A blog about data science, statistics, and data analysis with open-source software.
The data professions (data science, analysis, engineering, etc.) are highly technical fields, and much online discussion (in particular, on this blog!), conference presentations and classes focus on technical aspects of data work or on the results of data analyses. These discussions are necessary for teaching important aspects of the data trade, but they often ignore the fact that data and…
There are many blog posts and think-pieces about the state of data and the data labor market in the US, but far fewer such writings focused on Europe. The goal of this blog post is to present a data-driven analysis of the job market for data profiles in Europe in 2025, based on an analysis of 8,086 European job listings posted between April 13 to May 9, 2025. This blog post is based on a talk…
This blog post is the second installment in a series detailing analyses of the 2023 De Gemeente-Stadsmonitor (The Municipality and City Monitor) survey, conducted in the region of Flanders in Belgium. You can check out the first post here.
What’s it like to live in Flanders these days?
I don’t normally write about what I do at work (it’s not often allowed), but I’m happy to share a link to a piece I wrote with colleagues about doing data analysis and statistics in the aquaculture sector.
This post was co-written with Cesar Legendre of Prophecy Labs
In this post, we will return to the dataset containing song lyrics from country and R&B/hip-hop music that we analyzed in the two previous posts. The data consist of popular songs from the Billboard year-end music charts, and we will use the Python package Empath to measure the presence of higher-level categories (e.g. positive emotion words) in the song lyrics texts. This approach to text…
In this post, we will return to the dataset containing song lyrics from country and R&B/hip-hop songs that we analyzed in the previous post. The data consist of popular songs from the Billboard year-end music charts, and we will use the tidy analytic approach to text analysis to analyze how the two genres differ in their descriptions of men and women. This analytical approach is taken fairly…
In this post, we will analyze text data from song lyrics from two very different (yet quintessentially American) musical styles: country and R&B/hip-hop. The data consist of popular songs from the Billboard year-end music charts, and we will use a Python library called Scattertext to produce a visualization that gives a high-level view of the words that distinguish and are common across the…
Introduction
