Data Visualisation

Data visualisation allows you to:

• Extract valuable information and patterns from data

• Communicate this in a clear and comprehensible visual representation

• Enhance the communication of research findings, making it accessible to a broader audience

• Identify data quality issues, as outliers and data errors may become more visible in visualisations

Therefore, data visualisation is an aspect of research data management!

Below follow some resources that may help you in creating clearer, more accessible and more transparent data visualisations.

Tools¶

• Datawrapper, where you can upload your data to generate tables and charts.

• upset graphs are a straightforward way to visualize set intersections in a matrix layout, which can help in analysing multiple datasets at once.

• Using Python Plotly you can add annotations and animations as extra visual cues to highlight important features.

• Annotating visualisations in Python plotly (blog and video)

• Animations using Python plotly

Accessibility¶

• Tips to improve interpretability and accessibility by Dr Tracey Weissgerber (video)

• Writing Meaningful Alt-Texts for Data Visualisations in R

• Writing Alt Text to communicate the meaning in data visualizations by Hare (2022)

• Alt-texts

• Writing Alt Text for a Scientific Figure by Kristin Briney

• Writing Alt Text for Data Visualization To get started, use Amy Cesal’s quick formula: [alt text = chart type of type of data where reason for including chart. Link to data.]

Colours¶

• A detailed guide to colors in data vis style guides (blog)

Resources¶

Books and Articles¶

• Fundamentals of Data Visualisation by Wilke, 2019

• Data Visualisation, A practical introduction by Healy (2018)

• Creating clear and informative image-based figures for scientific publications by Jambor et al. (2021)

• A layered grammar of graphics by Wickham (2010)

• A Field Guide to Digital Color by Stone (2003)

• The Grammar of Graphics by Wilkinson (1999)

• The Visual Display of Quantitative Information by Tufte (2001)

• Avoiding Twisted Pixels: Ethical Guidelines for the Appropriate Use and Manipulation of Scientific Digital Images by Cromey (2010)

Other text resources and examples¶

• Data Visualisation Course

• Free visual and communication resources

• A collection of notebooks demonstrating plotting with matplotlib

• A Comprehensive Guide to the Grammar of Graphics for Effective Visualization of Multi-dimensional Data

• Friends Don’t let Friends Write Bad Graphs by Li (2023)

• Data by Design

• Parallel Coordinates Plots (PCP)

• I’ve Stopped Using Box Plots. Should You?

Videos¶

• 5 minute videos on Data visualisation - Introduction and motivation and Figure design, design process, fundamentals

• Create Effective Data Visualizations (second part focuses primarily on Tableau)

• Data visualisation for scientific papers videos by ReproducibiliTeach

• Outline of grammar of graphics

  • A Grammar of Graphics - Excellent summary of the grammar of graphics layers or ‘functional pipeline’

  • Leland Wilkinson - The Grammar of Graphics - Leland himself giving a quick high level summary of the grammar of graphics

• Martin Krzywinski: A pandemic of bad charts

• EMBL Keynote Lecture 2019 - Data visualization and data science, Hadley Wickham

• Practical high level intros to Tufte’s principles

  • What should we do to improve our graphics and figures?

  • Graphical Excellence

• Workshop: Missing Data Exploration, Imputation, and Evaluation by Hanne Oberman

• Violin plots should not exist by Angela Collier

Podcasts¶

• Data Viz Today

• Data Stories

• PolicyViz

Other¶

• biovis