机械语言 kmeans算法
package akria
import org.apache.log4j.{Logger, Level}
import org.apache.spark.mllib.clustering.KMeans
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.{SparkContext, SparkConf}
/**
* Created by sendoh on 2015/3/24.
*/
object Kmeans {
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().setAppName("Kmeans").setMaster("local[4]")
val sc = new SparkContext(conf)
//装载数据类
val data = sc.textFile("/datatnt/Kmeans_data.txt", 1)
val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble)))
//将数据集聚类,2个类,20次迭代,形成数据模型
val numClusters = 2
val numIterations = 20
val model =