Course description

The need for data visualization is frequent in day to day situations. Modern data visualization techniques can be used for the exploration and presentation of results that are easy, compact and understandable for a given audience.

However, generating high-quality visualizations that effectively communicate the desired insights can be time consuming and challenging in many different ways, for instance:

• setting up the appropriate environments
• choosing the appropriate visual variables
• handling the available tools
• coding
• generating publishing quality visualizations.

Goal and content of course

The aim of this course is to provide an introduction to practical data visualization in a hands-on learning environment. The course covers practical data handling for visualizations:

• a discussion and implementation of several visualization techniques which are frequently used in science
• a discussion of relevant perception issues which should be considered when producing visualizations
• a discussion on visualization design.

Several concrete use-cases involving designing effective visualizations for a selected set of problems will be used to exemplify the presented material.

Tableau, a drag and drop visualization tool, is used for visualization design for many types of interactive charts, such as bar and scatter plots, maps, heat maps and tree maps. For visualization techniques not available in Tableau such as violin plots and projections; docker environments, Python and R packages are briefly discussed as potential tools to build such visualizations. Source code of the visualizations will be shared for users with experience in R or Python. For this course, having some command line skills would be helpful but they are not strictly necessary. 

Course objectives

After the course:

1.     The participant will know the fundamentals of data visualization.
2.     The participant can create the most common data visualization techniques.
3.     The participant will know the most common pitfalls in visualization design (and how to avoid them)
4.     The participant can create effective visualizations.

For extra credit(s), the participants could choose a problem of their own research field related to: a data mining, data presentation, data analysis, or data discovery task. Participants will design and implement a visualization addressing the problem. Results and conclusions will be graded and feedback will be sent to the participants. 

 Please be aware that FSE PhD candidates get priority for registration.

ECTS

1

Available methods of payment

• Projectcode (e.g. ITB)
• Payment by money transfer