Spark機器學習：KMenas算法

KMenas算法比較簡單，不詳細介紹了，直接上代碼。

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

/**
  * Created by Administrator on 2017/7/11.
  */
object Kmenas {

  def main(args:Array[String]): Unit ={
    // 設置運行環境
    val conf = new SparkConf().setAppName("KMeans Test")
      .setMaster("spark://master:7077").setJars(Seq("E:\\Intellij\\Projects\\MachineLearning\\MachineLearning.jar"))
    val sc = new SparkContext(conf)
    Logger.getRootLogger.setLevel(Level.WARN)

    // 讀取樣本數據並解析
    val data = sc.textFile("hdfs://master:9000/ml/data/kmeans_data.txt")
    val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble))).cache()

    // 新建KMeans聚類模型並訓練
    val initMode = "k-means||"
    val numClusters = 2
    val numIterations = 500
    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))
    }

    // 誤差計算
    val Error = model.computeCost(parsedData)
    println("Errors = " + Error)

  }

}

運行結果：

文章出處：http://www.cnblogs.com/mstk/p/7151943.html