Back on the Football Trail
I haven’t done anything with football data for ages. All sorts of reasons why, including that maintaining the data became a proper pain in the neck and I was spending more time on that than on fun vis stuff and models. Anyway, some sudden inspiration, the old database is repaired, code dusted off and… Here’s…
30 Day Map Challenge 2020
My entries to November 2020’s ’30 Day Map Challenge’ on Twitter. No commentary, just maps.
A Better Covid-19 Heatmap
I got frustrated with the UK Government’s Covid-19 maps of England and tried to build a better one using R and Shiny. Code examples and analysis may be coming, but for now you can find the app here.
Learning to code (properly) in R and Shiny
You’ve probably seen this diagram before, or a variation on it; data science happens at the conjunction of statistics, domain knowledge and computer science. Sometimes the domain knowledge part is swapped for data visualisation, but it still works. I came to data science from statistics – my first job was as an econometrician – and…
Early season football viz, EPL and League 2
Five games into the Premier League season, I thought I’d resurrect some old ggplot2 scripts and have a look at teams’ shot locations, attacking play and possession areas. I’ve been drawing these charts on and off for a few seasons but only just noticed that it’s become possible to extend them to cover League 2….
Should I use a black background for my data visualisation?
I’ve wavered back and forth on this. Black backgrounds can make your data visualisation jump off the page but they’re not always the correct choice. Here’s when I’ll consider or reject ‘dark mode’ for a dashboard or other visualisation.
Visualising your Twitter personality
Who you follow on Twitter can say a lot about you and with a bit of R and Gephi, can look quite pretty too. Here’s my network (who I follow, not who follows me), clustered into communities by Gephi, based on the similarity of each account’s own followers. It works pretty well to profile my…