1. Data Visualization

2. Napoleon Invasion of Russia, 1812

3. © www. odt. org , from http://www. odt. org/Pictures/minard
© , from used by permission

4. Snow’s Cholera Map, 1855

5. Far East Asia at Night North Korea Notice how dark it is! Seoul
South Korea

6. Role of Visualization Support interactive exploration
Help in result presentation
Disadvantage: requires human eyes
Can be misleading

7. Bad Visualization Y-Axis scale gives WRONG impression of big change
Year
Sales
1999
2110
2000
2105
2001
2120
2002
2121
2003
2124
Y-Axis scale gives WRONG
impression of big change

8. Better Visualization Axis from 0 to 2000 scale gives
Year
Sales
1999
2110
2000
2105
2001
2120
2002
2121
2003
2124
Axis from 0 to 2000 scale gives
CORRECT impression of small change

9. Another Bad Visualization
Lie Factor=14.8
(E.R. Tufte, “The Visual Display of Quantitative Information”, 2nd edition)

10. Lie Factor The degree to which the graphical representation of a
particular effect matches the reality
For the fuel economy graph
Tufte’s requirement: 0.95<Lie Factor<1.05
(E.R. Tufte, “The Visual Display of Quantitative Information”, 2nd edition)

11. Tufte’s Principles of Graphical Excellence
Give the viewer
the greatest number of ideas
in the shortest time
with the least ink in the smallest space.
Tell the truth about the data!
(E.R. Tufte, “The Visual Display of Quantitative Information”, 2nd edition)

12. Visualization Methods
Visualizing in 1-D, 2-D and 3-D
Well-known visualization methods
E.g., histogram, box plot, scatter plot
Visualizing more dimensions
Scatter Plot Matrix
Parallel Coordinates
Chernoff Faces
Stick Figures

13. 1-D (Univariate) Data Representations Histogram Tukey box plot 20 7 53 1
Tukey box plot
Middle 50%
low
high
Mean 20
Histogram

14. 2-D (Bivariate) Data
Scatter plot, …
price
mileage

15. 3-D Data (Projection)
price

16. 3-D Image Requires 3-D blue and red glasses
Taken by Mars Rover Spirit, Jan 2004
Requires 3-D blue and red glasses

17. 4+ dimensions: Multiple Views
Give each variable its own display 1
A B C D E 2 3 4
A B C D E
Problem: does not show correlations

18. Scatter Plot Matrix Represent each possible pair of variables in their
own 2-D scatterplot
(car data)
Q: Useful for what?
A: linear correlations
(e.g. horsepower & weight)
Q: Misses what?
A: multivariate effects

19. Parallel Coordinates Encode variables along a horizontal line
Vertical line specifies values
Same dataset in parallel coordinates
Dataset in a Cartesian coordinates
Invented by
Alfred Inselberg
while at IBM, 1985

20. Example: Visualizing Iris Data
Iris versicolor
Iris setosa
Iris virginica

21. Example: Iris (2) Sepal Length Petal length Petal Width Sepal Width
3.5
5.1
0.2
1.4

22. Example: Iris (3) 3.5 5.1 1.4 0.2 Each data point is a line.
Similar points correspond to similar lines.
Lines crossing over correspond to negatively correlated attributes.
Problems:
order of axes
up to ~20 dimensions

23. Chernoff Faces Encode different variables’ values in characteristics
of human face
Fun applets:

24. Stick Figures Two variables mapped to X, Y axes
Other variables mapped to limb lengths and angles

25. Illustration of Stick Figure Use
Census data showing
age, income, sex,
education, etc.
Closed figures correspond to women and we can see more of them on the left.
Note also a young woman with high income

26. Summary Many methods Visualization is possible in more than 3-D
Aim for graphical excellence (and truth!)
Free and open-source software
Ggobi
Xmdv
Others (see