通过IDEA及hadoop平台实现k-means聚类算法

package main.scala.yang.spark

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.KMeans

object KMeansBeijing {
  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)

    // 设置运行环境
    val conf = new SparkConf().setMaster("local").setAppName("KMeansBeijing")
    val sc = new SparkContext(conf)

    // 装载数据集
    val data = sc.textFile("file:///home/hadoop/yang/USA/AUG_tag.csv", 1)
    val parsedData = data.filter(!isColumnNameLine(_)).map(line => Vectors.dense(line.split(‘,‘).map(_.toDouble))).cache()
    //
    // 将数据集聚类，7个类，20次迭代，进行模型训练形成数据模型
    val numClusters = 4
    val numIterations = 800
    val model = KMeans.train(parsedData, numClusters, numIterations)

    // 打印数据模型的中心点
    println("Cluster centers:")
    for (c <- model.clusterCenters) {
      println("  " + c.toString)
    }

    // 使用误差平方之和来评估数据模型
    val cost = model.computeCost(parsedData)
    println("Within Set Sum of Squared Errors = " + cost)

//    // 使用模型测试单点数据
//    println("Vectors 0.2 0.2 0.2 is belongs to clusters:" + model.predict(Vectors.dense("0.2 0.2 0.2".split(‘ ‘).map(_.toDouble))))
//    println("Vectors 0.25 0.25 0.25 is belongs to clusters:" + model.predict(Vectors.dense("0.25 0.25 0.25".split(‘ ‘).map(_.toDouble))))
//    println("Vectors 8 8 8 is belongs to clusters:" + model.predict(Vectors.dense("8 8 8".split(‘ ‘).map(_.toDouble))))

    // 交叉评估1，只返回结果
    val testdata = data.filter(!isColumnNameLine(_)).map(s => Vectors.dense(s.split(‘,‘).map(_.toDouble)))
    val result1 = model.predict(testdata)
    result1.saveAsTextFile("file:///home/hadoop/yang/USA/AUG/result1")

    // 交叉评估2，返回数据集和结果
    val result2 = data.filter(!isColumnNameLine(_)).map {
      line =>
        val linevectore = Vectors.dense(line.split(‘,‘).map(_.toDouble))
        val prediction = model.predict(linevectore)
        line + " " + prediction
    }.saveAsTextFile("file:///home/hadoop/yang/USA/AUG/result2")

    sc.stop()
  }

  private def isColumnNameLine(line: String): Boolean = {
    if (line != null && line.contains("Electricity")) true
    else false
  }
}