01.聚类分析-Kmeans的简单实现

Kmeans实例实现代码

软件环境：scala2.10.4+spark1.6.3

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

object MyTest {

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

    // 屏蔽不必要的日志显示在终端上

    Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
    Logger.getLogger("org.eclipse.jetty.server").setLevel(Level.OFF)

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

    //装载数据集
    val mydata = sc.textFile("kmeans_data.txt",1)
    val testdata = sc.textFile("kmeans_data_test.txt",1)
    val parsedData = mydata.map(s => Vectors.dense(s.split(' ').map(_.toDouble)))

    //将数据集聚类，2个类，20次迭代，