As data becomes easier and cheaper to generate, we are moving from a hypothesis-driven to data-driven paradigm in scientific research. As a result, we don’t only need to find ways to answer any questions we have, but also to identify interesting questions/hypotheses in that data in the first place. In other words: we need to be able to dig through these large and complex datasets in search for unexpected patterns that - once discovered - can be investigated further using regular statistics and machine learning. Interactive data visualization provides a methodology for just that: to allow the user (be they domain expert or lay user) to find those questions, and to give them deep insight in their data.
- Background and context of data visualization and visual data analysis
- Design as a process: framing the problem, ideation, sketching, design critique, …
- Programming visualizations: static and dynamic
- Project: visualization of expert dataset
- Danai Kafetzaki: firstname.lastname@example.org
- Georgia Panagiotidou: email@example.com
|1||18/2||- ex cathedra: introduction to data visualisation: history, marks/channels/…
- technical: vega-lite
|2||25/2||- part 1: ideation \& brainstorming strategies
- part 2: visual design
|6||7/4||vega and python|
|7||28/4||vega and R|
|8||19/5||final feedback on projects|
Grading will be based both on continuous evaluation (10%) and a written report (90%).
Make sure to add your blog URL to this form: https://forms.gle/2HYugBNZYJ2LJtzg7