Kmeans算法学习与SparkMlLib Kmeans算法尝试

package main.asiainfo.coc.sparkMLlib

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

/**
* Created by root on 12/15/15.
*/
object kmeans {
def main(args: Array[String]): Unit = {
val sparkConf = new SparkConf().setMaster("local").setAppName("cocapp")
val sc = new SparkContext(sparkConf)
// 装载数据集
val data = sc.textFile("/usr/local/spark-1.4.0-bin-2.5.0-cdh5.2.1/ysy.txt")
val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble)))
// 将数据集聚类，2个类，20次迭代，进行模型训练形成数据模型
val numClusters = 2
val numIterations = 20
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)
// 交叉评估1，只返回结果
val testdata = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble)))
val result1 = model.predict(testdata)
result1.foreach(println)
println("-----------------------")
// 交叉评估2，返回数据集和结果
val result2 = data.map {
line =>
val linevectore = Vectors.dense(line.split(' ').map(_.toDouble))
val prediction = model.predict(linevectore)
line + " " + prediction
}
result2.foreach(println)
sc.stop()
}
}