Data visualization
-
Upload
christian-stade-schuldt -
Category
Data & Analytics
-
view
132 -
download
1
Transcript of Data visualization
Data Visualization
Christian Stade-SchuldtProject-A Ventures
BI Team Knowledge Transfer
Outline
Motivation
Principles of Data Visualization
Types of Visualization
Summary
,
Project-A, Data Visualization, 2015 2
Why visualizing data?
É Visualization lets you see things that would rather go unnoticedÉ Visualization gives answers fasterÉ Color pictures are pretty and fun to look atÉ Simple example: Anscombe’s Quartet
,
Project-A, Data Visualization, 2015 3
Anscombe’s Quartet
I II III IVx y x y x y x y
10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.588.0 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 7.719.0 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 8.4714.0 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 5.254.0 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 5.567.0 4.82 7.0 7.26 7.0 6.42 8.0 7.915.0 5.68 5.10 4.74 5.0 5.73 8.0 6.89
,
Project-A, Data Visualization, 2015 4
Anscombe’s Quartet II
,
Project-A, Data Visualization, 2015 5
Edward Tufte
É Professor emeritus at YaleUniversity
É Pioneer in the field of datavisualization
É Notable works: The VisualDisplay of QuantitativeInformation
,
Project-A, Data Visualization, 2015 6
Principles of graphical excellence andintegrity
1. Serve a purpose
2. Make large data sets coherent
3. Present many numbers in a small space
4. Don’t lie
5. Use clear labels to defeat ambuigity and graphical distortion
6. Show entire scales
7. Show in context
,
Project-A, Data Visualization, 2015 7
Small multiples
,
Project-A, Data Visualization, 2015 8
The Lie factor
Lie factor =Size of effect in graphic
Size of effect in data(1)
=5.3− 0.6
0.6/27.5− 18
18= 14.8 (2)
,
Project-A, Data Visualization, 2015 9
Scale contorsions
,
Project-A, Data Visualization, 2015 10
Scale contorsions
,
Project-A, Data Visualization, 2015 11
Scale contorsions and context
,
Project-A, Data Visualization, 2015 12
Principle of data graphics
1. Above all else show the data
2. Maximize the data-ink ratio
3. Erase non-data-ink
4. Erase redundant data-ink
5. Revise and edit
,
Project-A, Data Visualization, 2015 13
Data-Ink
É Data-ink the non-erasable ink used for the presentation of dataÉ If removed the graphic would lose the contentÉ Non-Data-Ink is accordingly the ink that does not transport the
informationÉ Data-ink ratio = (data ink)/(total ink used to print the graphic)É Chartjunk: unecessary to comprehend the information represented or
distractive
,
Project-A, Data Visualization, 2015 14
Data-Ink-Ratio Example
Low Data-Ink-Ratio High Data-Ink-Ratio
,
Project-A, Data Visualization, 2015 15
Chart types
The goodÉ Bar chartsÉ Line chartsÉ Scatter plotsÉ Boxplots
The badÉ Pie chartsÉ Area charts
The uglyÉ All 3d charts
,
Project-A, Data Visualization, 2015 16
Bar charts
É Go-to graph for comparing accross categories, discrete data orcontinous data
É Proximity: Set white space width separating contiguous bars equal to50%-150% width of bars
É Fills: Avoid pattern lines, use soft but distinct colorsÉ Borders: AvoidÉ Tick marks: Do not overdo
,
Project-A, Data Visualization, 2015 17
Bar charts
,
Project-A, Data Visualization, 2015 18
Line chart
É Used for continous dataÉ Intervals should be equal in sizeÉ Values should only direct connect values in adjacent intervalsÉ Indicate missing data
,
Project-A, Data Visualization, 2015 19
Line chart
,
Project-A, Data Visualization, 2015 20
Scatter plots
É Great for correlation between two quantitave dimensions
,
Project-A, Data Visualization, 2015 21
Pie chartsPie charts are the Aquaman of data visualization
,
Project-A, Data Visualization, 2015 22
Pie charts
The same data represented as a column chart
,
Project-A, Data Visualization, 2015 23
3d Pie charts
What is worse than a pie chart? Meet the 3d pie chart
,
Project-A, Data Visualization, 2015 24
Maps
É provide specificinformationabout particularlocations
É provide generalinformationabout spatialpatterns
É can be used tocomparepatterns on twoor more maps
,
Project-A, Data Visualization, 2015 25
Maps
Relevant xkcd
,
Project-A, Data Visualization, 2015 26
Remember Color Blindness
Approximately 10% of males and 1% of females suffer color visiondeficiency
Original colors Perceived colors
,
Project-A, Data Visualization, 2015 27
Summary
É Visualize your dataÉ Choose the right type for your visualizationÉ Aim for a high Data-Ink-Ratio
,
Project-A, Data Visualization, 2015 28
For Further Reading I
Tufte, Edward RThe Visual Display of Quantitative Information.Graphics Press, 2001.
,
Project-A, Data Visualization, 2015 29