Residual view

Optional · models and matrices · V21 · 8 MIN

Inspect what a fitted line leaves unexplained.

Exercises within this concept

FollowFollow the techniqueCurrent exercise
ChangeAdapt a requirement
TransferCombine earlier skills

Understand the idea

A residual is observed y minus predicted y. A residual plot helps inspect what a fitted straight line fails to explain.

Illustration · not the exercise output

A small example

If observed y=12 and predicted y=10, residual=+2. If observed y=8, residual=−2.

Follow the code

Apply the idea to the supplied table. Read from top to bottom; the final line displays the result.

import matplotlib.pyplot as plt
import seaborn as sns

fig, ax = plt.subplots(figsize=(6, 4))
sns.residplot(data=df, x="hours", y="score", ax=ax)
ax.set(title="Study club", xlabel="hours", ylabel="Residual")
fig.tight_layout()
plt.show()

What each part does

sns.residplot: x against residuals after a linear fit
zero line: predictions equal observations

Your inputs

The editable setup on the right creates df. Run executes the setup and your work from top to bottom.

Study club · 8 synthetic rows
student	club	hours	score	group
Ari	Art	1	52	A
Bo	Code	3	71	A
Cy	Art	2	65	B
Dee	Code	4	82	B
Eli	Art	5	89	A
Flo	Code	3	76	A
Gus	Art	6	93	B
Han	Code	2	61	B

Your task · Follow

Using df, call sns.residplot with x=hours and y=score.
Chart: title "Study club"; x "hours"; y "Residual".

Hint

Residuals are observed minus predicted, not the original measured y values.

Reveal solution

One way to do it. Keep any supplied setup in the editor and use this in the Your work section.

import matplotlib.pyplot as plt
import seaborn as sns

fig, ax = plt.subplots(figsize=(6, 4))
sns.residplot(data=df, x="hours", y="score", ax=ax)
ax.set(title="Study club", xlabel="hours", ylabel="Residual")
fig.tight_layout()
plt.show()

Your task · Follow

Using df, call sns.residplot with x=hours and y=score.
Chart: title "Study club"; x "hours"; y "Residual".

YOUR PYTHON

Tab: indent · Shift+Tab: outdent · Esc, then Tab: leave editor

# Supplied setup — editable
import pandas as pd

data = {
    "student": ["Ari", "Bo", "Cy", "Dee", "Eli", "Flo", "Gus", "Han"],
    "club": ["Art", "Code", "Art", "Code", "Art", "Code", "Art", "Code"],
    "hours": [1, 3, 2, 4, 5, 3, 6, 2],
    "score": [52, 71, 65, 82, 89, 76, 93, 61],
    "group": ["A", "A", "B", "B", "A", "A", "B", "B"],
}

df = pd.DataFrame(data)

# Your work
import matplotlib.pyplot as plt
import seaborn as sns

fig, ax = plt.subplots(figsize=(6, 4))
# Build the requested chart
____
# Add the labels from Your task
ax.set(____)
fig.tight_layout()
plt.show()

Each run executes all editor code in a fresh Python session. Display charts with plt.show().

Python starts when you open a lesson.

Output

Run your code to see what Python returns.