java 矩阵乘法的mapreduce程序实现

java 矩阵乘法的mapreduce程序实现

map函数：对于矩阵m中的每个元素m(ij)，产生一系列的key-value对<(i，k)，（m，j，m(ij)）>

其中k=1,2.....知道矩阵n的总列数;对于矩阵n中的每个元素n(jk)，产生一系列的key-value对<(i , k) , (n , j ,n(jk)>, 其中i=1,2.......直到i=1,2.......直到矩阵m的总列数。

map

package com.cb.matrix;

import static org.mockito.matchers.intthat;

import java.io.ioexception;

import org.apache.hadoop.conf.configuration;
import org.apache.hadoop.io.text;
import org.apache.hadoop.mapred.filesplit;
import org.apache.hadoop.mapreduce.mapper;

import com.sun.org.apache.bcel.internal.generic.new;


public class matrixmapper extends mapper<object, text, text, text> {
 private text map_key=new text();
 private text map_value= new text();
 private int columnn;
 private int rowm;
 /**
 * 执行map()函数前先由conf.get()得到main函数中提供的必要变量
 * 也就是从输入文件名中得到的矩阵维度信息
 */
 
 @override
 protected void setup(mapper<object, text, text, text>.context context) throws ioexception, interruptedexception {
 // todo auto-generated method stub
 configuration config=context.getconfiguration();
 columnn=integer.parseint(config.get("columnn"));
 rowm =integer.parseint(config.get("rowm"));
 }
 
 @override
 protected void map(object key, text value, mapper<object, text, text, text>.context context)
  throws ioexception, interruptedexception {
 // todo auto-generated method stub
 //得到文件名，从而区分输入矩阵m和n
 filesplit filesplit=(filesplit)context.getinputsplit();
 string filename=filesplit.getpath().getname();
 
 if (filename.contains("m")) {
  string[] tuple =value.tostring().split(",");
  int i =integer.parseint(tuple[0]);
  string[] tuples=tuple[1].split("\t");
  int j=integer.parseint(tuples[0]);
  int mij=integer.parseint(tuples[1]);
  for(int k=1;k<columnn+1;k++){
  map_key.set(i+","+k);
  map_value.set("m"+","+j+","+mij);
  context.write(map_key, map_value);
  }
  
 }
 else if(filename.contains("n")){
  string[] tuple=value.tostring().split(",");
  int j=integer.parseint(tuple[0]);
  string[] tuples =tuple[1].split("\t");
  int k=integer.parseint(tuples[0]);
  int njk=integer.parseint(tuples[1]);
  for(int i=1;i<rowm+1;i++){
  map_key.set(i+","+k);
  map_value.set("n"+","+j+","+njk);
  context.write(map_key, map_value);
  }
 }
 
 }

}

reduce函数：对于每个键（i,k）相关联的值（m,j,m(ij)）及（n,j,n(jk)）,根据相同的j值将m(ij)和n(jk)分别存入不同的数组中，然后将俩者的第j个元素抽取出来分别相乘，最后相加，即可得到p(jk)的值。

reducer

package com.cb.matrix;


import java.io.ioexception;

import org.apache.hadoop.conf.configuration;
import org.apache.hadoop.io.text;
import org.apache.hadoop.mapreduce.reducer;



public class matrixreducer extends reducer<text, text, text, text> {
 private int sum=0;
 private int columnm;
 @override
 protected void setup(reducer<text, text, text, text>.context context) throws ioexception, interruptedexception {
 // todo auto-generated method stub
 configuration conf =context.getconfiguration();
 columnm=integer.parseint(conf.get("columnm"));
 }
 @override
 protected void reduce(text arg0, iterable<text> arg1, reducer<text, text, text, text>.context arg2)
  throws ioexception, interruptedexception {
 // todo auto-generated method stub
 int[] m=new int[columnm+1];
 int[] n=new int[columnm+1];
 
 for(text val:arg1){
  string[] tuple=val.tostring().split(",");
  if(tuple[0].equals("m")){
  m[integer.parseint(tuple[1])]=integer.parseint(tuple[2]);
  
  }else{
  n[integer.parseint(tuple[1])]=integer.parseint(tuple[2]);
  }
  for(int j=1;j<columnm+1;j++){
  sum+=m[j]*n[j];
  }
  arg2.write(arg0, new text(integer.tostring(sum)));
  sum=0;
 }
 }

}

 感谢阅读，希望能帮助到大家，谢谢大家对本站的支持！