最近在研究hadoop与mapReduce,网上教程只有个wordcount程序示范,太简单,故写了个相对复杂点的涉及到多个文件之间同时运算的矩阵乘法的代码用于实验与测试,供大家学习与参考。
下载地址:
http://download.csdn.net/detail/statdm/4395736
调用方法:
执行:hadoop jar matrix.jar com.baosight.mapred.test.MatrixMulti left:/tmp/a right:/tmp/b output:/tmp/c leftprefix:000000_ rightprefix:000000_
>参数1:left:左矩阵路径
>参数2:right:右矩阵路径
>参数3:output:左矩阵乘右矩阵结果路径
>参数4:leftprefix:左矩阵文件前缀
如/tmp/a/000000_0,000000_1,000000_2……的000000_
>参数5:rightprefix:右矩阵文件前缀
>左右矩阵按列存储,每个文件只存放一列值,如2x2的单位矩阵, 000000_0存放1 0
000000_1存放
0 1
代码示范:
package com.baosight.mapred.test; import java.io.IOException; import java.util.ArrayList; import org.apache.hadoop.io.DoubleWritable; import org.apache.hadoop.mapred.MapReduceBase; import org.apache.hadoop.mapred.Mapper; import org.apache.hadoop.mapred.OutputCollector; import org.apache.hadoop.mapred.Reporter; public class MatrixMapper extends MapReduceBase implements Mapper<MapInputKey,MapInputValue,ReduceInputKey,DoubleWritable>{ @Override public void map(MapInputKey key, MapInputValue value, OutputCollector<ReduceInputKey, DoubleWritable> output, Reporter reporter) throws IOException { ArrayList<Double> leftElements = value.leftMatrixColumn; ArrayList<Double> rightElements = value.rightMatrixColumn; int leftColNum = key.leftColNum; int rightColNum = key.rightColNum; for(int i = 0; i < leftElements.size();i++){ Double leftVal = leftElements.get(i); Double rightVal = rightElements.get(leftColNum); ReduceInputKey tempKey = new ReduceInputKey(); tempKey.row = i; tempKey.col = rightColNum; // output.collect(tempKey, new DoubleWritable(leftVal.doubleValue()*rightVal.doubleValue())); output.collect(tempKey, new DoubleWritable(leftVal*rightVal)); } } }