The picture can't be displayed.

Principles of Data Visualization

Descriptive Data Visualization

 Data Visualization
— In the Beginning…
— Graphics Movement
— Information Visualization
— Data Visualization

2
 In the Beginning . . .
— When did graphical visualization begin?
— 1930s
— 1960s
— 1990s
— 2000s
— Last year

3
Descriptive - Early Examples
William Playfair
Scottish Engineer
19th Century

4
 Graphics Movement
— Jacques Bertin introduced the concept of graphical encoding
— Not Artwork, it is a system of signs that convey meaning
— We will learn to “see” relationships in data
— Process of finding the right questions to answer

5
What is common?

Jacques Bertin 6
Types of Questions

Jacques Bertin 7
 Elementary Questions
— How many Females stay in February?

X Axis

Y Axis

Jacques Bertin 8
 Processing Routine
— Every cell above average is filled in with black

Jacques Bertin 9
 Intermediate Question
— Relationship of the group of months Dec, Jan, Feb
— To the grouping of characteristics on the x axis

Winter Pattern Repeating

Jacques Bertin 10
 Overall Information Level
— Generation of a set of insights

Jacques Bertin 11
 Visual Analysis Process
① Define the Problem / Objective
② Structure the Data
③ Adopt a Processing Technique
④ Simplify without Destruction
⑤ Communication

Jacques Bertin 12
8 Variables of Visual Encoding

Jacques Bertin 13
 X-Y Encoding as a Point
— Using size for the Z axis
— A and B are cities
— P is population in thousands
— S is surface area in square kilometers

Jacques Bertin 14
 X-Y Encoding as a Line
— Using size for the Z axis
— A and B are cities
— P is population in thousands
— S is surface area in square kilometers

Jacques Bertin 15
 X-Y Encoding as Area
— Using size for the Z axis
— A and B are cities
— P is population in thousands
— S is surface area in square kilometers

Jacques Bertin 16
 Size versus Value in the Z axis
— X-Y encoding as area
— Qualitatively compare the degree of black to white in 1
— Quantitatively compare size of each box in 2

Jacques Bertin 17
 Texture

Point

Line

Area

Jacques Bertin 18
 Color
— Red, Green, Blue Cones in our eyes receive color stimulus
— Color is provided by filtering/reducing the amount of RGB
— In RGB-A the “A” measures the amount opacity
— Arrangement of light to dark provides an order

Jacques Bertin 19
 Orientation
— Easier to interpret than shape
— Can be used in combination with size

Jacques Bertin 20
 Shape
— Shapes must be a certain size to have visual meaning
— When size contrast is low shapes have a small utility

Jacques Bertin 21
 What is Data?
— Something a computer system creates?
— Bits and bytes?
— Stuff in a database table?
— Pulses of light?
— Something Google makes?

22
 Data is an Observation

Phenomena Recording Measurements

Water Temperature Time

113° F @ 5:28 PM
127° F @ 5:31 PM
149° F @ 5:44 PM
177° F @ 5:50 PM
...
is data !!!

23
 Types of Data
— Nominal – assigns measurement to a category

— Ordinal – measurements in an order or sequence

— Interval – measurements in equal positions from each other

— Ratio – measurements can be fractions / multiples

24
 Nominal Data
Nominal data is composed of categories

Smart Phones

Product Categories Laptops

Servers

25
 Ordinal Data
Ordinal data is defined by a sequence

1. Exxon
2. AT&T
3. General Motors
Top 10 Customers
4. KB Homes
5. Kimberly Clark
6. ...

26
 Interval Data
Interval data is defined by an equal distance between units

Only relative values are significant, no absolute or zero point

1. 97°
2. 98°
3. 99°
Temperature
4. 100°
5. 101°
6. ...

27
 Ratio Data
Ratio data is defined by numeric ratios of comparisons

Use an absolute zero point

$25,000 (compared to zero)

10% (10 compared to 100)

400 Hours (compared to zero)

28
 Continuous & Discrete Data
— Continuous data elements can take on any value between one
number and another number

Weight: (140.25 lb … 152 lb … 161.7 lb)

— Discrete data elements can be counted as unique and separate

2,000 Servers
400 Dog Collars
42 Ice Cream Cones

29
Data Visualization Stack

Visualization

Insights

Information

Data Organization

Data Source

Measurements

Phenomena

30
 Information vs. Data

Information is a conceptual understanding (communication)

Physical state of water changes at 0° and 100°

Operates at a higher level than data (measurements)

70°… 71° … 72° … 73° … 74°

31
 What is an Insight?

Insights are new or fundamental understanding about the world

Matter has states of solid, liquid, and gas

Application or dynamics of understanding (communication)

Physical state of water changes at 0° and 100°

32
 What is an Insight?

Source: Malcom Gladwell

33
 Financial Example
— money.visualcapitalist.com/all-of-the-worlds-money-and-
markets-in-one-visualization/

Source: money.visualcapitalist.com
34
 Summary
— Questions exist at multiple levels of information
— Primary variables of image are X & Y dimensions with size and
value in the Z dimension
— Texture, color, orientation, and shape make up the differential
variables
— Data is the capture of a phenomena
— Information is a synthesis of data measurements
— Insight is something unusual or significant

35