java map统计词频_mapreduce 词频统计

基于八股文的形式编写mapreduce 程序

打包jar 与测试运行处理

wordcount 为例 理解mapreduce 并行计算原理

基于八股文的形式编写mapreduce 程序

mapreduce java 代码

package org.apache.hadoop.studyhdfs.mapredce;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.conf.Configured;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.util.Tool;

import org.apache.hadoop.util.ToolRunner;

/**

*

* @author zhangyy

*

*/

public class WordCountMapReduce extends Configured implements Tool{

// step 1: mapper class

/**

* public class Mapper

*/

public static class WordCountMapper extends //

Mapper{

// map output value

private final static IntWritable mapOutputValue = new IntWritable(1) ;