Machine Learning//Module 01//Spatial Partitioning

K-Means Visualizer

Observe iterative Euclidean Voronoi partitioning, centroid shifts toward cluster means, and Within-Cluster Sum of Squares (WCSS) convergence.

03 // Spatial Partitioning Canvas

Shifted(Iter 0)

Step 0/-1

01 // Hyperparameter Config

K-Means++ PRNG

Number of Clusters (K):3

Dataset Distribution:

Sample Size (N):80 points

02 // Clustering Telemetry

Live Mathematical Readout

Inertia (WCSS)0Σ ||x − c_k||²

StatusOptimizing...Δ = 0

Iteration0Step 0/-1

Reassigned0Points shifted

Step Trace:Ready to begin.

04 // Diagnostic: The Elbow Method

Within-cluster sum of squares (WCSS) strictly decreases as K increases, hitting 0 when K = N (each point is its own centroid).

Therefore, a lower WCSS does not alone prove that a larger K is superior. In machine learning practice, researchers run multiple K trials and look for the "Elbow Point"—the inflection where adding another centroid yields diminishing returns in variance reduction.