Hands-on, code-first tutorials. Each one walks you through building a core machine learning algorithm in pure Python — and 10 of them run live in your browser, no install required.
Once you make predictions, you need to know if they are any good. Implement accuracy, the confusion matrix, MAE, RMSE and R² from scratch — and learn which to trust when. Runnable in your browser.
Estimate how your model will perform on unseen data. Implement train/test splits, k-fold, stratified folds and the bootstrap from scratch. Runnable in your browser.
Many ML algorithms expect data on a common ruler. Implement normalization and standardization from scratch, avoid leakage, and know which one each algorithm wants. Runnable in your browser.
Before you train a model, you have to load data. Read CSVs, convert types and encode labels with nothing but the standard library. Runnable in your browser.
Why bother implementing algorithms yourself when great libraries exist? The case for building your own — what you learn, what it costs, and a five-step method that works.