词频统计之Reducer实现

MapReduce WordCount Reducer详解

最新推荐文章于 2023-06-09 01:36:57 发布

原创最新推荐文章于 2023-06-09 01:36:57 发布 · 233 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#代码

大数据专栏收录该内容

56 篇文章

订阅专栏

package com.imooc.bigdata.hadoop.hdfs.mr.wc;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.Iterator;

public class WordCountReducer extends Reducer <Text,IntWritable,Text,IntWritable>{
    /**
     *
     * (hello,1) (world,1)
     * (hello,1) (world,1)
     * (hello,1）(world,1)
     * (welcome,1)
     *
     * map的输出到reduce端，是按照相同的key分发到一个reduce上去执行
     *
     * reduce1:(hello,1) (hello,1) (hello,1) ==> (hello,<1,1,1>)
     * reduce2:(world,1) (world,1) (world,1) ==> (world,<1,1,1>)
     *
     *Reducer
     *
     */
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

        int count = 0;

        Iterator<IntWritable> iterator = values.iterator();
        while(iterator.hasNext()){
            IntWritable value = iterator.next();
            count += value.get();
        }
        context.write(key,new IntWritable(1));

    }
}