The notebook · 04 entries

Writing

Essays and notes on data science, method, and reading the story inside a dataset. Slow to publish, built to last.

What Physiology Taught Me About Reading a Dataset

Before I learned to code, I learned to ask what's actually going on in a system. Here's how that instinct changed the way I approach a spreadsheet.

Nov 2, 20256 min read

Before I learned to code, I learned to ask what's actually going on in a system. Here's how that instinct changed the way I approach a spreadsheet.

Oct 18, 20258 min read

Why counting words the naive way fails, and what cosine similarity is really measuring — the two ideas behind my content-based recommender.

Sep 27, 20255 min read

EDA gets treated as the boring bit before the 'real' modelling. I'd argue it's the whole game.

Sep 5, 20254 min read

Behind every row is a person. A short note on analysing sensitive datasets with respect.