学步园

  另外一个hadoop的入门demo，求平均数。是对WordCount这个demo的一个小小的修改。输入一堆成绩单（人名，成绩），然后求每个人成绩平均数，比如：

//  subject1.txt

  a 90
  b 80
  c 70

 // subject2.txt

  a 100
  b 90
  c 80

  求a,b,c这三个人的平均分。解决思路很简单，在map阶段key是名字，value是成绩，直接output。reduce阶段得到了map输出的key名字，values是该名字对应的一系列的成绩，那么对其求平均数即可。

  这里我们实现了两个版本的代码，分别用TextInputFormat和 KeyValueTextInputFormat来作为输入格式。

  TextInputFormat版本：

import java.util.*;
import java.io.*;

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



public class AveScore {
	
	public static class AveMapper extends Mapper<Object, Text, Text, IntWritable>
	{
		@Override
		public void map(Object key, Text value, Context context) throws IOException, InterruptedException
		{
			String line = value.toString();
			String[] strs = line.split(" ");
			String name = strs[0];
			int score = Integer.parseInt(strs[1]);
			context.write(new Text(name), new IntWritable(score));
		}
	}
	
	public static class AveReducer extends Reducer<Text, IntWritable, Text, IntWritable>
	{
		@Override
		public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException
		{
			int sum = 0;
			int count = 0;
			
			for(IntWritable val : values)
			{
				sum += val.get();
				count++;
			}
			
			int aveScore = sum / count;
			
			context.write(key, new IntWritable(aveScore));
		}
	}
	
	public static void main(String[] args) throws Exception
	{
		Configuration conf = new Configuration();
		
		Job job = new Job(conf,"AverageScore");
		job.setJarByClass(AveScore.class);
		
		job.setMapperClass(AveMapper.class);
		job.setReducerClass(AveReducer.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		System.exit( job.waitForCompletion(true) ? 0 : 1);
	}
}

KeyValueTextInputFormat版本；

import java.util.*;
import java.io.*;

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


public class AveScore_KeyValue {
	
	public static class AveMapper extends Mapper<Text, Text, Text, IntWritable>
	{
		@Override
		public void map(Text key, Text value, Context context) throws IOException, InterruptedException
		{
		    int score = Integer.parseInt(value.toString());
			context.write(key, new IntWritable(score) );
		}
	}
	
	public static class AveReducer extends Reducer<Text, IntWritable, Text, IntWritable>
	{
		@Override
		public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException
		{
			int sum = 0;
			int count = 0;
			
			for(IntWritable val : values)
			{
				sum += val.get();
				count++;
			}
			
			int aveScore = sum / count;
			
			context.write(key, new IntWritable(aveScore));
		}
	}
	
	public static void main(String[] args) throws Exception
	{
		Configuration conf = new Configuration();
		conf.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator", " ");
		
		Job job = new Job(conf,"AverageScore");
		job.setJarByClass(AveScore_KeyValue.class);
		
		job.setMapperClass(AveMapper.class);
		job.setReducerClass(AveReducer.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		job.setInputFormatClass(KeyValueTextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class); 

		
		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		System.exit( job.waitForCompletion(true) ? 0 : 1);
	}
}

输出结果为：

  a 95
  b 85
  c 75