Spark mllib k-means 聚合

K-Means算法是一种基于距离的聚类算法，采用迭代的方法，计算出K个聚类中心，把若干个点聚成K类。

package com.immooc.spark

import org.apache.log4j.{Level, Logger}
import org.apache.spark.mllib.clustering.KMeans
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.{SparkConf, SparkContext}

object KMeansTest {
  def main(args:Array[String]): Unit = {


    val conf = new SparkConf().setAppName("KMeansTest").setMaster("local[2]")
    val sc = new SparkContext(conf)

    Logger.getRootLogger.setLevel(Level.WARN)

    // 读取样本数据1，格式为LIBSVM format
    val data = sc.textFile("file:///Users/walle/Documents/D3/sparkmlib/kmeans_data.txt")
    val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble))).cache()

    // 新建KMeans聚类模型，并训练
    val initMode = "k-means||"
    val numClusters = 4
    val numIterations = 100
    val model = new KMeans().
      setInitializationMode(initMode).
      setK(numClusters).
      setMaxIterations(numIterations).
      run(parsedData)
    val centers = model.clusterCenters
    println("centers")
    for (i <- 0 to centers.length - 1) {
      println(centers(i)(0) + "\t" + centers(i)(1))
    }

    // 误差计算
    val WSSSE = model.computeCost(parsedData)
    println("Within Set Sum of Squared Errors = " + WSSSE)
  }
}

1. 输出

centers
9.05	9.05
0.05	0.05
9.2	9.2
0.2	0.2
Within Set Sum of Squared Errors = 0.03000000000004321

http://www.waitingfy.com/archives/4699

4699