0% found this document useful (0 votes)
3 views

Data Visualization - Lecture 01

Uploaded by

jaswinder singh
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
3 views

Data Visualization - Lecture 01

Uploaded by

jaswinder singh
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 60

WEEK 1: INTRODUCTION TO

DATA VISUALISATION

Programme BSHDS - Bachelor of Science (Hons) in Data


Science
[email protected]
LECTURE OVERVIEW

• What is Data Visualisation?


• Concepts and Definitions.
• Historical Perspective on Data
Visualisation
• Characteristics of Data, Data Types
and Information
• Ethical issues and data visualisation
• Communication through visualisation
• Data Visualisation examples
• Introduction to lab exercises
(tomorrow)
WHAT IS DATA
VISUALISATION?

Concepts and definitions


DEFINING DATA
VISUALIS ATION

“The communication of information


using graphical representations” –
Ward et al, 2010
“Data visualisation is the
presentation of data in a pictorial or
graphical format. It enables decision
makers to see analytics presented
visually, so they can grasp difficult
concepts or identify new patterns. ”
- SAS Software
D E F I N IN G DATA
V IS U A L IS AT ION
(K IR K )

•(Kirk, 2019)
KIRK’S DISSECTION OF THE TERM
“UNDERSTANDING”
WHY IS DATA VISUALIS ATION IMPORTANT?
(S AS.COM)

• Because of the way the human brain processes


information, using charts or graphs to visualize
large amounts of complex data is easier than poring
over spreadsheets or reports
• Data visualisation is a quick, easy way to convey
concepts in a universal manner – and you can
experiment with different scenarios by making
slight adjustments

Image source: https://projectyourself.com/wp-content/uploads/sites/4/2014/08/Depositphotos_10171240_l.jpg


DV AS K E Y TOOL IN T H E
D E M OC RAT IZAT ION OF
DATA

• Employees who aren’t data


scientists or analysts should be
able to:
• ask questions of the data based on
their own business expertise
• quickly and easily find patterns
• spot inconsistencies
• get answers to questions they
haven’t yet thought to ask
DATA CITIZENSHIP

“In the early days of computing, it took a specialist with a


strong background in data science to mine structured
data for information. Today, self-service business
intelligence (BI) tools allow employees at every level of
an organization to run ad hoc reports on the fly. Changes
in how data can be analyzed and visualized allow
workers who have no background in mathematics,
statistics or programming be able to make data-driven
decisions.”
https://whatis.techtarget.com/definition/data-citiz
en
HISTORICAL USES OF
DATA VISUALISATION
ANCIENT HISTORY

•“Earliest visualisations may have taken the form


of drawings in sand or scratched on rock and it is
possible that the famous Palaeolithic cave
paintings in Lascaux, southern France, may have
functioned as both hunting guides and directions
to the spirit world.”
• http://data-art.net/resources/history_of_vis.php

•Example of early Babylonian world map (600 BC)


MODERN HISTORY

• First Pie Chart


• William Playfair
• Statistical Breviary (1801),
showing the proportions of
the Turkish Empire located
in Asia, Europe and Africa
before 1789

Image source: Wikimedia Commons.


• William Playfair's
trade-balance time-
BAL ANCE series chart,
OF TRADE published in his
Commercial and
Political Atlas (1786)

Image source: Wikimedia Commons.


PRIES TLY’S
CH ART OF
BIOG RAPH Y

• Playfair got the idea


for the bar from
Priestly’s Biography
chart.
• Playfair’s was the first
time economic data
was presented in this
way

Image source: Wikimedia Commons.


In this bar chart Scotland's imports and
exports from and to 17 countries in 1781
are represented

P L AY FA I R –
INVENTOR OF BAR
C H A RT

Image source: Wikimedia Commons.


FLORENCE
NIGHTINGALE

• First female member of


Royal Statistical society

• Used charts to make


arguments for public
health

• "a true pioneer in the Image source: Wikimedia Commons.


graphical representation
of statistics"
SOME HISTORY - CHARLES JOSEPH
MINARD
Image source: Wikimedia Commons.
• Charles Minard's map of Napoleon's disastrous
Russian campaign of 1812.

• The graphic is notable for its representation in


two dimensions of six types of data:
• Number of Napoleon's troops
• Distance
• Temperature
• Latitude and longitude
• Direction of travel Image source: Wikimedia Commons.

• Location relative to specific dates

SOME HISTORY - CHARLES JOSEPH


MINARD
MORE MINARD – STYLES STILL USED TODAY

Image source: Wikimedia Commons. Image source: Wikimedia Commons.


CHARACTERISTICS OF DATA,
DATA TYPES AND INFORMATION
• Before visualisation, consider
your data – the critical raw
material for your visualisation
• You’ll use four distinct activities
to start extracting information
D ATA A N D I N F O R M AT I O N –
CHA RACTERISTICS A N D
from your dataset
TYPES
• To this this, you’ll need to
understand your data types
and characteristics
Step 4:
Exploration
Step 3:
Transformati
Step 2: on
Examination
Step 1:
Acquisition
NORMALISED
VS CROSS-
TABUL ATED
DATA
DATA TYPES

Textual Versus
numeric
Discrete versus
Qualitative versus
continuous
quantitative
NOIR (nominal ,
ordinal, interval
and ratio )
What units are your data expressed in?

DATA SIZE AND What is the range? [ minimum, maximum]


SHAPE : For categorical data, how many values are
AMOUNT AND held? Can data points hold more than one
value?
RANGE
• Variety of statistical methods to
investigate data size and shape
• Chart types [CHRTS]
• Categorical : compare categories and
distributions
• Hierarchical: show part-to-whole
D ATA A N D I T S relationships and hierarchies
R E P R E S E N TAT I O N • Relational: explore and explain
correlations and connections
• Temporal: plot trends and intervals over
time
• Spatial: map spatial patterns
SIMPLE BAR CHART

A simple bar chart that displays counts of unique


values for one variable.

The worksheet contains a column of categorical


data named Flaws.

The graph shows the counts for each type of paint


flaw.
6, 15, 13, 6
Image source: Minitab Express Support.
SALES DATA
(USING
TABLEAU)
TABLE VS BUBBLE CHART

Demographics
90.00
36200.00
85.00
30400.00
Demographics 80.00 41700.00

Name Birth Rate Life Expectancy GDP 75.00


Life Expectancy
Brazil 15.20 72.79 $36,700 36700.00
70.00
Japan 8.39 83.91 $36,200 3900.00
India 20.60 67.14 $3,900 65.00

Ireland 15.81 80.32 $41,700 60.00


5.00 7.00 9.00 11.00 13.00 15.00 17.00 19.00 21.00 23.00
Spain 10.40 81.27 $30,400
Birth Rate

YouTube: How To... Draw and Format a Basic Bubble Chart in Excel 2010
ETHICAL ISSUES FOR DATA
VISUALISATION
• Ethical issues with sourcing data
• Research Project Ethical Approval
• Required for research involving human
participants or an analysis of non-public
secondary archived data (that includes
humans related information).
DATA VISUALIS ATION • Non-public secondary archived data :
AND ETHICS Confirmation is required from the owner of
the private data set(s) that access to the data
set, data processing and analysis and public
presentation of the results is permitted.
• Ethical approval to be received prior
conducting the research work ( e.g. data
collection from participants/ data analysis)
• Plagiarism – don’t do it!
Ethical issues in the use of
data visualisations

Beware the possibility of


DATA manipulation of data
visualisation that misleads
VISUALISATION (intentionally or
AND ETHICS unintentionally) the data
consumer

Does your y axis start at


zero – if not, do you have a
good reason and is it clear to
the observer?
SOME EXAMPLES OF
UNETHICAL VISUALIS ATIONS
UNETHICAL
V I S U A L I Z AT I O N
S ( C O N T. )
DANGERS OF RELIANCE ON
VISUALISATION ALONE

Just because the graphic


is “statistical,” does not
make it reliably
informative

Source: http://data-visualisation-
software.com/dangers-of-bling-
data-visualisations
DANGERS OF RELIANCE ON
VISUALISATION ALONE

• Introducing a
third factor in
your
visualisation
removes the risk
of
misinterpretatio
n of data
• How many
Source: http://data-visualisation-software.com/dangers-of-bling-data-
variables is it
VISUAL
TRENDS

•Source:
https://www.statista.com
/chart/7370/was-2016-
really-so-bad-for-
celebrity-deaths/
DV A N D E T H I C S :
“ S H A R P I E G AT E ”

•https://www.youtube.co
m/watch?v=-agIn4JFiK8
COMMUNICATION THROUGH
VISUALISATION
THE NATURE OF GOOD
COMMUNICATION

• Communication is a two-way activity


• Presenting information and ideas, sharing thoughts, seeking feedback
• The data analyst
• The audience
• What are the motivation of both?
• Good research and learning is the key to good communication followed
by preparation , design, execution and feedback
TOP DOWN PROCESSING THEORY

• Psychologist Richard Gregory (1970) argued that perception


is a constructive process which relies on top-down processing
• Stimulus information from our environment is frequently
ambiguous
• To interpret it, we require higher cognitive information either
from past experiences or stored knowledge in order to makes
inferences about what we perceive.
• For Gregory perception is a hypothesis, which is based on
prior knowledge. In this way we are actively constructing our
perception of reality based on our environment and stored
information.
Gregory, R. (1970). The Intelligent Eye. London: Weidenfeld and Nicolson.
PERCEPTION
S CAN BE
AMBIGUOUS

The Necker Cube


NON-REALIZABLE
OBJECTS

• How many boards


• 3?
• 4??
Where is the
ridge?
Where is the gap?
N ON -
R E AL IZAB LE
OB JE C T S

Image source: Ward, M., Grinstein, G. & Keim, D. (2015) Interactive Data
Visualisation: Foundations, Techniques, and Applications. A K Peters Ltd [ISBN: 978 1 4822
5737 3]
WHAT DO YOU SEE?

• Michael Michalko’s creative thinking techniques


give you the extraordinary ability to focus on
information in a different way and different
ways to interpret what you are focusing on.
• To the right is a picture of an old bottle. Look
closely at the artwork on the bottle. What do
you see?
NINE FACES

• There are nine people in this


picture. Inspect the picture and see
how many can you find.
• If you find 6, you have an ordinary
power of observation.
• Find 7, you have an above average
power of observation.
• Find 8, you are very observant.
Congratulate yourself.
• Find 9, you are extremely observant.
You are very intuitive and creative.
DATA VISUALIZATION - SEARCH
TERM

•Source: Google Trends


DATA VISUALIZATION - SEARCH
TERM (BY REGION)
CYCLE DATA
REPORT (NTA)

•Source:
https://data.dublinked.ie
/dataset/cycle-counters
DATA VI S U A L I S AT I ON - E XAM P L E S

•Source: Knowledge is Beautiful


(David McCandless, 2016)
BROWSER MARKET SHARE (2002 – 2009)

Source: https://www.visualcapitalist.com/internet-browser-market-
BROWSER
MARKET
SHARE (2024)
US PRESIDENTIAL ELECTIONS (1952 –
2012)

Red:
Republican
Blue:
Democrat

https://www.270towin.com/1956_Election/interactive_map
ZOOM INTO 2012 – WHO WON?

Image source: https://www.nytimes.com/elections/2012/results/president.html


ZOOM INTO 2012 – NOW WHO WON?

Image source: https://www.nytimes.com/elections/2012/electoral-map.html


AND 2016 ….
HOW ABOUT AN
INFOGRAPHIC?

• https://www.visualcapitalist.com/u-
s-presidential-voting-history-by-
state/
THE PROBLEM WITH MAPS

Source:
http://www.thefunctionalart.com/2016/06/diverging-color-schemes-showin
BREXIT

Source:
Lab/exercises available on
Moodle

LAB Work your way through


EXERCISES exercises

See lab/exercises we can


discuss any questions arising
from lecture/course or
difficulties during lab time
Questions?

You might also like