VU Visual Data Science

VU Visual Data Science WS 3.0 ECTS, 186.868

Johanna Schmidt


A summary of the results of lab part 2 can be found here, the number of points have been sent via email. Thank you for the participation of the lecture!


The VU Visual Data Science will discuss how techniques from visualisation and visual analytics can be applied to data science. The lecture part will start with a theoretical introduction to visualisation and visual analytics. Afterwards current visualisation solutions for data science will be introduced, and it will be discussed how current software libraries and applications implement these techniques. The VU will mainly consist of a practical part where visualisation techniques will be applied to data sets. There is also a possibility to analyze your own data.


Date Title Downloads
03.10.2018 Introductory lecture ("Vorbesprechung")
10.10.2018 Introduction to Visualisation
17.10.2018 Introduction to Visual Data Science
24.10.2018 --
31.10.2018 Visualisation for Spatial Data
07.11.2018 Visualisation for Graph Data, Visualisation for Multivariate Data  
14.11.2018 --
21.11.2018 Visualisation for Machine Learning
28.11.2018 Guest lecture by Thomas Mühlbacher: Visual Data Science Applications in Energy, Industry, and Engineering - a talk about current data science projects together with industry partners, and how visualisation supports different data science tasks  
05.12.2018 Applications & Libraries
12.12.2018 Applications & Libraries

Other Dates

Date Type Content
19.12.2018 Deadline Lab Part 1
09.01.2019 Q&A Session Lab Part 2
16.01.2019 Workshop Part 1 (mandatory!) Final presentations
23.01.2019 Workshop Part 2 (mandatory!) Final presentations
30.01.2019 Deadline Lab Part 2


The lab part of the VU consists of two parts (both parts have to be submitted for a positive grade).

Part 1

-- Lab Part 1 Results --
-- Lab Part 1 Description --
In the first part we will study the difference between statistical analysis and visual data analysis. A multivariate dataset is provided, and three tasks have to be solved. The tasks have to be solved twice, once solely using statistical methods, and once solely using visual analysis. Afterwards, a report (min. 2 A4 pages) has to be written to document the findings, and evaluate the differences between the two methods. The report has to be submitted until December 19th, 2018, via email (

Part 2

-- Lab Part 2 Results --
-- Lab Part 2 Description --
After we got to know how visualization can be used to analyze data, we will now concentrate on presentation. The first goal of this lab part is to create a visual presentation (e.g., a dashboard) of a dataset which will then be presented in a workshop. Two workshops will take place on January 16th, 2019 and January 23rd, 2019 (see arrangement below). The attendance of the workshop is mandatory. As a second goal of this lab part, we will broaden our knowledge about visual tools. For this we will create the same visualization with different data science tools, identify differences between the tools, and evaluate them. The findings have to be summarized in a report which has to be submitted until January 30th, 2019, via email ( The final evaluation results will be published online.

Extra task

-- Task Description --
The extra (bonus) task is optional and can be used to gain additional points in case you could not attend the lecture (see below). The deadline for this task is January 30th, 2019.

Final Workshop

The final presentations will take place on two days in January, and will be scheduled in the following way:
January 16th, 2019
00026842 00327029 00425061 00627631 00725136 00815302 00825264 00926571
01127793 01128138 01129941 01226745 01258009 01260167 11831429  
January 23rd, 2019
01263356 01342667 01348181 01358135 01425285 01425684 01452119
01552238 01625713 11734662 11743494 11778996 11830124  
Attendance of the workshop is mandatory for the scheduled day only.


The grade of the lecture is defined by how many points participants earned during the lecture. There will be no final exam at the end.
Grades are defined as follows:
Sehr Gut (1) > 85 points
Gut (2) > 75 points
Befriedigend (3) > 62 points
Genügend (4) > 50 points
Nicht Genügend (5) <= 50 points
Points can be earned based on the following scheme:
Attendance of the lecture 3 points / lecture
Lab Part 1 30 points
Lab Part 2 50 points
Extra (bonus) task 10 points