Hands-on data training for journalists and other data storytellers.
1-on-1 sessions to level up your data skills scheduled around your time and project.
A community for and by nerds in the newsroom.
Cleaning messy donor names in OpenRefine, one clustering algorithm at a time — fingerprints, phonetic matching, and nearest neighbor.
Cleaning messy datasets two ways: by hand in OpenRefine and with an LLM — and how the dirt itself hides stories.
Let's dig into the dirt 🐸🧹
What makes a good map for your story, plus a hands-on intro to QGIS, the best free mapping tool.
No coding knowledge needed — a systematic approach to prompting so you can get an LLM to code anything.
Also: come learn about maps! Now for real.
What text embeddings are and how to put them to work in practice.
Read the words as critically as you read the numbers — what a health-data Pondcast taught us about LLM bias.
Also: come learn about maps!
Uncovering narratives and insights from healthcare expenditure data.
Also: come learn about embeddings and how to find even more stories in data!
Build intuition for what pivot tables do, how to read them, and how to construct them from a question.
What tidy data is, the most common ways spreadsheets go wrong, and a checklist to confirm your data is analysis-ready.
A step-by-step checklist to interrogate any dataset and surface story angles — from first look to context checks.
Let the computer track your units and never miscalculate gigatons vs megatons again.