Finding Clusters

k-means

An interactive lesson with 6 steps, about 5 minutes: you predict, drag and solve, with instant feedback on every answer. It runs in your browser and needs JavaScript.

What you’ll learn

• k-means: assign points to the nearest centre, move centres to the means, repeat.
• It always settles, but possibly on a local optimum: restart several times.
• Choose k with care; the elbow of the inertia curve is a guide.

Steps

1. No labels at all
2. Watch it run
3. Move the centre
4. How many clusters?
5. Unlucky starts
6. Inertia by hand