spark 实现K-means算法

spark 实现K-means算法

package kmeans;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;.
import java.util.Arrays;
import java.util.Iterator;


import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.api.java.function.VoidFunction;


import scala.Tuple2;



public class kmeans{
   
  static double[][] center = new double[4][2];  //这里有4个中心点，为2维
  static int[] number = new int[4];           //记录属于当前中心点的数据的个数，方便做除法
  static double[][] new_center = new double[4][2];    //计算出来的新中心点
  public static void main(String[] args) {
   

    // 从文件中读出中心点，并且放入center数组中
    ArrayList<String> arrayList = new ArrayList<String>();
    try {
   
      File file = new File("/usr/local/hadoop-2.7.3/centers.txt");
      InputStreamReader input = new InputStreamReader(new FileInputStream(file));
      BufferedReader bf = new BufferedReader(input);
      // 按行读取字符串
      String str;
      while ((str = bf