Intro Visualization
Intro Visualization
Visualization
Guoning Chen
Data is generated
everywhere and everyday
Age of Big Data
Data in ever increasing sizes ⇒ need an effective way to
understand them
History of Visualization
• Visualization = rather old L. da Vinci (1452-1519)
Source: NASA
This pipeline represents only the lecturer’s opinion and need not reflect the opinions of NSF or UH!
Data Visual Analytic Pipeline
Data acquisition Data are generated/collected.
Feature detection
Structure extraction
Analysis
Statistical analysis
etc.
Data are mapped to visual
Visualization mapping primitives, e.g. colors,
geometry, etc.
Tree Text
• Information visualization focuses on:
– high-dimensional (>>4), abstract data (i.e. tree, graphs, hierarchy, …)
– Data is discrete in the nature
– Examples include financial, marketing, HR, statistical, social media, political,
…...
– Feature are not well-defined, the typical analysis tasks including finding
patterns, clusters, voids, outliers
Use Colors Wisely
What is Wrong with this Color Scale
Not a bad choice of color scale,
but the Dynamic Range needs some work
Use the Right Transfer Function Color Scale
to Represent a Range of Scalar Values
• Gray scale
• Intensity Interpolation
• Saturation interpolation
• Two-color interpolation
• Rainbow scale
• Heated object interpolation
• Blue-White-Red
Low High
. . .
It is not possible to list all the useful rules. They come with a lot of experience!
Beware of Color Pollution
• Improve understanding
1. Provide explanations and draw conclusions
2. Use all available space
3. Align juxtaposed plots
4. Use log scales when appropriate
5. Bank to 45
Data we are discussing