Interactive Visual Data Analysis (Data Science)

Course Description

Data Science is an interdisciplinary course with three main topics: machine learning, data-driven simulation, and interactive visual data analysis. The goal of this part on interactive visual data analysis is to introduce you to the benefits, concepts, and practice of designing interactive data visualizations that help gain insights from large and complex data. With enormous amounts of data being collected, being able to turn these data into informed and actionable decisions plays a key role for success. To understand complex phenomena, however, it is not enough to let machines analyze data computationally or let humans analyze data manually. Instead, human and machine analysis can be coupled, taking advantage of both their strengths to understand the behavior of a system, explore phenomena and trends, discover dependencies, and finally make an informed decision. For this purpose, visual representations, interaction techniques, and computational methods need to be synthesized. Through lecture sessions and exercises, we will dive deeper into these components.

Prerequisites

There are no enforced prerequisites for this course. However, a general interest in data visualization and computational approaches are recommended.

Course Mechanics

The course part combines lecture sessions with exercise sessions that revisit and augment the lecture contents. Among other methods such as moderated discussions, the exercises make use of Observable notebooks to provide programming assignments that gradually build and extend an interactive visualization and thereby put the lecture contents into practice. The assignments incrementally work through the stages of transforming raw data into an interactive visualization. For each stage, we will provide an intermediate solution that serves as a common starting point for the next assignment.