Spark MLlib聚类代码

部分数据：

1.658985	4.285136
-3.453687	3.424321
4.838138	-1.151539
-5.379713	-3.362104
0.972564	2.924086
-3.567919	1.531611
0.450614	-3.302219
-3.487105	-1.724432
2.668759	1.594842
-3.156485	3.191137
3.165506	-3.999838
-2.786837	-3.099354
4.208187	2.984927

代码：

package workStudy.MLlib

import org.apache.spark.mllib.clustering.KMeans
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.{SparkConf, SparkContext}
/**
 * Created by Administrator on 2016/10/11.
 */
/**
 * 聚类操作
 */
object day2 {
  def main(args: Array[String]) {
    val conf = new SparkConf()
      .setMaster("local")
      .setAppName("day2")
    val sc = new SparkContext(conf)
    //  val data=MLUtils.loadLibSVMFile(sc,"E://machinedata/KNN/Sparkkmean.txt")
    val data = sc.textFile("E://machinedata/kMeans_demo/testSet.txt") //输入数据集
    val parsedData = data.map(s => Vectors.dense(s.split('\t').map(_.trim.toDouble))).cache() //训练数据

    val numClusters = 2 //聚类中心
    val numIterations = 20 //迭代次数
    val model = KMeans.train(parsedData, numClusters, numIterations) //训练模型
    model.clusterCenters.foreach(println) //聚类中心点坐标
  }
}

运行结果：

[-3.0953906153846154,-2.262190846153846]
[1.3368722037037037,1.1696492222222223]