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

 1 package org.apache.hadoop.examples;
 2 
 3 import java.io.IOException;
 4 import java.util.Iterator;
 5 import java.util.StringTokenizer;
 6 import org.apache.hadoop.conf.Configuration;
 7 import org.apache.hadoop.fs.Path;
 8 import org.apache.hadoop.io.IntWritable;
 9 import org.apache.hadoop.io.Text;
10 import org.apache.hadoop.mapreduce.Job;
11 import org.apache.hadoop.mapreduce.Mapper;
12 import org.apache.hadoop.mapreduce.Reducer;
13 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
14 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
15  
16 public class calcGPA {
17     public calcGPA() {
18     }
19  
20     public static void main(String[] args) throws Exception {
21         Configuration conf = new Configuration();
22         
23         String fileAddress = "hdfs://localhost:9000/user/hadoop/";
24         
25         //String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
26         String[] otherArgs = new String[]{fileAddress+"score1.txt", fileAddress+"score2.txt", fileAddress+"score3.txt", fileAddress+"output"};
27         if(otherArgs.length < 2) {
28             System.err.println("Usage: calcGPA <in> [<in>...] <out>");
29             System.exit(2);
30         }
31  
32         Job job = Job.getInstance(conf, "calc GPA");
33         job.setJarByClass(calcGPA.class);
34         job.setMapperClass(calcGPA.TokenizerMapper.class);
35         job.setCombinerClass(calcGPA.IntSumReducer.class);
36         job.setReducerClass(calcGPA.IntSumReducer.class);
37         job.setOutputKeyClass(Text.class);
38         job.setOutputValueClass(IntWritable.class);
39  
40         for(int i = 0; i < otherArgs.length - 1; ++i) {
41             FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
42         }
43  
44         FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
45         System.exit(job.waitForCompletion(true)?0:1);
46     }
47  
48     public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
49  
50         public IntSumReducer() {
51         }
52  
53         public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
54             int sum = 0;
55             int count = 0;
56             
57             IntWritable val;
58             for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get(),count++) {
59                 val = (IntWritable)i$.next();
60             }
61             
62             
63             int average = (int)sum/count;
64             context.write(key, new IntWritable(average));
65         }
66     }
67  
68     
69     public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
70  
71         public TokenizerMapper() {
72         }
73  
74         public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
75             StringTokenizer itr = new StringTokenizer(value.toString(), "\n");
76  
77             while(itr.hasMoreTokens()) {
78                 StringTokenizer iitr = new StringTokenizer(itr.nextToken());
79                 String name = iitr.nextToken();
80                 String score = iitr.nextToken();
81                 context.write(new Text(name), new IntWritable(Integer.parseInt(score)));
82             }
83  
84         }
85     }
86 }

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。