Data Science

This is the skill you want when you're staring at a new CSV and need to decide what actually matters. It walks you through the full EDA to modeling workflow with strong opinions on statistical rigor: visualize before you model, check your test assumptions instead of blindly running t-tests, always validate on holdout data. The guidance is practical, like when to use Mann-Whitney over t-tests based on normality checks, how to build reproducible cleaning pipelines that don't mutate your original dataframe, and why you should report effect sizes alongside p-values. Built for engineers who can code but want to avoid the common statistical traps that make your analysis meaningless.