![Page 1: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/1.jpg)
Network-based Visual Analysis of Tabular Data
Zhicheng Liu, Shamkant Navathe, John Stasko
![Page 2: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/2.jpg)
Tabular Data
2
![Page 3: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/3.jpg)
Tabular Data
• Rows and columns
• Rows are data cases; columns are attributes/dimensions
• Attribute types
o Quantitative (numbers)
o Ordinal (e.g. small, medium, large)
o Nominal (names, categories)
3
![Page 4: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/4.jpg)
Insight Discovery on Tabular Data: Example
• NSF Grants
o Grant Title
o Amount
o Date
o Program Manager
o Awardee / Researcher Name
o Awardee Affiliation
o …
4
![Page 5: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/5.jpg)
Visualizing Tabular Data
5
[Rao and Card, 1994]
[Tableau]
[Spotfire]
![Page 6: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/6.jpg)
6
# Grants in each program
![Page 7: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/7.jpg)
7
Amount by date
![Page 8: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/8.jpg)
8
Amount by date & ProgMgr
![Page 9: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/9.jpg)
9
Collaboration between
institutions?
![Page 10: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/10.jpg)
10
Relationship between
ProgMgr and Researchers?
![Page 11: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/11.jpg)
11
• Quantitative attributes
o Nominal data as independent
variables, or not handled
• Patterns of distributions,
correlations and outliers of
numerical values
• Nominal attributes
o Quantiative attributes are
useful too
• Entities with interesting
roles, emergent global
structures
![Page 12: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/12.jpg)
12
Explicit Network Tabular Data
Current State of the Art
Spotfire , Tableau,
TableLens ….
GUESS, UCINet,
SocialAction ….
![Page 13: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/13.jpg)
Problems with this Partition
• Analytical: Network semantics are dynamic
• Usability: Modeling networks is tedious and requires
programming skill
13
Counter-intuitive for Exploratory Analysis
![Page 14: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/14.jpg)
NodeXL
14 [Hansen, et. al. 2010]
![Page 15: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/15.jpg)
Questions & Approaches
15
Goal: Network-based Visual Analysis of Tabular Data
1. Which conceptually
meaningful operations are
necessary to extract and
transform tabular data into
networks for exploratory
analysis?
2. Given a set of operations,
how to provide analysts with
easy access to these
operations and to couple
network modeling with
exploratory analysis?
• Domain independent
• Generalized operations
• Expressive power
• Hide technical details
• Reduce articulatory distance
• Immediate visual feedback
![Page 16: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/16.jpg)
• Networks: Weighted Simple
Graphs
o Undirected
o At most one edge between any two
nodes
o Edges are weighted
Formal Framework
• Tables: Relational model [Codd, 1969]
o Each row is uniquely identifiable
o Values in each cell is atomic: number, boolean, string, date
16
A B
![Page 17: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/17.jpg)
An Example
17
ID LastNm FirstNm Type Date Size Visitee Loc
1 Dodd Chris VA 6/25/09 2018 POTUS WH
2 Smith John VA 6/26/09 237 Office
Visitors WH
3 Smith John AL 6/26/09 144 Amanda
Kepko OEOB
4 Hirani Amyn VA 6/30/09 184 Office
Visitors WH
5 Keehan Carol VA 6/30/09 8 Kristin
Sheehy WH
6 Keehan Carol VA 7/8/09 26 Daniella
Leger OEOB
![Page 18: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/18.jpg)
First-order Graph: Single Table
18
ID LastNm FirstNm Type Date Size Visitee Loc
1 Dodd Chris VA 6/25/09 2018 POTUS WH
2 Smith John VA 6/26/09 237 Office Visitors WH
3 Smith John AL 6/26/09 144 Amanda
Kepko OEOB
4 Hirani Amyn VA 6/30/09 184 Office Visitors WH
5 Keehan Carol VA 6/30/09 8 Kristin Sheehy WH
6 Keehan Carol VA 7/8/09 26 Daniella Leger OEOB
LastNm FirstNm
Dodd Chris
Smith John
Smith John
Hirani Amyn
Keehan Carol
Keehan Carol
Loc
WH
WH
OEOB
WH
WH
OEOB
![Page 19: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/19.jpg)
First-order Graph: Single Table
19
ID LastNm FirstNm Type Date Size Visitee Loc
1 Dodd Chris VA 6/25/09 2018 POTUS WH
2 Smith John VA 6/26/09 237 Office Visitors WH
3 Smith John AL 6/26/09 144 Amanda
Kepko OEOB
4 Hirani Amyn VA 6/30/09 184 Office Visitors WH
5 Keehan Carol VA 6/30/09 8 Kristin Sheehy WH
6 Keehan Carol VA 7/8/09 26 Daniella Leger OEOB
LastNm, FirstNm
Dodd Chris
Smith John
Smith John
Hirani Amyn
Keehan Carol
Keehan Carol
Loc
WH
WH
OEOB
WH
WH
OEOB
![Page 20: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/20.jpg)
First-order Graph: Single Table
20
ID LastNm FirstNm Type Date Size Visitee Loc
1 Dodd Chris VA 6/25/09 2018 POTUS WH
2 Smith John VA 6/26/09 237 Office Visitors WH
3 Smith John AL 6/26/09 144 Amanda
Kepko OEOB
4 Hirani Amyn VA 6/30/09 184 Office Visitors WH
5 Keehan Carol VA 6/30/09 8 Kristin Sheehy WH
6 Keehan Carol VA 7/8/09 26 Daniella Leger OEOB
Type
VA
VA
AL
VA
VA
VA
LastNm, FirstNm
Dodd Chris
Smith John
Smith John
Hirani Amyn
Keehan Carol
Keehan Carol
Loc
WH
WH
OEOB
WH
WH
OEOB
![Page 21: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/21.jpg)
First-order Graph: Single Table
21
ID LastNm FirstNm Type Date Size Visitee Loc
1 Dodd Chris VA 6/25/09 2018 POTUS WH
2 Smith John VA 6/26/09 237 Office Visitors WH
3 Smith John AL 6/26/09 144 Amanda
Kepko OEOB
4 Hirani Amyn VA 6/30/09 184 Office Visitors WH
5 Keehan Carol VA 6/30/09 8 Kristin Sheehy WH
6 Keehan Carol VA 7/8/09 26 Daniella Leger OEOB
[Type]
[Type = VA]
[Type = VA]
[Type = AL]
[Type = VA]
[Type = VA]
[Type = VA]
LastNm, FirstNm
Dodd Chris
Smith John
Smith John
Hirani Amyn
Keehan Carol
Keehan Carol
Loc
WH
WH
OEOB
WH
WH
OEOB
![Page 22: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/22.jpg)
Higher-order Graph: Transformations
• Aggregation
• Projection
• Edge Weighting
• Slicing ‘n Dicing
22
![Page 23: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/23.jpg)
Aggregation: Entity Resolution
23
Dodd, Chris WH
Smith, John WH
Keehan, Carol OEOB
Hirani, Amyn WH
Keehan, Carol WH
Smith, John OEOB
Dodd, Chris
Smith, John WH
Hirani, Amyn
Keehan, Carol
Smith, John
OEOB
original graph after aggregation
![Page 24: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/24.jpg)
Aggregation: Pivoting
24
Dodd, Chris
Smith, John WH
Hirani, Amyn
Keehan, Carol
Smith, John
OEOB
VA WH
AL OEOB
Type Location
original graph after aggregation
![Page 25: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/25.jpg)
Projection
25
Dodd, Chris
OEOB
WH
Hirani, Amyn
Keehan, Carol
Smith, John
Dodd, Chris Smith, John
Hirani, Amyn Keehan, Carol
![Page 26: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/26.jpg)
Edge Weighting
26
ID LastNm FirstNm Type Date Size Visitee Loc
1 Dodd Chris VA 6/25/09 2018 POTUS WH
2 Smith John VA 6/26/09 237 Office Visitors WH
3 Smith John AL 6/26/09 144 Amanda
Kepko OEOB
4 Hirani Amyn VA 6/30/09 184 Office Visitors WH
5 Keehan Carol VA 6/30/09 8 Kristin Sheehy WH
6 Keehan Carol VA 7/8/09 26 Daniella Leger OEOB
Size
2018
237
144
184
8
26
LastNm, FirstNm
Dodd Chris
Smith John
Hirani Amyn
Keehan Carol
Visitee
POTUS
Office Visitors
Amanda
Kepko
Kristin Sheehy
Daniella Leger
![Page 27: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/27.jpg)
Edge Weighting
27
ID LastNm FirstNm Type Date Size Visitee Loc
1 Dodd Chris VA 6/25/09 2018 POTUS WH
2 Smith John VA 6/26/09 237 Office Visitors WH
3 Smith John AL 6/26/09 144 Amanda
Kepko OEOB
4 Hirani Amyn VA 6/30/09 184 Office Visitors WH
5 Keehan Carol VA 6/30/09 8 Kristin Sheehy WH
6 Keehan Carol VA 7/8/09 26 Daniella Leger OEOB
LastNm, FirstNm
Dodd Chris
Smith John
Hirani Amyn
Keehan Carol
Visitee
POTUS
Office Visitors
Amanda
Kepko
Kristin Sheehy
Daniella Leger
2018
237
144
184
8
26
![Page 28: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/28.jpg)
Loc
WH
WH
OEOB
WH
WH
OEOB
Slice ‘n Dice
28
ID LastNm FirstNm Type Date Size Visitee Loc
1 Dodd Chris VA 6/25/09 2018 POTUS WH
2 Smith John VA 6/26/09 237 Office Visitors WH
3 Smith John AL 6/26/09 144 Amanda
Kepko OEOB
4 Hirani Amyn VA 6/30/09 184 Office Visitors WH
5 Keehan Carol VA 6/30/09 8 Kristin Sheehy WH
6 Keehan Carol VA 7/8/09 26 Daniella Leger OEOB
LastNm, FirstNm
Dodd Chris
Smith John
Hirani Amyn
Keehan Carol
Visitee
POTUS
Office Visitors
Amanda
Kepko
Kristin Sheehy
Daniella Leger
![Page 29: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/29.jpg)
Loc
WH
WH
OEOB
WH
WH
OEOB
Slice ‘n Dice
29
ID LastNm FirstNm Type Date Size Visitee Loc
1 Dodd Chris VA 6/25/09 2018 POTUS WH
2 Smith John VA 6/26/09 237 Office Visitors WH
3 Smith John AL 6/26/09 144 Amanda
Kepko OEOB
4 Hirani Amyn VA 6/30/09 184 Office Visitors WH
5 Keehan Carol VA 6/30/09 8 Kristin Sheehy WH
6 Keehan Carol VA 7/8/09 26 Daniella Leger OEOB
LastNm, FirstNm
Dodd Chris
Smith John
Hirani Amyn
Keehan Carol
Visitee
POTUS
Office Visitors
Kristin Sheehy
LastNm, FirstNm
Smith John
Keehan Carol
Visitee
Amanda
Kepko
Daniella Leger
WH OEOB
![Page 30: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/30.jpg)
Expressive Power
• Proximity grouping
• Extending to directed one-mode network
• Limitations
30
![Page 31: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/31.jpg)
Ploceus Interface Overview
31
Data Manage-
ment View
Network Schema
View
Network Visualization View
![Page 32: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/32.jpg)
Direct Manipulation Interface
32
![Page 33: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/33.jpg)
Ploceus
Demo
33
![Page 34: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/34.jpg)
Related Work
34
Centrifuge Orion
![Page 35: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/35.jpg)
Multiple Tables
35
GID Title Program Program
Manager Amount Year
1 Data Mining of
Digital Behavior Statistics
Sylvia
Spengler 2241750 2001
2
Real-time Capture,
Management and
Reconstruction of
Spatio-Temporal
Events
Information
Technology
Research
Maria
Zemankova 430000 2000
3
Statistical Data
Mining
of Time-Dependent
Data with
Applications in
Geoscience and
Biology
ITR for
National
Priorities
Sylvia
Spengler 566644 2003
PID Name Org
1 Padhraic
Smyth
University of
California
Irvine
2 Sharad
Mehrotra
University of
California
Irvine
Person Grant Role
1 1 PI
2 1 coPI
2 2 PI
1 3 PI
![Page 36: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/36.jpg)
Grant Role Person
1 PI 1
1 coPI 2
2 PI 2
3 PI 1
First-order Graph: Multiple Tables
36
GID Title Program ProMgr Amount Year
1 Data Mining of Digital
Behavior Statistics
Sylvia
Spengler 2241750 2001
2 Real-time Capture,
Management …
Information Tech-
nology Research
Maria
Zemankova 430000 2000
3 Statistical Data Mining
of Time-Dependent …
ITR for National
Priorities
Sylvia
Spengler 566644 2003
PID Name Org
1 Padhraic Smyth University of
California Irvine
2 Sharad Mehrotra University of
California Irvine
1 Padhraic Smyth University of
California Irvine 1 Padhraic Smyth
University of
California Irvine
2 Sharad Mehrotra University of
California Irvine 2 Sharad Mehrotra
University of
California Irvine
PID Name Org
Data Mining of Digital
Behavior Statistics
Sylvia
Spengler 2241750 2001
Real-time Capture,
Management …
Information Tech-
nology Research
Maria
Zemankova 430000 2000
Title Program ProMgr Amount Year
Statistical Data Mining
of Time-Dependent …
ITR for National
Priorities
Sylvia
Spengler 566644 2003
Data Mining of Digital
Behavior Statistics
Sylvia
Spengler 2241750 2001
Grant Role Person
1
PI 1
1
coPI 2
2
PI 2
3
PI 1
![Page 37: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/37.jpg)
Open Issues with Multiple Tables (1)
• Join Specification
37
![Page 38: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/38.jpg)
Open Issues with Multiple Tables (2)
• Interpretation of Edge Weights
38
![Page 39: Network-based Visual Analysis of Tabular Data](https://reader030.vdocuments.us/reader030/viewer/2022012508/6184ce9b29cd66314645272e/html5/thumbnails/39.jpg)
Acknowledgments
39
IIS-0915788 VACCINE Center