Box and Whisker Plot with Seaborn and Matplotlib   

This article explores how to create Box and Whisker Plots using Seaborn and Matplotlib to visualize dataset distribution, spread, and outliers.

Why Use Box and Whisker Plots?

When dealing with statistical datasets, understanding the distribution and detecting outliers is essential. Using box plots helps:

• Visualize Data Distribution: Display how data is spread, showing the center, range, and overall distribution in a compact visual form
• Compare Multiple Groups: Efficiently compare different datasets side by side, such as student scores across classes or sales across regions
• Detect Outliers: Easily spot unusual or extreme values that lie far from the rest of the data
• Understand Skewness: Determine whether data is symmetric or skewed by observing the median position and whisker lengths

Components of a Box and Whisker Plot

A Box and Whisker Plot is made up of the following components:

• Box: Extends from the first quartile (Q1) to the third quartile (Q3), representing the middle 50% of the data, also known as the Interquartile Range (IQR)
• Whiskers: Extend from Q1 to the minimum value and from Q3 to the maximum value, showing the range of most of the data
• Median Line: A line inside the box represents the median (Q2), dividing the dataset into two equal halves
• Outliers: Data points that lie beyond the whiskers are treated as outliers and are usually shown as individual points

More information can be found: Matplotlib Boxplot Documentation

Steps to Create a Box and Whisker Plot

• Import required libraries (matplotlib, seaborn, pandas)
• Load or create your dataset
• Extract the relevant feature columns
• Create a box plot using sns.boxplot() or plt.boxplot()
• Customize colors, labels, and outlier markers

Dataset: Student Test Scores

The dataset contains test scores of a group of students with the following values:

Data (test scores): 78, 85, 90, 92, 95, 96, 97, 98, 99, 100, 105, 110, 120

The five-number summary for this dataset is: 78, 91, 97, 102.5, 120

import pandas as pd
data = pd.DataFrame({
    "scores": [78, 85, 90, 92, 95, 96, 97, 98, 99, 100, 105, 110, 120]
})
print("Shape of input data: "+str(data.shape))
data.head()

Example: Plot Box and Whisker Plot for Test Scores

import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

plt.figure(figsize=(8, 6))
sns.boxplot(y=data["scores"], color="skyblue", width=0.4)
plt.title("Box and Whisker Plot: Student Test Scores")
plt.ylabel("Scores")
plt.grid(axis="y", linestyle="--", alpha=0.7)
plt.show()

Output

• A vertical box plot is displayed for the scores feature
• The box represents the Interquartile Range (IQR) from Q1 (91) to Q3 (102.5)
• The median line (Q2 = 97) is drawn inside the box
• Whiskers extend from the minimum (78) to Q1 and from Q3 to the maximum (120)
• No outliers are detected in this dataset

Example: Comparing Multiple Groups

import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
%matplotlib inline

data = pd.DataFrame({
    "scores": [78, 85, 90, 92, 95, 96, 97, 98, 99, 100, 105, 110, 120,
               65, 70, 72, 75, 80, 82, 85, 88, 90, 92, 95, 98, 100,
               88, 90, 92, 94, 96, 98, 100, 102, 104, 106, 108, 110, 112],
    "class": ["A"]*13 + ["B"]*13 + ["C"]*13
})

plt.figure(figsize=(10, 6))
sns.boxplot(x="class", y="scores", data=data, palette="Set2")
plt.title("Box Plot Comparison: Scores Across Classes")
plt.xlabel("Class")
plt.ylabel("Scores")
plt.show()

Output

• Three box plots are displayed side by side for Class A, B, and C
• Each box shows the median, quartiles, and whiskers for its group
• Comparing boxes makes it easy to spot differences in central tendency and spread
• Outliers (if any) appear as individual points beyond the whiskers

Customizations

• Adjust width=0.4 in sns.boxplot() to change box thickness
• Use palette="Set2" for different color schemes
• Add notch=True for notched box plots to compare medians visually
• Modify figsize=(10, 6) to increase/decrease plot size
• Use hue="class" for grouped box plots with additional categories

sns.boxplot(x="class", y="scores", data=data, palette="Set2", 
            width=0.5, notch=True, hue="class", legend=False)

Uses of Box and Whisker Plot

• Visualizing Data Distribution: Box plots provide a clear picture of how data is spread, showing the center, range, and overall distribution in a compact visual form
• Comparing Multiple Groups: They are useful for comparing different datasets side by side, such as student scores across classes or sales across regions
• Detecting Outliers: Box plots make it easy to spot unusual or extreme values that lie far from the rest of the data
• Understanding Skewness: By observing the position of the median and the length of whiskers, one can determine whether data is symmetric or skewed
• Supporting Statistical Analysis: They provide a quick summary of key statistics, helping analysts decide which statistical methods or tests to apply
• Quality Control and Monitoring: In manufacturing and business processes, box plots help track variations and identify when results fall outside acceptable limits

Box and Whisker Diagram

   Box and Whisker Plot: Student Test Scores
   ─────────────────────────────────────────

   Scores
     │
 120 ┤ ────────  ●  ← Maximum (top of upper whisker)
     │           │
 110 ┤           │
     │           │
 105 ┤           │
     │           │
     │      ┌────┴────┐  ← Q3 (102.5)
 100 ┤      │         │
     │      │         │
     │      │─────────│  ← Median / Q2 (97)
  97 ┤      │         │
     │      │         │
     │      └────┬────┘  ← Q1 (91)
  90 ┤           │
     │           │
  85 ┤           │
     │           │
  78 ┤ ────────  ●  ← Minimum (bottom of lower whisker)
     │
     └──────────────────────────────
              Test Scores

What the Rendered Plot Shows

Install Requirements (if needed)

pip install matplotlib seaborn pandas

If you'd like, I can also provide a side-by-side comparison plot (Class A vs B vs C) as runnable code — just let me know.