Kmeans.scala

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

/**
  * Created by taiwoadetiloye on 2016-04-01.
  */

object kmeans extends App{

  val config = new SparkConf().setAppName("My Kmeans Sample App").setMaster("local")
  val sc = new SparkContext(config)
  val sqlContext = new SQLContext(sc)

  // Load and parse the data/kmeans/kmeans_data.txt

  val lines = sc.textFile("****/kmeans_data.txt") //change this to your local file path
  val data = lines.filter(_.nonEmpty)
  val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble))).cache()
  parsedData.cache()
  // Cluster the data into two and three classes using KMeans
  val numClusters = 2
  val numIterations = 20
  val clusters = KMeans.train(parsedData, numClusters, numIterations)
  clusters.clusterCenters.foreach(println)

  parsedData.foreach(println )
  clusters.predict(parsedData).foreach(println) //or clusters



  // Evaluate clustering by computing Within Set Sum of Squared Errors
  val WSSSE = clusters.computeCost(parsedData)
  println("Within Set Sum of Squared Errors = " + WSSSE)

  // Save and load model
  //clusters.save(sc, "/Users/taiwoadetiloye/IdeaProjects/simpleGraph/src/main/resources/")
  //val sameModel = KMeansModel.load(sc, "/Users/taiwoadetiloye/IdeaProjects/simpleGraph/src/main/resources/")

}