Classification World

Build the distribution a dataset is a sample of, then sample it.

Class

Drag on the field to lay down probability mass for this class.

Brush width 0.28

π₀ 0.33 π₁ 0.33 π₂ 0.33

How common each class is overall. Moves mass between classes without changing any class's shape.

Points 200

Every resample is a fresh independent dataset. The world does not change.

Paste-ready Python for the Colab companion. The dataset is the points on screen; the world is the distribution behind them.

Surface shows

0 components

Bayes accuracy —

Drag here to paint class 0

The world itself — drag to rotate

Hover the surface to read the distribution

P(0|x) — P(1|x) — P(2|x) —