MR词频统计

最新推荐文章于 2024-08-07 12:07:44 发布

It_sucks

最新推荐文章于 2024-08-07 12:07:44 发布

阅读量72

点赞数

文章标签： mr hadoop mapreduce

本文链接：https://blog.csdn.net/weixin_71132847/article/details/130797923

版权

本文介绍了使用Hadoop的MapReduce实现词频统计的示例。通过WordCountMapper类进行单词拆分并输出，然后在WordCountReduce类中对相同单词的计数进行求和。最后，WordCountRunner类配置并运行MapReduce任务，输入文件位于'D:\mr\intput'，输出结果保存在'D:\mr\output'。

摘要由CSDN通过智能技术生成

WordCountMapper

package com.text212;

import java.io.IOException;

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

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{

   @Override
   protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
           throws IOException, InterruptedException {

       String line = value.toString();
       String[] words = line.split(" ");
       for(String word:words){
           context.write(new Text(word), new IntWritable(1));
       }

   }

}

WordCountReduce

package com.text212;

import java.io.IOException;

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

public class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable>{

   @Override
   protected void reduce(Text key, Iterable<IntWritable> value,
           Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
       int count = 0;
       for(IntWritable iw:value){
           count += iw.get();
       }
       context.write(key, new IntWritable(count));
   }

}

WordCountRunner

package com.text212;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCountRunner {

public static void main(String[] args) throws Exception {

       Configuration conf = new Configuration();
Job job = Job.getInstance(conf);

       job.setJarByClass(WordCountRunner.class);
       job.setMapperClass(WordCountMapper.class);
       job.setReducerClass(WordCountReduce.class);

job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);

job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);

FileInputFormat.setInputPaths(job, new Path("D:\\mr\\intput"));

FileOutputFormat.setOutputPath(job, new Path("D:\\mr\\output"));

boolean res = job.waitForCompletion(true);

System.exit(res ? 0 : 1);

}

}