Generalized K-Means Clustering
  • Introduction
    • Relation to Spark K-Means Clusterer
    • Algorithms Implemented
  • Requirements
  • Quick Start
  • Concepts
    • Bregman Divergence
    • WeightedVector
    • BregmanPoint, BregmanCenter, BregmanPointOps
    • KMeansModel
    • MultiKMeansClusterer
    • KMeansSelector
  • Usage
    • Selecting a Distance Function
    • Constructing K-Means Models using Clusterers
    • Embedding Data
    • Seeding the Set of Cluster Centers
    • Iterative Clustering
    • Alternative KMeansModel Construction
    • Customizing
      • Creating a Custom Distance Function
      • Creating a Custom Embedding
Powered by GitBook
On this page

Last updated 12 months ago

Lloyd's algorithm is simple to describe, but in practice different implementations are possible that can yield dramatically different running times depending on the data being clusters. We abstract the clusterer using the MultiKMeansClusterer trait.

PreviousKMeansModelNextKMeansSelector
  1. Concepts

MultiKMeansClusterer

trait MultiKMeansClusterer extends Serializable with Logging {
  def cluster(
    maxIterations: Int,
    pointOps: BregmanPointOps,
    data: RDD[BregmanPoint],
    centers: Seq[IndexedSeq[BregmanCenter]]): Seq[(Double, IndexedSeq[BregmanCenter])]

  def best(
    maxIterations: Int,
    pointOps: BregmanPointOps,
    data: RDD[BregmanPoint],
    centers: Seq[IndexedSeq[BregmanCenter]]): (Double, IndexedSeq[BregmanCenter]) = {
    cluster(maxIterations, pointOps, data, centers).minBy(_._1)
  }
}