Data Visualization (Academic Course)

“Graphical excellence is that which gives to the viewer the greatest number of ideas in the shortest time with the least ink in the smallest space.” — Edward Tufte

The ever increasing computational capacity has enabled us to acquire, process and analyze larger data-sets and information. However, the human memory and attention required to use this data is more limited and has remained relatively constant. Data visualization can enable us to compress data and encode them in ways to aid perceptual, cognitive and emotional capacity required to comprehend, retain and make decisions using this data. This course is designed to help you learn the art and science of data visualization.

Course Objectives

• Understand the value of data visualization and the role it plays in business analytics and decision making
• Learn the theory of data visualization including grammar, types, color, annotation, flow, animation, interaction etc.
• Build an understanding of visual perception and cognition to gain an intuitive sense of how data visualization work
• Get exposure to multiple tools that can be used to create data visualization
• Learn through practice the multiple contexts in which data visualization is used in business
  • Static visualization (say, adding a chart in a report)
  • Dashboard visualization (say, monitoring KPIs in a operational or strategic dashboard)
  • Narrative visualization (say, telling a compelling data-story in a presentation)
  • Interactive visualization (say, allowing user to visually explore a complex data-set)

Session Plan

Session #1: Value of Data Visualization

• Start with exploring the visual-wired and the story-wired brain
• Understand the value of visualization - Expression (record), Exploratory (analyze) and Explanatory (communicate)
• See the role of data visualization in business analytics and decision making - descriptive, deductive, predictive and prescriptive
• Introduction to data models (variable types, dimensions, measures) and visual encoding options
• Principles of graphical perception and integrity

Session Readings and References

• Chapter 2: Visual and Statistical Thinking: Display of Evidence for Making Decisions (Visual Explanation - Tufte)
• Chapter 1: Graphical Excellence (The Visual Display of Quantitative Information - Tufte)
• [Optional] Chapter 2: Graphical Integrity (The Visual Display of Quantitative Information - Tufte)
• [Optional] Chapter 3: Sources of Graphical Integrity & Sophistication (The Visual Display of Quantitative Information - Tufte)

Session #2: Theory of Data Visualization

• Learn the grammar of graphics: data, variable mapping, data transformation, geometric shape, position and aesthetics, a coordinate system, and scale transformation
• See the principles of data-ink and chart-junk
• Understand how visual perception works and how it can be applied to choose the appropriate visualizations

Session Readings and References

• Chapter 5: Visual Perception and Graphical Communication (Show Me the Numbers - Few)
• A Layered Grammar of Graphics by Hadley Wickam, Journal of Computational and Graphical Statistics (pdf link)
• [Optional] Chapter 4: Data-Ink and Graphical Redesign (The Visual Display of Quantitative Information - Tufte)
• [Optional] Chapter 5: Chart Junk (The Visual Display of Quantitative Information - Tufte)
• [Optional] Chapter 6: Data-Ink Maximization and Graphical Design (The Visual Display of Quantitative Information - Tufte)

Assignment #1: Visualization Critique

Session #3: Types of Data Visualization

• Understand types of questions answered by data visualizations and graphics that can be used to represent them
• Explore a guide to choosing appropriate type of graphical representations
• Learn about graphical representations that are best avoided or minimized

Session Readings and References

• Chapter 6: Fundamental Variations of Graphs (Show Me the Numbers - Few)
• Chapter 12: Silly Graphs that are Best Forsaken (Show Me the Numbers - Few)
• [Optional] A Tour through the Visualization Zoo by Heer, Bostock & Ogievetsky in ACM Queue 2010 (pdf link)

Session #4: Tools for Data Visualization

• Understand the tools landscape: Charting-based tools, Grammar-based tools and Canvas-based tools
• Overview and introduction to select tools for data visualization:
  • Excel
  • Tableau
  • R - ggplot2
  • d3.js
  • Processing
• Hands-on exercises for creating simple visualizations in each of these tools

Session Readings and References

• For Tableau: Start with the training and tutorials on Tableau site. (Access free online version)
• For ggplot2: Start with R Graphics Cookbook by Winston Chang. (Access free online version)
• For d3.js: Start with Interactive Data Visualization for the Web by Scott Murray. (Access free online version)
• For Processing: Start with tutorials at Processing.org site. (Access free online version)

Session #5: Using Color and Annotation in Data Visualization

• Make effective use of color in visualization - color for categorical encoding, color for quantitative encoding
• Understand use of typography and annotation within graphical communication
• Explore design of secondary graph components - trend and reference lines, scales, tick marks, grid lines, axes and legends

Session Readings and References

• Chapter 9: Aesthetic and Technique in Data Graphical Design (The Visual Display of Quantitative Information - Tufte)
• Chapter 5: Color and Information (Envisioning Information - Tufte)
• Chapter 10: Component-level Graph Design (Show Me the Numbers - Few)

Assignment #2: Static Visualization

Session #6 - Creating High Density Data Visualization

• Choosing visual representation for multiple variables e.g. aesthetics like color, and using facets or small multiples
• Using high-density representations: spark lines, bullet graphs, tree maps, geo-spatial maps etc.

Session Readings and References

• Chapter 11: Displaying Many Variable at Once (Show Me the Numbers - Few)
• Chapter 8: Data Density and Small Multiples (The Visual Display of Quantitative Information - Tufte)
• [Optional] Chapter 9: Designing Bullet Graphs (Information Dashboard Design - Few)
• [Optional] Chapter 10: Designing Sparklines (Information Dashboard Design - Few)

Session #7 - Putting together a Data Dashboard

• Understand point of view in a dashboard: explanatory vs. exploratory
• Choose a structure for the dashboard: flow, relationships, grouping or narrative
• Map the dashboard layout: grids, white space and screen space
• Understand guiding design principles: compactness, modularity, reveal, focus & guide attention, customization, context aware, lead to action

Session Readings and References

• Chapter 2: Thirteen Common Mistakes in Dashboard Design. [Information Dashboard Design - Few]
• A Guide to Creating Dashboard People Love - Juice Analytics (pdf link)

Assignment #3: Dashboard Visualization

Session #8: Crafting Visual Stories with Data

• Explore the principles of storytelling and narrative
• Lessons on how stories work from other mediums - oral storytelling, journalism, movies, comics and consulting
• Selection of messaging - text annotation and verbal
• Building a data-visual-story - understand framing, transitions and flow

Session Readings and References

• Chapter 13: Telling Compelling Stories with Numbers [Show Me the Numbers - Few]
• The Ultimate Collection of Data Storytelling Resource - Juice Analytics (html link)
• [Optional] Narrative Visualization: Telling Stories with Data - Segel & Heer - InfoVis 2010 (pdf link)

Session #9 Animation and Interactivity

• Engagement in context - personal, presentation & participation
• Use of animation in graphical transitions
• Explore common interaction patterns: select, explore, reconfigure, encode, filter, drill-down, connect and dynamic queries

Session Readings and References

• Interactive Dynamics for Visual Analysis, Heer & Shneiderman (pdf link)
• Up and Down the Ladder of Abstraction - Bret Victor (html link)

Assignment #4: Narrative or Interactive Visualization

Session #10 - Presentations and Recap

• Additional visualization constructs - text visualization, networks & graphs, maps and cartography
• Presentation of Assignment #4 - Narrative or Interactive Visualization
• Recap of the overall course

Assessment

Learning is best achieved through participation and practice. Attending the class sessions is a must to engage in a dialogue and learn from the question & answers and the sharing of experiences that happens. Further, there will be four assignments as part of the course. The first two assignments are individual and the next two assignments can be done in groups of two. The aim of the assignments is to provide you with a testing ground to put in practice all the theory and exemplars you would be learning about data visualization in the class.

• Class Participation (10%)
• Assignment #1 (individual): Visualization Critique (15%)
• Assignment #2 (individual): Static Visualization (25%)
• Assignment #3 (group): Dashboard Visualization (25%)
• Assignment #4 (group): Narrative or Interactive Visualization (25%)

Facilitator’s Profile

Amit Kapoor is interested in learning and teaching the craft of telling visual stories with data. He is the founder partner at narrativeVIZ Consulting, where he teaches data-science, data-visualisation and data-stories as tools for improving communication, persuasion, and leadership and conducts workshops on these topics for businesses, nonprofits, and academic institutes. He also teaches visualisation as a guest faculty in design context at NID, Bangalore and in management context at IIM Bangalore & IIM Ahmedabad

His background is in strategy consulting in using data-driven stories to drive change across organizations and businesses. He has more than 15 years of management consulting experience, first with AT Kearney in India, then with Booz & Company in Europe and more recently for startups in Bangalore. He did his B.Tech in Mechanical Engineering from IIT, Delhi and PGDM (MBA) from IIM, Ahmedabad. You can find more about him at amitkaps.com and tweet him at @amitkaps.