Chapter 2 · Inside a Learning System

Choosing a model: train, validation, test

150 iris flowers, 3 species, split into train / validation / test before any model is fit. Three named model families compete on validation only; the test set opens once, at the end. You only need to recognize the names here — how each one works comes later in the book.

Sepal length vs. sepal width

Only 2 of the 4 available measurements are used, on purpose.

150 flowers · 3 species

SetosaVersicolorVirginica

Just the names, for now. Logistic Regression, Linear Discriminant Analysis, and Gaussian Naive Bayes each score every flower differently, but the mechanics come later in the book — Chapter 3 (Bayes' Theorem) and Chapter 5 (Bayes vs. Logistic) unpack two of these in depth. What matters here is the workflow: fit on train, choose on validation, and touch the test set exactly once.