Advanced Data

Visualization
and Interpretation
(Part 1)

2
Overview

The Art of Effective Data Visualization

Chart Types
The Art of Effective
Data Visualization
Colour Theory
Color is a highly subjective topic. Reactions to individual colors will vary between people and
cultures

Color theory, on the other hand, is an advanced and evidence-based science that can teach us a
lot.

Concepts

Color Palette: Color blindness: Color Meaning:

Choose a color palette that is Be mindful of colorblindness Use color to convey meaning,
visually appealing, consistent, when choosing colors. Use such as highlighting trends,
and appropriate for the data. contrasting colors and consider grouping categories, or
Consider using a limited alternative methods for indicating positive or negative
number of colors to avoid representing data, such as values.
overwhelming the viewer. patterns or shapes.
Colour Harmony
Color harmony refers to aesthetically pleasing combinations of colors, which enhance the user’s
experience

Three colors evenly Colors opposite each

spaced around the other on the color
color wheel (e.g., red, wheel (e.g., red and
yellow, and blue). They green). They provide
offer a balanced and high contrast and
vibrant palette. visual interest.

Variations in lightness Colors next to each other on

and saturation of a the color wheel (e.g., blue,
single color. They are blue-green, and green). They
easy on the eyes and create a harmonious and
produce a cohesive look. pleasing effect.
Colour Palette

Color palettes are a collection of colors that are used together to create
a cohesive and visually appealing design

Choose a color palette that is visually appealing, consistent, and

appropriate for the data. Consider using a limited number of colors to
avoid overwhelming the viewer.
Types of Palette

Qualitative Sequential Diverging

Use distinct colors for different This palette is designed with The use of two contrasting
categories. Ensure enough discrete steps or a continuous colors to represent values
contrast between colors to gradient above and below a central
distinguish categories easily. point.
This is useful for highlighting
deviations from a norm.
Design Principles
Keep the visualization simple and uncluttered. Avoid
Simplicity
unnecessary details that can distract the viewer.

Use clear and concise labels, titles, and legends. Ensure

Clarity that the data is presented in a way that is easy to
understand.

Use consistent formatting, fonts, and colors throughout the

Consistency
visualization.

Use visual cues, such as color, size, or shape, to emphasize

Emphasis
important data points.

Use white space effectively to create visual breathing room

White Space
and improve readability.
Data Storytelling
Data storytelling is the practice of using narratives and visualizations to
effectively communicate insights from data to an audience.
It's about transforming raw data into a compelling story that resonates
with people and drives action.
Key Elements of Data Storytelling

Data Narrative Visualizations

The foundation of the The story arc that connects Charts, graphs, and other
story. It should be the data points, creating a visual aids that make the
accurate, relevant, clear and engaging data more understandable
and insightful. message. and impactful.
Effective Data Storytelling

KNOW YOUR AUDIENCE

TELL A STORY

USE A NARRATIVE

ENGAGE THE VIEWER

Chart Types
What are Charts?

Chart are visual representations of data that help to easily

understand and interpret complex information.

They are essential tools for data analysis, presentation, and

decision-making.
Common Basic Chart Types
Bar Charts
Compare categories or groups.
Characteristics: Rectangular bars with lengths proportional to the values they represent.

Simple Bar Chart Stacked Bar Chart Clustered Bar Chart

Compares values across Shows the contribution of Compares multiple categories

different categories different sub-categories to a within each group
total
Bar Chart (Example)
Subject Gender Age
Literature Male 15
Literature Female 16
Chemistry Male 16
Literature Female 17
Chemistry Male 18
Literature Female 16
Literature Male 17
Literature Female 16 Simple bar chart showing the number
of students taking each subject
Chemistry Male 25
Chemistry Female 17
Bar Chart (Example)
Subject Gender Age
Literature Male 15
Literature Female 16
Chemistry Male 16
Literature Female 17
Chemistry Male 18
Literature Female 16
Literature Male 17
Literature Female 16 A stacked bar chart showing the number
of students taking each subject and how
Chemistry Male 25
different genders contribute to it
Chemistry Female 17
Bar Chart (Example)
Subject Gender Age
Literature Male 15
Literature Female 16
Chemistry Male 16
Literature Female 17
Chemistry Male 18
Literature Female 16
Literature Male 17
Literature Female 16 A clustered bar chart comparing the
distribution of each gender taking
Chemistry Male 25
different subjects
Chemistry Female 17
Common Basic Chart Types

Pie Charts
Show the proportion of different categories within a
whole (100%).

Characterized by a circle divided into sectors, each

representing a percentage of the total.

It is not suitable for comparing many categories or

small differences.
Pie Chart (Example)
Subject Gender Age
Literature Male 15
Literature Female 16
Chemistry Male 16
Literature Female 17
Chemistry Male 18
Literature Female 16
Literature Male 17
Literature Female 16 Pie chart showing the distribution of male
and females.
Chemistry Male 25
Chemistry Female 17
Pie Chart (Example)
Subject Gender Age
Literature Male 15
Literature Female 16
Chemistry Male 16
Literature Female 17
Chemistry Male 18
Literature Female 16
Literature Male 17
Literature Female 16 Pie chart showing the distribution of
students taking each subject
Chemistry Male 25
Chemistry Female 17
Common Basic Chart Types
Line Charts:
This is used for showing trends over time or across a continuous variable.
Points connected by lines to represent changes in values.

Simple Line Chart Multiple Line Chart Area Chart

This is used to show a single This is used to compare multiple The space between the line and
trend on the chart. trends in one line chart. the axis is filled to emphasize
the magnitude of change.
Line Chart (Example)
Year Sample A Sample B
2015 288 563
2016 788 675
2017 655 176
2018 647 717
2019 568 518
2020 457 616
2021 567 617
2022 656 716 A simple line chart showing the quantity
sold for Sample A across the years
2023 673 725
2024 637 417
Line Chart (Example)
Year Sample A Sample B
2015 288 563
2016 788 675
2017 655 176
2018 647 717
2019 568 518
2020 457 616
2021 567 617
2022 656 716 A multiple line chart comparing the
quantity sold for Sample A against
2023 673 725
Sample B across the years
2024 637 417
Line Chart (Example)
Year Sample A Sample B
2015 288 563
2016 788 675
2017 655 176
2018 647 717
2019 568 518
2020 457 616
2021 567 617
2022 656 716 An Area chart showing the quantity sold
for Sample A across the years.
2023 673 725
Same as line but with shaded area
2024 637 417
Advanced Chart Types
Sankey diagrams
These is a powerful visualization technique that excels at depicting flows
and transformations within a system.
They are particularly useful for understanding complex processes,
identifying bottlenecks, and analyzing the distribution of quantities.

Key Components

Nodes: Represent the Links: Connect the nodes, Link Width: The width of
different stages, entities, illustrating the flow of each link is proportional to
or categories within the quantities (e.g., energy, the magnitude of the flow
system. materials, data, money) it represents.
between them.
Sankey Diagram (Example)

Use case: number of people

number of
people migrated
migrating from
Analyzing the rate one country (left)
to the country
of migration (right)
between regions
Applications of Sankey Diagram

Web Traffic Supply Chain Energy Flow Data

Analysis Management Transformation
 Advanced Chart Types
Heat maps
These are graphical representations of data where values are depicted
by color.
They use a system of color-coding to represent different values, often
using a gradient from cool colors (e.g., blue) to warm colors (e.g., red) to
indicate increasing values.
Key Components

Color Gradient: A Grid or Matrix: Data is Visual Patterns: Patterns

continuous range of colors organized in a grid or and trends emerge
representing data values. matrix format. visually, highlighting areas
of high and low values.
Heat Map (Example)
horse- model_
mpg cylinders displacement weight acceleration
power year
mpg 1 -0.775 -0.804 -0.778 -0.832 0.42 0.579
cylinders -0.775 1 0.951 0.843 0.896 -0.505 -0.349
Use case:
displacement -0.804 0.951 1 0.897 0.933 -0.544 -0.37
Visualizing
Correlation horsepower -0.778 0.843 0.897 1 0.865 -0.689 -0.416
coefficient weight -0.832 0.896 0.933 0.865 1 -0.417 -0.307
for better
acceleration 0.42 -0.505 -0.544 -0.689 -0.417 1 0.288
readability
model_year 0.579 -0.349 -0.37 -0.416 -0.307 0.288 1
Applications of Heat Map

Geographical Analysis

Website Optimization

Machine Learning
Advanced Chart Types
Radar Chart
This is also known as spider charts or star plots
It is a graphical method for displaying multivariate data in the form of a two-dimensional chart
of three or more quantitative variables represented on axes starting from the same point

Key Components

Radial Axes: Multiple Data Points: Data Polygon Shape: A line Visual Comparison:
axes (spokes) radiate values for each connects the data The shape and size of
from a central point, variable are plotted points for each the polygon provide a
each representing a along their respective variable, forming a visual comparison of
different variable. axes. polygon. the data across
different variables.
Radar Chart (Example)
Use case:
Comparison of the skills level between different species in a forest.

Sp. Sp.
Name HP Attack Defense Speed
Atk Def

Bulbasaur 45 49 49 65 65 45

Charmander 39 52 43 60 50 65

Squirtle 44 48 65 50 64 43
Applications of Radar Chart

Product Comparison

Performance Analysis

Portfolio Analysis
Advanced Chart Types
Network Graph
Network graphs are a powerful visualization technique used to depict
relationships and connections between different entities.
They are widely used in various fields, including social network analysis,
computer science, biology, and transportation.

Key Components

Nodes: Represent Edges (or Links): Connect nodes, illustrating the

individual entities (e.g., relationships between them. These
people, computers, relationships can be various, such as
websites, molecules). friendships, data transfers, or chemical bonds.
Network Graph (Example)

Use case A (Undirected Use case C (Directed

and Unweighted) and Unweighted)
They are connected but The connection is
no direction and no unweighted: just
weight. connected or not.
For example living in the For example following on
same house X

Use case B (Undirected Use case D (Directed

and Weighted) and Weighted)
Same as B, the weight is Same as C, the weight is
the intensity. the intensity.
For example copies of Migration from one
publications sold country to another.
Applications of Network Graph

Computer
Science Transportation

Social Network Biology

Analysis
Conclusion
Data visualization transforms raw data into meaningful and impactful visuals, making it easier
to understand, interpret, and communicate insights.

Chart types serve different purposes:

• Bar charts: Compare categories.
• Line charts: Show trends over time.
• Pie charts: Illustrate proportions.

Specialized visualizations like the

• Sankey diagrams depict flows and transformations within a system,
• Network graphs Illustrate connections and relationships between entities,
• Radar charts compare multiple variables for a single subject.
• Heatmaps visualize data density and patterns

The principles of effective data visualization are important to ensure that insights are captured
by the audience