Personal website of Etienne Bacher: blog posts about R, research, and software.

themis 1.1.0 is now on CRAN. This release adds eleven new sampling steps, per-class sampling targets, and support for new distance metrics.

lorax is a new R package that characterizes fitted tree- and rule-based models: extract their decision rules, see which predictors they actually use, and convert trees for plotting with partykit.

Our obsession with AI code-writing tools is overwhelming the web’s unsung human caretakers

The inter-generational struggle to find clothes that fit more than a tiny portion of women

Air 0.10.0 is here! This release rounds up everything new since 0.8.2: a new `assignment-style` option, tighter Positron and RStudio integrations, installation via uv and friends, pre-commit support, ...

Join us for a full day of collaborative open source work — whether you're a seasoned contributor or making your very first pull request.

The Rousseeuw Prize for Statistics is a biennial prize to celebrate outstanding contributions to statistics research.

Two years of Long Covid data with the Visible app — calendar heatmaps, ridgeline plots, change-point detection, and stability score across menstrual cycle phases.

Two new cheatsheets for Tidymodels are now available: one for creating models with parsnip, and one for preprocessing data with recipes.

A small cascade of CRAN releases brings new model types to tidymodels.

Introducing ggsql, a grammar of graphics for SQL that lets you describe visualizations directly inside SQL queries.

Five git commands that tell you where a codebase hurts before you open a single file. Churn hotspots, bus factor, bug clusters, and crisis patterns.

Using OpenStreetMap historical data to map the rise and fall of burger chains in London.

It is becoming ever clearer both how devastating the second wave of winter 2020/21 was, and how much of that devastation could have been avoided.