MapReduce编程：平均成绩

 问题描述

现在有三个文件分别代表学生的各科成绩，编程求各位同学的平均成绩。

                   

 

编程思想

map函数将姓名作为key，成绩作为value输出，reduce根据key即可将三门成绩相加。

 

代码

package org.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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class calcGPA {
    public calcGPA() {
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();

        String fileAddress = "hdfs://localhost:9000/user/hadoop/";

        //String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
        String[] otherArgs = new String[]{fileAddress+"score1.txt", fileAddress+"score2.txt", fileAddress+"score3.txt", fileAddress+"output"};
        if(otherArgs.length < 2) {
            System.err.println("Usage: calcGPA <in> [<in>...] <out>");
            System.exit(2);
        }

        Job job = Job.getInstance(conf, "calc GPA");
        job.setJarByClass(calcGPA.class);
        job.setMapperClass(calcGPA.TokenizerMapper.class);
        job.setCombinerClass(calcGPA.IntSumReducer.class);
        job.setReducerClass(calcGPA.IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        for(int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }

        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true)?0:1);
    }

    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

        public IntSumReducer() {
        }

        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            int count = 0;

            IntWritable val;
            for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get(),count++) {
                val = (IntWritable)i$.next();
            }


            int average = (int)sum/count;
            context.write(key, new IntWritable(average));
        }
    }


    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

        public TokenizerMapper() {
        }

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString(), "\n");

            while(itr.hasMoreTokens()) {
                StringTokenizer iitr = new StringTokenizer(itr.nextToken());
                String name = iitr.nextToken();
                String score = iitr.nextToken();
                context.write(new Text(name), new IntWritable(Integer.parseInt(score)));
            }

        }
    }
}

 

疑问

在写这个的时候，我遇到个问题，就是输入输出文件的默认地址，为什么是user/hadoop/，我看了一下配置文件的信息，好像也没有出现过这个地址啊，希望有人能解答一下，万分感谢。