๐ข Titanic Dataset Visualization Using Sunburst Chart
The Titanic dataset is one of the most widely used datasets in data science. In this guide, we’ll explore how to visualize it using a sunburst chart—a powerful way to understand hierarchical relationships.
๐ Table of Contents
- Dataset Overview
- What is a Sunburst Chart?
- Math Behind the Visualization
- Steps to Create Chart
- Code Example
- Output
- Key Insights
- Key Takeaways
- Related Articles
๐ Dataset Overview
| Column | Description |
|---|---|
| class | Passenger class (1st, 2nd, 3rd) |
| sex | Gender |
| embark_town | Boarding location |
| survived | 0 = No, 1 = Yes |
๐ What is a Sunburst Chart?
A sunburst chart shows hierarchical relationships using concentric circles.
๐ Math Behind the Visualization (Simple)
1. Probability of Survival
\[ P(Survival | Class) = \frac{\text{Survivors in Class}}{\text{Total Passengers in Class}} \]
This tells us survival likelihood for each class.
2. Conditional Probability
\[ P(Survival | Class, Gender) = \frac{\text{Survivors in Group}}{\text{Total in Group}} \]
3. Hierarchical Contribution
\[ Total = \sum_{i} Group_i \]
Each segment size is proportional to its count.
⚙️ Steps to Create Sunburst Chart
- Clean dataset
- Select relevant columns
- Define hierarchy
- Generate visualization
๐ป Code Example
import plotly.express as px
import pandas as pd
df = px.data.titanic()
df = df.dropna(subset=['class','sex','embark_town','survived'])
fig = px.sunburst(
df,
path=['class','sex','embark_town','survived'],
color='survived',
color_continuous_scale='RdBu'
)
fig.show()
๐ฅ️ Output
Click to View
Sunburst chart generated successfully. Interactive visualization opens in browser.
๐ Key Insights
- 1st class passengers had higher survival rates
- Women survived more than men
- Cherbourg passengers had slightly better survival
๐ก Key Takeaways
- Sunburst charts simplify complex relationships
- Hierarchy reveals deeper insights
- Probability helps interpret visual segments
๐ฏ Final Thoughts
The sunburst chart transforms raw Titanic data into a meaningful story. It shows not just who survived—but why patterns exist across different groups.
No comments:
Post a Comment