开发运行hadoop的AvgScore程序

整体思路：在eclipse里开发计算学生平均成绩，打成jar包后在Hadoop中运行。

学生成绩纯文本文件如下：

we 90
sdf 89
sf 87
sf 90
sdf 78
sdf 67
we 98

注意地方：运行Hadoop程序一定要用root把防火墙关掉：service iptables stop。不然运行会提示PriviledgedActionException异常。

怎么运行hadoop程序，此处不表，在wordcount中有介绍。

源码：

package com.apache.hadoop.examples;

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

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.Mapper;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.hadoop.yarn.server.resourcemanager.ResourceManager;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
//实现统计学生平均成绩功能，源文件中学生姓名和成绩空格相连，每行只有一门科目；若某个学生有多门成绩，则分多行。
//实现Tool工具类，是为了初始化一个hadoop配置实例
public class AvgSore implements Tool{
	Configuration configuration;
	public static final Logger log = LoggerFactory.getLogger(AvgSore.class);
	
	public static class MyMap extends Mapper<Object, Text, Text, IntWritable>{

		@Override
		protected void map(Object key, Text value, Context context)
				throws IOException, InterruptedException {
			//将输入的纯文本的数据转化成String
			String stuInfo = value.toString();
			System.out.println("studentInfo:"+stuInfo);
			log.info("MapStudentInfo:"+stuInfo);
			//将输入的数据先按行进行分割
			StringTokenizer tokenizerArticles = new StringTokenizer(stuInfo, "\n");
			//分别对每一行进行处理
			while(tokenizerArticles.hasMoreTokens()){
				//每行按空格进行划分
				StringTokenizer tokenizer = new StringTokenizer(tokenizerArticles.nextToken());
				String name = tokenizer.nextToken();//学生姓名
				String score = tokenizer.nextToken();//学成成绩
				Text stu = new Text(name);
				int intscore = Integer.parseInt(score);
				log.info("MapStu:"+stu.toString()+" "+intscore);
				context.write(stu, new IntWritable(intscore));//输出学生姓名和成绩
			}
			
		}
		
	}
			
	public static class MyReduce extends Reducer<Text, IntWritable, Text, IntWritable>{

		@Override
		protected void reduce(Text key, Iterable<IntWritable> values, Context context)
				throws IOException, InterruptedException {
			int sum = 0;
			int count=0;
			Iterator<IntWritable> iterator = values.iterator();
			while(iterator.hasNext()){
				sum += iterator.next().get();
				count++;
			}
			int avg = (int)sum/count;
			context.write(key, new IntWritable(avg));//输出学生姓名和成绩平均值
		}
	}
	
	@Override
	public Configuration getConf() {
		return configuration;
	}

	@Override
	public void setConf(Configuration conf) {
		conf = new Configuration();
		configuration = conf;
	}

	@Override
	public int run(String[] args) throws Exception {
		Job job = new Job(getConf(), "AvgScore");
		job.setJarByClass(AvgSore.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		job.setMapperClass(MyMap.class);
		job.setReducerClass(MyReduce.class);
		job.setCombinerClass(MyReduce.class);
		job.setInputFormatClass(TextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);
		FileInputFormat.addInputPath(job, new Path(args[0]));//设置文件输入路径
		FileOutputFormat.setOutputPath(job, new Path(args[1]));//设置文件输出路径
		boolean success = job.waitForCompletion(true);
		
		return success ? 0:1;
	}
	
	public static void main(String[] args) throws Exception{
		//在eclipse工具上配置输入和输出参数
		int ret = ToolRunner.run(new AvgSore(), args);
		System.exit(ret);
	}
	
}