Data Exploration and Visualization

Content

• The Role of Visualization in Big Data Analytics
• Visualization: Best Practices
• Tools and Techniques
• The MovieLens Dataset and Exercises

The Role of Visualization

The main purpose is to display information in a way that is meaningful.

Raw Data

Data Processing

Cleaned Data

Exploratory Data Analysis

Models and Algorithms

Decisions / Insights

Challenges

Does the data fit into memory?

Scale

Does the data fit into memory?

Static vs Dynamic

Does the data fit into memory?

Variable Quality

Types of Visualizations

Information Visualization

Scientific Visualization

Geographical Visualization

(or visualization basics)

Best Practices

Choose the right visual!

Data-to-ink-ratio

The Gestalt Principles of Perception

1. Similarity

2. Proximity

3. Closure

4. Continuation

Watch out for Pie Charts!

"The only thing worse than a pie chart is several of them."

Edward Tufte, Statistican and Artist

Tools and Techniques