K-Means clustering.
Move from scattered points to structure. Watch centroids and cluster assignments converge, one iteration at a time.
Your experiment starts here
Ready to explore?
Runs in your browser.
Quick start
Get hands-on.
Choose K and a point count, generate a dataset, then run clustering. Change K or regenerate to compare the results.
What to look for
- Nearest-centroid assignment using Euclidean distance.
- Centroid updates using the mean of assigned points.
- Lloyd’s algorithm, convergence, and sensitivity to initialization.