MapReduceAPI

最新推荐文章于 2022-03-17 12:35:21 发布

佑熙

最新推荐文章于 2022-03-17 12:35:21 发布

阅读量438

点赞数

CC 4.0 BY-SA版权

分类专栏： MapReduceAPI 文章标签： MapReduceAPI

本文链接：https://blog.youkuaiyun.com/weixin_42871374/article/details/84571795

MapReduceAPI 专栏收录该内容

1 篇文章

订阅专栏

本文详细介绍了如何使用 Hadoop 的 Combiner 功能来优化 MapReduce 任务的性能，通过实例展示了如何减少网络传输的数据量，提高数据处理效率。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

CombinerTest
package a.b.c;

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.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;


//求取NASA的每个ip的访问次数

class SumMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
	@Override
	protected void map(LongWritable key, Text value,Context context)
			throws IOException, InterruptedException {
		String lineString=value.toString();
		String []wordStrings=lineString.split(" ");
		String visitorIP=wordStrings[0];
		context.write(new Text(visitorIP), new IntWritable(1)); 
	}
}


class SumCombiner extends Reducer<Text, IntWritable, Text, IntWritable>{
	@Override
	protected void reduce(Text key, Iterable<IntWritable> val,Context context)
			throws IOException, InterruptedException {
		int sum=0;
		for (IntWritable values:val){
			sum+=values.get();
		}
		context.write(key, new IntWritable(sum));
		
	}
}


class SumReducer extends Reducer<Text,IntWritable,Text,IntWritable>{
	@Override
	protected void reduce(Text key, Iterable<IntWritable> val,Context context)
			throws IOException, InterruptedException {
		int sum=0;
		for (IntWritable values:val){
			sum+=values.get();
		}
			context.write(key, new IntWritable(sum));
		
	}

}



public class CombinerTest {
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		Configuration configuration=new Configuration();
		Job job=Job.getInstance(configuration);
		
		
		//设置类
		job.setJarByClass(CombinerTest.class);
		
		
		//设置mapper类
		job.setMapperClass(SumMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		//设置combiner类
		job.setCombinerClass(SumCombiner.class);
		
		
		//设置reducer类
		job.setReducerClass(SumReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		
		//File
		FileInputFormat.addInputPath(job,new Path(args[0]));
		FileOutputFormat.setOutputPath(job,new Path(args[1]));
		
		System.exit(job.waitForCompletion(true) ? 0 : 1);
		
			
	}

}