The Art of Data Visualization Agenda: 6:00 - 6:15: Welcome 6:15 – 6:45: Guidelines for Data Visualization 6:45- 7:30 : Large-scale GPU-Accelerated Data Visualization with MapD 7:30 - 8:00: 1000+ Members Giveaway / Networking + Q&A

1. Data Science | Design | Technology
(January 30, 2018)
https://www.meetup.com/DSDTMTL
1

2. Agenda
6:00 - 6:15: Welcome
6:15 - 7:00: Guidelines for Data Visualization
7:00 - 7:30: Large-scale GPU-Accelerated
Data Visualization with MapD
7:30 - 8:00: 1000+ Members Giveaway /
Networking + Q&A
2
The Art of Data Visualization

3. Special Event
February 12
"Studies in Gameful Interaction Design and Games
User Research"
Dr Lennart Nacke, Director of the HCI Games Group | Associate
professor for human-computer interaction -University of Waterloo
3

4. 4
R&D Technologist
(x2)
R&D UX Designer
(x1)
Software Engineer
(x2)

5. DSDT Meetup
Gift for one
participant of
today’s meetup
5
1000+
Members!!

6. Guidelines for
Data Visualization
Data Science | Design | Technology 6

7. Data Visualization
Guidelines
Ignacio Alvarez

8. “Visual representations not only make the
patterns, trends, and exceptions in
numbers visible and understandable, they
also extend the capacity of our memory,
making available in front of our eyes what
we couldn’t otherwise hold all at once in
our minds.”
– Stephen Few

9. 5 Rules
2 Rule
1 - Make sure your visualization answers a question
2 - Consider your audience and the context of use
3 - Use the right method of visualization
4 - Make Your Visualization Readable
5 - Use the right analytical interaction and
navigation

10. Make sure your
visualization
answers a
question
– Define the goal / the objective : what do you want
to achieve with this visualization.

11. Explore
By MATT DANIELS

12. Explain
http://drones.pitchinteractive.com/index.fr.html

13. Decide

14. Consider your
audience
and the
context of use

15. What information
does he need to be
successful?
What level of detail
does the user need?
What actions can be
taken?
Consider accessibility
What is the context of
use?

17. Use the right
method of
visualization

18. Time Series

19. Part-to-
Whole

20. Deviation
Analysis

21. Distribution

22. Make Your
Visualization
Readable

23. 1- Avoid having to much information.

24. 2 - Think about the form.

25. 3 – Be careful with colors

26. 4 - Spatial position

27. Use the right
analytical
interaction and
navigation
Comparing
Sorting
Adding variables
Filtering
Highlighting
Aggregating
Re-expressing
Re-visualizing
Zooming and panning
Re-scaling
Accessing details on demand
Annotating
Bookmarking

28. http://www.datasketch.es/october/code/nadieh/

30. Questions?

31. Open GPU-Accelerated
Data Analytics
January 31, 2018

32. Aaron Williams
VP of Global Community
@_arw_
aaron@mapd.com
/in/aaronwilliams/
/williamsaaron
Christophe Viau
Data Visualization Engineer
chrisv@mapd.com
/in/christopheviau/
/biovisualize

33. “Every business will become a
software business, build
applications, use advanced analytics
and provide SaaS services.”
- Smart CEO Guy

34. The Evolution of Data as a Weapon
4
Collect It Make It
Actionable
Make it
Predictive

35. MapD: Extreme Analytics
5
100x Faster Queries
MapD Core
The world’s fastest
columnar database,
built specifically for GPUs
+
Visualization at the Speed of Thought
MapD Immerse
A visualization front end that
leverages the speed &
rendering superiority of GPUs

36. MapD System Architecture
Accelerating the existing data infrastructure
6

37. 7
MAPD DEMOS

38. Core Density Makes a Huge Difference
8
GPU ProcessingCPU Processing
40,000
Cores
20 Cores
*fictitious example
Latency Throughput
CPU
1 ns
per task
(1 task/ns) x (20 cores) =
20 tasks/ns
GPU
10 ns
per task
(0.1 task per ns) x (40,000 cores) =
4,000 task per ns
Latency: Time to do a task. | Throughput: Number of tasks per unit time.

39. Query Compilation with LLVM
9
Traditional DBs can be highly inefficient
• each operator in SQL treated as a separate function
• incurs tremendous overhead and prevents vectorization
MapD compiles queries w/LLVM to create one custom function
• Queries run at speeds approaching hand-written functions
• LLVM enables generic targeting of different architectures (GPUs, X86, ARM, etc).
• Code can be generated to run query on CPU and GPU simultaneously
1011101010100101011010110101010
1
0011010110110101010101010101110
1
LLVM

40. Keeping Data Close to Compute
MapD maximizes performance by optimizing memory use
10
SSD or NVRAM STORAGE (L3)
250GB to 20TB
1-2 GB/sec
CPU RAM (L2)
32GB to 3TB
70-120 GB/sec
GPU RAM (L1)
24GB to 256GB
1000-6000 GB/sec
Hot Data
Speedup = 1500x to 5000x
Over Cold Data
Warm Data
Speedup = 35x to 120x
Over Cold Data
Cold Data
COMPUTE
LAYER
STORAGE
LAYER
Data Lake/Data Warehouse/System Of Record
SpeedIncreases
SpaceIncreases

41. The Status Quo: Memory Bottlenecks
11
PCIe
4-16GB/s

42. The GPU Open Analytics Initiative Model
Standard in-memory format; zero-copy interchange
12
GPU

43. The GPU Open Analytics Initiative Model
Standard in-memory format; zero-copy interchange
13

44. Interactive Machine Learning
Empowering the People in the Pipeline
14
Personas in
Analytics Lifecycle
(Illustrative)
Business Analyst
Data Scientist
Data Engineer
IT Systems Admin
Data Scientist / Business Analyst
Data Preparation
Data
Discovery
& Feature Engineering
Model & Validate Predict
Operationalize
Monitoring & Refinement
Evaluate
& Decide
GPUsMapD H20.ai MapD

45. MapD Immerse
Using a hybrid approach to speed and scale visualization
15
Basic charts are frontend
rendered using D3 and other
related toolkits
Scatterplots, pointmaps + polygons
are backend rendered using the Iris
Rendering Engine on GPUs
Geo-Viz is composited over a
frontend rendered basemap

46. Built for an open-source ecosystem
16
Extending multiple APIs
● Dc.js (docs): Mapd-charting (docs)
● Crossfilter: Mapd-crossfilter
● Vega (editor): Mapd Raster
● GPU DB Connector (docs)
Part of an ecosystem
● Related projects like Deck.gl
● Building blocks like Mapbox, which uses Leaflet
● Using smaller building blocks, like D3.js

47. Try MapD
It’s free and it’s easy
17
Play with the live demos: https://www.mapd.com/demos/
Try the Test Drive: https://mapd.io/testdrive-enterprise
Install the Community Edition:
https://www.mapd.com/platform/download-community/
Join our forums:
https://community.mapd.com/
Review these slides:
https://speakerdeck.com/mapd

48. © MapD 2017
MapD Test Drive
18
Try it now: mapd.io/testdrive-enterprise
Use our sample data or
upload your own
Try our dashboards or
create your own
The easiest way to try a
complete MapD instance

49. AWS Credits Available
19
Free GPU Compute!
We’re looking for interesting use cases.
Email Aaron Williams (aaron@mapd.com) with your ideas!

50. Aaron Williams
VP of Global Community
@_arw_
aaron@mapd.com
/in/aaronwilliams/
/williamsaaron
Christophe Viau
Data Visualization Engineer
chrisv@mapd.com
/in/christopheviau/
/biovisualize

52. Merci / Thank You
22
@jdalabsmtl
Data Science | Design | Technology
(Check for next DSDT meetup at https://www.meetup.com/DSDTMTL)