Systèmes d'Information Décisionnels - Cours - 20150309 - DataVisualisation

Université Paris-Sud
MASTER 1 MIAGE
Cours de Gestion des Systèmes
d’Information Décisionnels
2ème semestre 2014-2015
Cours de Gestion des SI Décisionnels - MASTER 1 MIAGE Paris-Sud Année 2014-2015 – Abed Ajraou - Tous droits réservés

Objectif de la Data Visualisation
• Les 2 objectifs de la data visualisation:
1. Data Analysis: making sense of the data
2. Communication

Comment il est facile de comprendre
le business?
2013 Sells (in $)
Jan Feb March April May Jun Jul Aug Sep Oct Nov Dec Total
BtoC sells 1534 1697 1798 1556 1651 1834 1492 1559 1800 1547 1659 1809 19936
BtoB sells 658 647 667 654 678 659 458 459 647 687 675 654 7543
Total 2192 2344 2465 2210 2329 2493 1950 2018 2447 2234 2334 2463 27479

Pourquoi nous avons besoin de la
Data Visualisation?
I II III IV
x y x y x y x y
10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58
8.0 6.95 8.0 8.14 8.0 6.77 8.0 5.76
13.0 7.58 13.0 8.74 13.0 12.74 8.0 7.71
9.0 8.81 9.0 8.77 9.0 7.11 8.0 8.84
11.0 8.33 11.0 9.26 11.0 7.81 8.0 8.47
14.0 9.96 14.0 8.10 14.0 8.84 8.0 7.04
6.0 7.24 6.0 6.13 6.0 6.08 8.0 5.25
4.0 4.26 4.0 3.10 4.0 5.39 19.0 12.50
12.0 10.84 12.0 9.13 12.0 8.15 8.0 5.56
7.0 4.82 7.0 7.26 7.0 6.42 8.0 7.91
5.0 5.68 5.0 4.74 5.0 5.73 8.0 6.89
Anscombe's quartet
Property Value
Mean of x in each case 9 (exact)
Variance of x in each case 11 (exact)
Mean of y in each case 7.50 (to 2 decimal places)
Variance of y in each case 4.122 or 4.127 (to 3 decimal places)
Correlation between x and y in each case 0.816 (to 3 decimal places)
Linear regression line in each case y = 3.00 + 0.500x (to 2 and 3 decimal places, respectively)
http://en.wikipedia.org/wiki/Anscombe's_quartetCours de Gestion des SI Décisionnels - MASTER 1 MIAGE Paris-Sud Année 2014-2015 – Abed Ajraou - Tous droits réservés

Pourquoi nous avons besoin de la
Data Visualisation?
Anscombe's quartet
http://en.wikipedia.org/wiki/Anscombe's_quartetCours de Gestion des SI Décisionnels - MASTER 1 MIAGE Paris-Sud Année 2014-2015 – Abed Ajraou - Tous droits réservés

Communication
• Dans notre vie, chaque jour, nous
communiquons. En entreprise, c’est toujours le
cas!
• Vous aurez à communiquer pour:
– Echanger sur votre vécu et vos idées
– Influancer vos collègues même s’ils sont plus anciens
que vous
• Mais les personnes sont des humains! Et l’humain
est une créature émotionnelle et donc nous
devons savoir comment l’être humaine pense et
écoute!

Vision = the most powerful sense!
70%
of our
sense
30% of
our
sense

Pre-attentive perception
• Some visual features are processed pre-
attentively, e.g. without focusing attention
• Low-level (unconscious) cognitive processes

http://www.slideshare.net/janwillemtulp/data-visualization-5724069

Gesalt Theory: The Form Theory
http://sixrevisions.com/usability/data-visualization-gestalt-laws/
• Law of Prägnanz: Keep it simple. Arrange data logically wherever possible.
• Law of Continuity: Arrange objects in a line to facilitate grouping and
comparison.
• Law of Similarity: Use similar characteristics (color, size, shape, etc.) to establish
relationships and to encourage groupings of objects.
• Law of Focal Point: Use distinctive characteristics (like a different color or a
different shape) to highlight and create focal points.
• Law of Proximity: Know what your chart’s information priority is, and then
create groupings through proximity to support that priority.
• Law of Isomorphic Correspondence: Keep in mind your user and their
preconceived notions and experiences. Stick to well-established conventions
and best practices.
• Law of Figure/Ground: Ensure there is enough contrast between your
foreground and background so that charts and graphs are more legible.
• Law of Common Fate: Use direction and/or movement to establish or negate
relationships.

Gesalt Theory: Law of Prägnanz: Arrange data logically
wherever possible!
http://sixrevisions.com/usability/data-visualization-gestalt-laws/Cours de Gestion des SI Décisionnels - MASTER 1 MIAGE Paris-Sud Année 2014-2015 – Abed Ajraou - Tous droits réservés

Gesalt Theory: Law of Continuity

16
0
20
40
60
80
100
120
01/01/2015
02/01/2015
03/01/2015
04/01/2015
05/01/2015
06/01/2015
07/01/2015
08/01/2015
09/01/2015
10/01/2015
11/01/2015
12/01/2015
13/01/2015
14/01/2015
15/01/2015
16/01/2015
Série1
0
20
40
60
80
100
120
01/01/2015
02/01/2015
03/01/2015
04/01/2015
05/01/2015
06/01/2015
07/01/2015
08/01/2015
09/01/2015
10/01/2015
11/01/2015
12/01/2015
13/01/2015
14/01/2015
15/01/2015
16/01/2015
Série1
Gesalt Theory: Law of Continuity

Gesalt Theory: Law of Similarity

Gesalt Theory: Law of Focal Point

Gesalt Theory: Law of Proximity

Gesalt Theory: Law of Isomorphic Correspondence

About the color
The hue dimension is circular, and present the colors in the same order. In any
hue circle, analogous hues are close together, most simply variations
of the same color name (such as purple, or purple-red).

About the color
• Analogous color schemes choose colors that are next to each others in
color wheel
• Complementary color schemes are opposite each others in the color
wheel
• Split Complementary is a mix of complementary & analogous

About the color
• Culture influence
For example:
• In Western: Good
Luck can represent
by green, but in
Chinese is red!
• Marriage can be
represent by white
but in Hindi and Asia
it’s red!

About the color
Original Graph Deuteranomaly (Affects 4.9% of Men)
Be aware of the color perception of every one. 8% of the population have color blind!
http://tim.webanalyticsdemystified.com/?p=387Cours de Gestion des SI Décisionnels - MASTER 1 MIAGE Paris-Sud Année 2014-2015 – Abed Ajraou - Tous droits réservés
=> Problème de perception du vert

About the color
Original Graph Deuteranopia (Affects 1.1% of Men)
=> Problème de perception du vert

About the color
Original Graph Protanopia (Affects 1% of Men)
=> Problème de perception du rouge

About the color
Original Graph Protanomaly (Affects 1% of Men)

About the color
Original Graph Achromatopsia (Extremely Rare)

About the color
How to choose the colors? Use: http://colorbrewer2.org/

Back to the Gesalt Theory: The Form Theory
http://sixrevisions.com/usability/data-visualization-gestalt-laws/
• Law of Prägnanz: Keep it simple. Arrange data logically wherever possible.
• Law of Continuity: Arrange objects in a line to facilitate grouping and
comparison.
• Law of Similarity: Use similar characteristics (color, size, shape, etc.) to establish
relationships and to encourage groupings of objects.
• Law of Focal Point: Use distinctive characteristics (like a different color or a
different shape) to highlight and create focal points.
• Law of Proximity: Know what your chart’s information priority is, and then
create groupings through proximity to support that priority.
• Law of Isomorphic Correspondence: Keep in mind your user and their
preconceived notions and experiences. Stick to well-established conventions
and best practices.
• Law of Figure/Ground: Ensure there is enough contrast between your
foreground and background so that charts and graphs are more legible.
• Law of Common Fate: Use direction and/or movement to establish or negate
relationships.

Gesalt Theory: Law of Figure/Ground

Gesalt Theory: Law of Common Fate

Combination of variables
Jacques Bertin’s Semiology graphics:
• We can represent maps in points, lines &
zones
• We can different variables, like Orientation
(OR), Form (F), Value - Tint (V), Size (T)
• Here how Jacques Bertin make the
combination of these variables
To be efficient, humans can easily perceive:
• 12 orientations
• 10 forms
• 5 sizes
• 3 values (tint)

Combination of variables- Example

• First rule of an efficient data visualization:
keep it simple!
• Abstraction has a perfect sense in Data
Visualization

Goal of a data visualization
• To achieve the goal of a good data visualization, the display
should achieve the following:
1. Clearly indicates how the values relate to one another.
2. Represents the quantities accurately.
3. Makes it easy to compare the quantities.
4. Makes it easy to see the ranked order of values.
5. Makes obvious how people should use the information -
what they should use it to accomplish - and encourages
them to do this.
Source: “Data Visualization for Human Perception” Stephen FewCours de Gestion des SI Décisionnels - MASTER 1 MIAGE Paris-Sud Année 2014-2015 – Abed Ajraou - Tous droits réservés

Tufte’s principles

Why is 3D “harder”?
“Human Based Visual Communication” presentation by Dan Young – Corporate CMKCours de Gestion des SI Décisionnels - MASTER 1 MIAGE Paris-Sud Année 2014-2015 – Abed Ajraou - Tous droits réservés

Why is 3D “harder”?
Poucentage%
France Italie Suisse Espagne Portugal
Country Pourcentage %
France 50
Italie 15
Suisse 10
Espagne 20
Portugal 5

Bad or Good Data Visualization?

http://simplystatistics.org/2012/11/26/the-statisticians-at-fox-news-use-classic-and-novel-graphical-techniques-to-lead-with-data/

Web site for the video: https://www.wat.tv/images/v70/PlayerLite.swf?videoId=3azh7

Exercice
• Try to find the best way to represent this data:
Number of person by transport type in Spain in
2012:
Plane: 7,876,951
4 wheel vehicles: 35,417,247
Bus: 17,675,980
Motorcycles: 6,874,887
Pedestrians: 5,639,072

Solution 1

Solution 2

Solution 3

Solution 4

Solution 5

Solution 6

Solution 7

One of the best in the world!

Conclusion
• A data visualization should:
– Be understanding by your audience very quickly: clear title, clear
axis, clear purpose, do not surcharge the different variables
– Respect the Gesalt Laws as soon as possible
– Show all the data – not trying to influence an opinion
– Use small space to represent large data set (vs Infographic)
– Specify the source of data
– Give accurate information – for example, there is no sense to
compare the number of cars crashed between France &
Liechtenstein … it’s better to see this data regarding the number
of cars in circulation or the length of roads in each country

Systèmes d'Information Décisionnels - Cours - 20150309 - DataVisualisation

Recommandé

Recommandé

Contenu connexe

Similaire à Systèmes d'Information Décisionnels - Cours - 20150309 - DataVisualisation

Similaire à Systèmes d'Information Décisionnels - Cours - 20150309 - DataVisualisation (20)

Systèmes d'Information Décisionnels - Cours - 20150309 - DataVisualisation