All posts that are about or contain


Reading "Visual Analytics for Data Scientists"

This post is also about or contains
Reading Visual Analytics

I have got more and more interested in working with Visual Analytics. When asking my ex-supervisor for good material on the topic, he did suggest this book, "Visual Analytics for Data Scientists" by Andrenko et al. 1.

I have started to read it, and it seems to be a thorough introduction to the field. Here they do not present the newest research but, as they say, go through  "... the main principles and describe the techniques and approaches that are ready to be put in practice ...". They state that today professionals have started to use visualisation in the analysing process and not only when presenting the findings. And many of them that publish visualisations do have a "quiet little idea of how to choose appropiate visualisation techniques and design correct and effective visualisation of the data they deal with ..." and how to use it. This knowledge gap is what this book is trying to change.

They start with a good example that goes through all the analysing steps. And they also do the iterations that are a vital part of visual analytics. Then they go through how to analyse the data before describing the distribution and finding patterns.

So far, it has been quite interesting, and I have a somewhat better understanding of the material. But it has not reviled much new material compared to what we learned in the visualisation group and could be a book in the master curriculum. My first impression so far is that it could be of interest to everyone that does a sort of analysis work, not only for a data scientist.

As a definition, they cite the following, "the science of analytical reasoning facilitated [made easier] by interactive visual interfaces" 2.
  1. Andrienko, N., Andrienko, G., Fuchs, G., Slingsby, A., Turkay, C., & Wrobel, S. (2020). Visual analytics for data scientists. Springer,

  2. Cook, K., & Thomas, J. (2005, May 9). Illuminating the path: The research and development agenda for visual analytics. OSTI.GOV.



I have studied visualization at the VisGroup here in Bergen, Norway. Unfortunately, I managed not to complete the master thesis due to dyslexia and the fact that I am also bipolar. The first years were a fascinating time before I then got a down period.

My topic for the thesis was how to compare spatial objects and how abstracting them could make the comparison task simpler. The subtitle of it was Comparative Visualization by Abstracting a Spatial Ensemble Data of Plant Growth. I will try to make some posts about this topic and visualization in general. And I will end this with two citations on visualization and one on the comparison task.

The purpose of visualization is insight, not pictures. - Ben Shneiderman 1

Computer-based visualization systems provide visual representations of datasets designed to help people carry out tasks more effectively. Visualization is suitable when there is a need to augment human capabilities rather than replace people with computational decision-making methods. - Tamara Munzner 2

... one may take the viewpoint that much, if not most, of analysis can be viewed as comparison. - Michael Gleicher 3

  1. Card, S. K., Mackinlay, J., & Shneiderman, B. (1999). Readings in Information Visualization: Using Vision to Think (Interactive Technologies) (1st ed.). Morgan Kaufmann.
  2. Munzner, T. (2014). Visualization Analysis and Design (AK Peters Visualization Series) (1st ed.). A K Peters/CRC Press.
  3. Gleicher, M. (2018). Considerations for Visualizing Comparison. IEEE Transactions on Visualization and Computer Graphics, 24(1), 413-423.