MachineLearning/kmeans library

🔶 k-Means Clustering (robust, production-minded)

A compact, well-documented implementation of k-means clustering with a k-means++ initializer, configurable distance metric (Euclidean), and a deterministic API that exposes fit, predict, and inertia.

Contract:

• Input: feature matrix X as List<List<double>> (n x m), k clusters.
• Output: learned centroids and integer labels for each point.
• Error modes: throws ArgumentError on invalid shapes or parameters.

Time Complexity: O(n * k * iters * m) Space Complexity: O(k * m + n)

Classes

KMeans