
- Action: Controls point or font size
alpha
- Geoms: All
- Action: Controls transparency
  (0 = invisible, 1 = opaque)

linewidth
- Geoms: line, smooth
- Action: Controls line thickness
linetype
- Geoms: line, smooth
- Action: Controls line pattern
  (solid, dashed, dotted)

Aesthetics in Action

ggplot(
  mpg, 
  aes(x = displ, y = hwy)
) +
  geom_point(
    size = 4,
    color = "coral",
    shape = "square",
    alpha = 0.5
  ) +
  geom_smooth(
    color = "steelblue",
    linewidth = 1.5,
    linetype = "dashed"
  )

Aesthetics in Action

ggplot(economics, aes(x = date, y = unemploy)) + 
  geom_hline(yintercept = 10000, color = "coral", 
             linetype = "dashed", linewidth = 2) +
  geom_line(linewidth = 1)

Grouping

Implicit vs. Explicit Grouping

Grouping controls how functions (like geom_smooth or geom_line) analyze your data.
- Do we calculate one trend or many?

Implicit Grouping (via color, shape, etc.)
- Mapping a variable to appearance automatically groups the data.
- Result: Separate geoms + a Legend.

Explicit Grouping (via group)
- Mapping a variable to group groups the data without changing appearance.
- Result: Separate geoms + No Legend.

Smooth (No Grouping)

# No color mapping leads to a smooth for all datapoints
ggplot(mpg, aes(x = displ, y = hwy)) + geom_smooth()

Smooth (Implicit Grouping)

# Mapping color to drv leads to a separate smooth for each group
ggplot(mpg, aes(x = displ, y = hwy, color = drv)) + geom_smooth()

ChickWeight Dataset

data("ChickWeight", package = "datasets")

glimpse(ChickWeight)

Rows: 578
Columns: 4
$ weight <dbl> 42, 51, 59, 64, 76, 93, 106, 125, 149, 171, 199, 205, 40, 49, 5…
$ Time   <dbl> 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 21, 0, 2, 4, 6, 8, 10, 1…
$ Chick  <ord> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, …
$ Diet   <fct> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …

Line Series (No Grouping)

# Without grouping, we get an incomprehensible line for all Chicks
ggplot(ChickWeight, aes(x = Time, y = weight)) + geom_line()

Line Series (Explicit Grouping)

# But with explicit grouping, we get a separate line per Chick
ggplot(ChickWeight, aes(x = Time, y = weight, group = Chick)) + 
  geom_line(alpha = 0.3)

Foundations of Data Science

Roadmap

Setup

Layering

Layering

The Smooth Geom

Overlapping the Layers

Economics Dataset

Line Geoms for Time Series

Adding Reference Lines

Aesthetics

Aesthetics

Setting Color

Mapping Color

Pitfall: Setting in aes

Pitfall: Mapping in geom

Setting Shape

Mapping Shape

Redundant Mapping

Other Useful Aesthetics

Aesthetics in Action

Aesthetics in Action

Grouping

Implicit vs. Explicit Grouping

Smooth (No Grouping)

Smooth (Implicit Grouping)

ChickWeight Dataset

Line Series (No Grouping)

Line Series (Explicit Grouping)

Foundations of
Data Science