CHAPTER 1 - DATA VISUALIZATION

CAN BE VISUALIZED (4)

- VISIBLE REALITY
- HIDDEN REALITY
- INVISIBLE REALITY
- ABSTRACT REALITY
HOW TO VISUALIZE THEM? (4)
VISUALIZATION TYPES / FEATURES
- 2D VS 3D
- STATIC VS MOTION
- VIRTUAL VS MATERIALIZED
- REALISTIC VS ABSTRACT
VISUALIZATION USAGES (6) MAJOR USE CASES
- PRESENTATION
- REPORTING
- ANALYTICAL
- MONITORING
- PUBLIC COMMUNICATION / JOURNALISM
- DEMONSTRATION / SIMULATION
PROCESS OF VISUALIZATION
-
CHAPTER 2 - DATA AND TASK ABSTRACTION
DATA COLLECTION METHODS (5)
- SENSORS
- LOGS
- EXPERIMENTS
- HUMAN - GENERATED DATA
- SURVEYS
ATTRIBUTE TYPES (6)
- CATEGORICAL
- ORDINAL
- QUANTITATIVE
- SEQUENTIAL
- DIVERGING
- CYCLIC
PROCESS OF TASK ABSTRACTIONS
-
CHAPTER 3 - MARKS AND CHANNELS
CHANNEL TYPES (2)
- IDENTITY CHANNELS
- MAGNITUDE CHANNELS
MARK TYPES (2)
- CONNECTION MARK
- CONTAINMENT MARK
CHAPTER 4 - COMMON VISUALIZATION IDIOMS
BIG DATA VISUALIZATION CATEGORIES (5)
- TEMPORAL
- HIERARCHICAL
- NETWORK
- MULTIDIMENSIONAL
- GEOSPATIAL
VISUALIZATION FORMS
- BAR CHART
- LINE CHART
- SCATTERPLOT
- SPARKLINE
- PIE CHART
- GAUGE
- WATERFALL CHART
- FUNNEL CHART
- HEAT MAP
- HISTOGRAM
- BOX PLOT
- MAPS
- TABLES
- INDICATORS
- AREA CHART
- RADAR OR SPIDER CHART
- TREE MAP

Information Design
- Practice of presenting info
Information Visualization
- Study of visual representation
Infographics
- Mixture of texts
Sparkline
- Embedded small chart
Diagram
- Qualitative information, include small chart
Separability
-
Visual Pop out
- Standout item
Popout
- Preattentive processing / tunable detection
Illustrational diagram
- Visualize quantitative, qualitative data
Dashboard
 - Visual oriented display consolidated and arranged in a single screen
Data visualization
- To interpret and gain insight to data
Visualization
- Vision, forming visual image
Mark
- Basic graphical element, geometric primitives
Data presentation
- Summarized information
 CHAPTER 1 - OVERVIEW OF DATA VISUALIZATION

EBOOK VISUALIZATION
 1. Visualization
2. Data Visualization
3. Data Visualization Catalogue
4. Data Presentation
5. Infographic
6. Information Visualization
7. Illustrational chart
8. Sparkline
9. Diagram
10. Illustration of idea

BABADCBDAD

Visualization
- Vision
- Process of forming visual image
Data Visualization
- Graphical representation and presentation of data for the purpose of perception and understanding.
- More interactive in software
The Data Visualization Catalogue
- Provides an excellent introduction to different types of visualizations
- Explore the Search by Function feature to find the best visualizations for a given purpose
Data Presentation
- In statistics, method that people summarize, organize and communicate information using a variety of
tools, including tables and diagrams/charts.
Infographics
- Mixture of texts, graphics, data visual forms to quickly and vividly communicate complex information
Information Visualization
- Study of visual representations of information or data to reinforce human cognition. Numeric and non
numeric data like geographic info and text
Sparkline
- Small chart embedded in a context of words, numbers, tables, images, or other type of information
- Presents general shape of variation in simple and highly condensed way
Illustration of Idea
- Can be considered as information visualization but not data visualization

1.
INTRODUCTION TO VISUALIZATION

Visualization
- Vision
- Process of forming visual image

Can be visualized:
- Visible Reality
-
- Hidden Reality
-
- Invincible Reality
-
- Abstract Reality
-

Types/Features of Visualization Forms

- 2D/3D
- Static vs Motion
- Virtual vs Materialized (computerized vs built in real world)
- Reality vs Abstract (Realistic Object vs Abstract Shape)

Visualization Process
- May change original forms and create new forms of things
- Sample: using an Arrow for Air flow

Data Visualization
- Graphical representation and presentation of data for the purpose of perception and understanding.
- More interactive in software
Data
- Numerical values describing entity/activity
- Abstract

Related fields
- Data presentation
- Information design/visualization, illustration
- Business data visualization
- Big data visualization

Data Presentation
- In statistics, method that people summarize, organize and communicate information using a variety of
tools, including tables and diagrams/charts.

Data Visualization
- Data
- Information
- Insights to huge data through vis representations - interactive/raw data
- Enhance learning, understanding, reasoning, helps in decision making
- Link in raw data and us
- Lead a user to: detect patterns, trends, and correlations in data
- Prompt a user to: draw inferences, anticipate potential trajectories and outcomes

Information Design
- Practice of presenting information
- Layout, flow, use of text style, bullets, spacing, etc

Information Visualization
- Study of visual representations of information or data to reinforce human cognition. Numeric and non
numeric data like geographic info and text
Infographics
- Mixture of texts, graphics, data visual forms to quickly and vividly communicate complex information

Infographics vs Data Visualization

- Infographics are one time use, casual use for general people. Presentation only. Fixed datra set or
numbers, general info- qualitative, to impress casual viewers.
- Data visualization use data processing or analytical tools form a data source, interactive, quantitative,
automatically populated, dynamic data source

Computer Graphics
- Computer generated graphics based on logic and algorithms
- Computing intensive
- Do not use business / transactional data from human

Scientific Visualization
Physical Science Visualization
- Concerned with Three dimensional phenomena, meteorological, medical, biological
- Simulation of reality
Mathematical Model/Algorithm Visualization
- Math calculations/ models
Business Data/ Information Visualization
Business-
- Describes events, activities, operations that make a system running
- Activities associated with human, that impacts human
Business Data Features:
- Abstract - represents patterns
- Quantitative
- structured/ semi-structured, repeated
- Multi dimensional
- Comprehensible
Business Data Visualization Features:
- Info seeking, analysis, decision support, monitoring, communication
- Simple standard abstract images
- Reused
- Data binding techniques
Where is data visualization used in business?
- BI Analysis / self-service
- Presentation results in data mining
- Visual analytics
- operational/administrative monitoring
Business Data Visualization
- Periodical Reports
- Performance Dashboards
- Visual data exploration and seeking
- Visual analytics
- Real time monitoring
Not Business Data Visuals
- Not meaningful business data
- Mathematical visuals
- Scientific visualization
- Reality simulation
- Infographics /data graphics
- Too much artistic, visual embellishment

WHY DATA VISUALIZATION

- Visualizing is basically a human physiological and psychological capability, and plays important role in
human information behaviour and decision making
- Recall or memorize data more effectively
 - Enable fast perception based on instinct
- Hel;ps data comprehension and enhance problem solving capabilities (cognition)
- extract/provoke additional (implicit) perspectives and meaning
- Ease the cognitive load of information processing and information
- Help to shape the alteration and focus
- Effective communication (storytelling)
- In specific:
- Identify patterns and trends
- Quickly focus on area of interest or area of difference identify structures or relationships
- More comprehendible with familiar visual context
- Identify structures and relationships that are hard to express in words

Data Visualization in BI/Analytics

- Data Viis- important part of data exploration
- Digestible insights
Conditional Formatting
- Direct formatting on text or numbers using visual properties, embedded in a pre-established
presentation
Sparkline
- Small chart embedded in a context of words, numbers, tables, images, or other type of information
- Presents general shape of variation in simple and highly condensed way
Chart
- Graphical representation of data
- Cunique combination of symbols directly represents quantitative values
VISUALIZATION

ASSIGNMENT #1
1. What is Data?
Data refers to a collection of raw facts, figures, symbols, or observations that are typically in numerical,
textual, or other formats. Data is the foundation of information and knowledge and can be processed and
analyzed to reveal insights, patterns, and relationships.

2. Different Types of Data:

There are various types of data, including:

1. Numerical Data: Quantitative data represented by numbers. Examples include age,

temperature, and income.

2. Categorical Data: Qualitative data is represented by categories or labels. Examples include

gender, color, and product types.

3. Ordinal Data: Categorical data with a specific order or ranking. Example: Education levels (e.g.,
high school, bachelor's, master's).

4. Time Series Data: Data collected over time at regular intervals. Examples include stock prices,
weather data, and sales records.

5. Text Data: Unstructured textual information. Examples include tweets, articles, and reviews.

6. Spatial Data: Data with geographic information. Examples include maps, GPS coordinates, and
satellite images.

7. Binary Data: Data with only two possible values. Examples include yes/no, true/false, and 0/1.

3. What is Visualization and Data Visualization?

Visualization is the representation of data in a visual or graphical form, making complex information
more accessible and understandable. Data visualization specifically involves using visual elements like charts,
graphs, maps, and other visual aids to present data in an easily interpretable manner.

4. Why is Data Visualization Important?

Data visualization is important because it allows people to comprehend and interpret complex data
patterns, relationships, and trends quickly. It aids in decision-making, communication, and analysis by
presenting information in a way that is more intuitive and impactful than raw data.

5. Characteristics of Data Visualization:

Effective data visualization should possess the following characteristics:

1. Clarity: The visualization should convey the intended message clearly and without ambiguity.

2. Simplicity: Complex data should be simplified without losing key insights.

3. Relevance: The visualizations should be relevant to the audience's needs and interests.

4. Accuracy: The data should be accurately represented to avoid misinterpretation.

5. Interactivity: Interactive visualizations allow users to explore and manipulate data for deeper
insights.

6. Data Visualization Techniques and Examples:

There are various data visualization techniques, including:

1. Bar Chart: A chart that represents data with rectangular bars. Example: A bar chart showing monthly
sales of different products.
 2. Line Chart: A chart that depicts data points connected by lines. Example: A line chart showing
temperature variations over a week.

3. Pie Chart: A chart that divides a whole into parts using sectors of a circle. Example: A pie chart
showing the distribution of a budget among different expenses.

4. Scatter Plot: A plot of data points on a two-dimensional plane. Example: A scatter plot illustrating
the relationship between height and weight.

5. Heatmap: A matrix of colors representing data values. Example: A heatmap showing website traffic
across different hours and days.

7. What Makes Data Visualization Good?

A good data visualization should be:

1. Clear and Concise: Convey information without clutter and confusion.

2. Engaging: Capture the viewer's attention and keep them interested.

3. Insightful: Highlight key trends and patterns in the data.

4. Relevant: Address the intended audience's needs and questions.

5. Interactive: Allow users to explore data on their own terms.

6. Ethical: Present data fairly and avoid misrepresentation.

7. Aesthetic: Well-designed visualizations enhance understanding and perception.

In summary, data visualization transforms raw data into meaningful insights through visual
representation, making it easier for individuals to understand, analyze, and communicate complex information.

SELF-ASSESSMENT #1

1. Having a human in the decision-making loop allows for contextual understanding, empathy, and ethical
considerations that computers may lack.

2. Computers in the loop provide data processing speed, accuracy, and the ability to handle large volumes
of information efficiently.

3. Using an external representation can help simplify complex data and make it more understandable,
aiding decision-making.

4. Depending on vision is a common way to leverage human's strong visual processing capabilities for
data interpretation.

5. Showing data in detail enables users to explore and understand the nuances, supporting informed
decision-making.

6. Interactivity enhances user engagement and allows for dynamic exploration and analysis of data.

7. The design space for visualization idioms is vast because different data types and tasks demand
unique visual approaches.
8. Focusing on tasks ensures that visualizations are purpose-driven, addressing specific user needs. To
address the similarities and differences of specific user needs.

9. Many designs are ineffective due to a lack of understanding of user requirements, leading to poor
usability.

10. Caring about effectiveness ensures that visualization solutions serve their intended purpose, leading to
better decision-making.

11. Validation is difficult because it often involves subjective judgments and can be influenced by biases
and context.

12. Resource limitations can include hardware constraints, budget constraints, and time constraints,
impacting the complexity and quality of visualizations. In more simple terms, visual information on
computers cannot handle infinity even a human brain experience what we call short term memory loss
due to its limited capacity.

13. Analyzing visualization helps uncover insights, patterns, and anomalies in data, improving
decision-making and understanding by thinking systematically. .
 CHAPTER 2 - INPUT, DATA & TASK ABSTRACTION

1. Attribute - is something that can be measured, observed, or logged

2. Link - is a relationship between items
3. Types - type of data is its structural or mathematical interpretation
4. Semantics - meaning of it / semantic of data is the real world meaning
5. Data Abstraction - is about understanding your data
- Reducing complexity of large datasets by displaying them in a format that is easier to handle
and comprehend
- Onscuring irrelevant elements, emphasizing crucial information
6. -grid - strategy used for sampling continuous data, positions -
7. Geometry - or SPATIAL - items/positions
8. Diverging - e.g. temperature, altitude - specifies information about the shape of items with explicit
spatial positions. The items could be points, or one-dimentional lines or curves, or 2D surfaces or
regions, or 3D volumes
9. Cyclic - e.g hour, week, month
10. Task Abstraction - why is the user lloking at it? The GOAL is to transform user task from a domain
specific language into a high-level concise representation. In task abstraction, you need to collect
user’s tasks first or their QUESTIONS

2.
 3. Focus group -
4. Observation -
5. Survey -
6. Exploratory Prototype -
7. -experiment -
8. Low-level -
9. High-level -
10. Ereder? -
11. Race -

INPUT, DATA & ABSTRACTION

INPUT, DATA & TASK ABSTRACTION

Identify dataset and attribute types

- Religion by country data - multidimensional table
- Migrant deaths data - tabular data
Dataset Types
- Tables - tabular data
- Networks - nodes, link TREES: subset of networks
- Spatial - data elements maps tot he earth: position / field - grid
Attribute - column of a table
- Categorical attribute - distinct things inside of them (distinct things that don’t have an order between
them)
- Ordinal attribute - distinctly different things but have an order between them
- Quantitative attributes - numbers - specific quantities

country religion population

China Christian 1,000,000

(categorical attribute) categorical quantitative

Cause of death Number of dead / date location

missing

categorical quantitative ordinal Latitude longitude

categorical

SELF-ASSESSMENT #2
1. Task abstraction in data visualization simplifies complex data analysis goals into specific, manageable
objectives. For instance, when analyzing e-commerce data, you might abstract tasks like understanding
product popularity by age group, visualizing sales by region, and tracking the impact of discounts. Each
of these tasks can then be addressed through focused visualizations to extract meaningful insights.
- Collecting user's task
- Example: conveying the meaning of the data either by identifying its category and structure.
- "Why is the user looking at it?"

2. Data abstraction in data visualization simplifies complex datasets into more digestible forms. For
instance, when analyzing daily stock price data, you might abstract it into monthly or quarterly trends,
showing average prices and trading volumes over time. This simplification aids in identifying long-term
patterns while reducing the intricacy of daily price fluctuations.
- Structural or mathematical interpretation
- "What is shown"
- Task abstraction is about understanding your data
3. Data abstraction is important because it allows users and developers to work with complex systems
more effectively by simplifying the interactions and reducing cognitive load. It also promotes modularity
and code reusability.
- It allows users to easily work with the data

4. The 3 levels of data abstraction in the context of databases are:

- Physical Level: Describes how data is stored on hardware.
- Logical Level: Represents data independently of the physical storage details.
- View Level: Presents a specific perspective of the data to users, often through customized views
or queries.

5. Task Abstraction in Data Visualization refers to simplifying the process of interpreting and
understanding data through graphical representations. For instance, creating a bar chart to show sales
figures abstracts the underlying numerical data, making it easier for users to grasp trends.

6. The different types of datasets are as follows:

- Tables – tabular data
- Networks – nodes, links, like trees (a subset of networks)
- Spatial – geographical location or positioning

7. A Data Set is a collection of data points or information typically organized in a structured format. It can
be a spreadsheet, database table, or any other dataset used for analysis, research, or reference.

8. Creating data sets involves collecting, organizing, and storing data using tools like spreadsheets,
databases, or data collection software. You define the data's structure, format, and any necessary
metadata.

9. Analyzing data sets typically involves:

- Cleaning and preprocessing data to remove errors or inconsistencies.
- Exploring data using descriptive statistics and visualization.
- Applying statistical techniques or machine learning algorithms for deeper insights.
- Interpreting results and making informed decisions based on the data.

LABORATORY EXERCISE #1
CHAPTER 1 - DATA VISUALIZATION Data visualization
CAN BE VISUALIZED (4) - To interpret and gain insight to data
- VISIBLE REALITY Visualization
- HIDDEN REALITY - Vision, forming visual image
- INVISIBLE REALITY Mark
- ABSTRACT REALITY - Basic graphical element, geometric primitives
HOW TO VISUALIZE THEM? (4) Data presentation
- 2D VS 3D - Summarized information
- STATIC VS MOTION
- VIRTUAL VS MATERIALIZED
- REALISTIC VS ABSTRACT
VISUALIZATION USAGES (6) MAJOR USE CASES
- PRESENTATION
- REPORTING
- ANALYTICAL
- MONITORING
- PUBLIC COMMUNICATION / JOURNALISM
- DEMONSTRATION / SIMULATION
PROCESS OF VISUALIZATION
-
CHAPTER 2 - DATA AND TASK ABSTRACTION
DATA COLLECTION METHODS (5)
- SENSORS
- LOGS
- EXPERIMENTS
- HUMAN - GENERATED DATA
- SURVEYS
ATTRIBUTE TYPES (6)
- CATEGORICAL
- ORDINAL
- QUANTITATIVE
- SEQUENTIAL
- DIVERGING
- CYCLIC
PROCESS OF TASK ABSTRACTIONS
-
CHAPTER 3 - MARKS AND CHANNELS
CHANNEL TYPES (2)
- IDENTITY CHANNELS
- MAGNITUDE CHANNELS
MARK TYPES (2)
- CONNECTION MARK
- CONTAINMENT MARK
CHAPTER 4 - COMMON VISUALIZATION IDIOMS
BIG DATA VISUALIZATION CATEGORIES (5)
- TEMPORAL
- HIERARCHICAL
- NETWORK
- MULTIDIMENSIONAL
- GEOSPATIAL
VISUALIZATION FORMS
- BAR CHART
- LINE CHART
- SCATTERPLOT
- SPARKLINE
- PIE CHART
- GAUGE
- WATERFALL CHART
- FUNNEL CHART
- HEAT MAP
- HISTOGRAM
- BOX PLOT
- MAPS
- TABLES
- INDICATORS
- AREA CHART
- RADAR OR SPIDER CHART
- TREE MAP

Information Design
- Practice of presenting info
Information Visualization
- Study of visual representation
Infographics
- Mixture of texts
Sparkline
- Embedded small chart
Diagram
- Qualitative information, include small chart
Separability
-
Visual Pop out
- Standout item
Popout
- Preattentive processing / tunable detection
Illustrational diagram
- Visualize quantitative, qualitative data
Dashboard
- Visual oriented display consolidated and arranged in a single screen