HADOOP抽样计算

最新推荐文章于 2021-07-22 10:57:06 发布

原创最新推荐文章于 2021-07-22 10:57:06 发布 · 455 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#hadoop #bigdata

该博客介绍了如何在Hadoop中使用TotalOrderPartitioner进行全排序的示例代码，包括设置分区中值文件、配置抽样参数和运行MapReduce任务。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package com.zhiyou.bd23.totalorder;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.InputSampler;
import org.apache.hadoop.mapreduce.lib.partition.TotalOrderPartitioner;

public class TotalOrder3 {
	
	public static void main(String[] args) throws Exception {
		Configuration configuration = new Configuration();
//		configuration.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator", ",");

		//抽样后计算的中值保存的文件位置
		Path partitionerFile = new Path("/partitioner_file");
		//在configuration设置分区中值文件的位置
		TotalOrderPartitioner.setPartitionFile(configuration, partitionerFile);
		
		Job job = Job.getInstance(configuration);
		job.setJarByClass(TotalOrder3.class);
		job.setJobName("使用TotalOrderPartitioner全排序实例");
		
		job.setMapperClass(Mapper.class);
		job.setReducerClass(Reducer.class);
		job.setPartitionerClass(TotalOrderPartitioner.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		job.setInputFormatClass(KeyValueTextInputFormat.class);
		
		Path inputPath = new Path("/README.txt");
		Path outputDir = new Path("/to3");
		outputDir.getFileSystem(configuration).delete(outputDir, true);
		FileInputFormat.addInputPath(job, inputPath);
		FileOutputFormat.setOutputPath(job, outputDir);
		job.setNumReduceTasks(2);
		
		//设置采样过程的参数
		InputSampler.RandomSampler<Text, NullWritable> sampler = new InputSampler.RandomSampler<Text, NullWritable>(0.1, 20);
		//配置抽样过程和写partitioner文件的过程
		InputSampler.writePartitionFile(job, sampler);
		
		System.exit(job.waitForCompletion(true)?0:1);
	}
}