1、项目名称：

2、程序代码：

package com.averagescorecount;

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.LongWritable;

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 ScoreCount {

    /*这个map的输入是经过InputFormat分解过的数据集，InputFormat的默认值是TextInputFormat，它针对文件，

    *按行将文本切割成InputSplits，并用LineRecordReader将InputSplit解析成<key,value>对，

    *key是行在文本中的位置，value是文件中的一行。

    */

    public static class Map extends Mapper<LongWritable, Text, Text , IntWritable>{

        public void map(LongWritable key , Text value , Context context ) throws IOException, InterruptedException{

            String line = value.toString();

            System.out.println("line:"+line);

            System.out.println("TokenizerMapper.map...");

            System.out.println("Map key:"+key.toString()+" Map value:"+value.toString());

            //将输入的数据首先按行进行分割

            StringTokenizer tokenizerArticle = new StringTokenizer(line,"\n");

            //分别对每一行进行处理

            while (tokenizerArticle.hasMoreTokens()) {

                //每行按空格划分

                StringTokenizer tokenizerLine = new StringTokenizer(tokenizerArticle.nextToken());

                String strName = tokenizerLine.nextToken();//学生姓名部分

                String  strScore= tokenizerLine.nextToken();//成绩部分

                Text name = new Text(strName);

                int scoreInt = Integer.parseInt(strScore);

                 System.out.println("name:"+name+"  scoreInt:"+scoreInt);

                context.write(name, new IntWritable(scoreInt));

                System.out.println("context_map:"+context.toString());

            }

             System.out.println("context_map_111:"+context.toString());

        }

    }

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

            public void reduce(Text key , Iterable<IntWritable> values,Context context) throws IOException,InterruptedException{

                int sum = 0;

                int count = 0;

                int score = 0;

                System.out.println("reducer...");

                System.out.println("Reducer key:"+key.toString()+"  Reducer values:"+values.toString());

                //设置迭代器

                Iterator<IntWritable> iterator = values.iterator();

                while (iterator.hasNext()) {

                    score = iterator.next().get();

                    System.out.println("score:"+score);

                    sum += score;

                    count++;

                }

                int average = (int) sum/count;

                System.out.println("key"+key+"   average:"+average);

                context.write(key, new IntWritable(average));

                System.out.println("context_reducer:"+context.toString());

            }

    }

    public static void main(String[] args) throws Exception {

    Configuration conf = new Configuration();

    Job job = new Job(conf, "score count");

    job.setJarByClass(ScoreCount.class);

    job.setMapperClass(Map.class);

    job.setCombinerClass(Reduce.class);

    job.setReducerClass(Reduce.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);

    }

}
 
3、测试数据：
陈洲立 67
陈东伟 90
李宁 87
杨森 86
陈东奇 78
谭果 94
盖盖 83
陈洲立 68
陈东伟 96
李宁 82
杨森 85
陈东奇 72
谭果 97
盖盖 82
陈洲立 46
陈东伟 48
李宁 67
杨森 33
陈东奇 28
谭果 78
盖盖 87
 

4、运行过程：

14/09/20 19:31:16 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
14/09/20 19:31:16 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
14/09/20 19:31:16 WARN mapred.JobClient: No job jar file set.  User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
14/09/20 19:31:16 INFO input.FileInputFormat: Total input paths to process : 1
14/09/20 19:31:16 WARN snappy.LoadSnappy: Snappy native library not loaded
14/09/20 19:31:16 INFO mapred.JobClient: Running job: job_local_0001
14/09/20 19:31:16 INFO util.ProcessTree: setsid exited with exit code 0
14/09/20 19:31:16 INFO mapred.Task:  Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@4080b02f
14/09/20 19:31:16 INFO mapred.MapTask: io.sort.mb = 100
14/09/20 19:31:16 INFO mapred.MapTask: data buffer = 79691776/99614720
14/09/20 19:31:16 INFO mapred.MapTask: record buffer = 262144/327680
line:陈洲立 67
TokenizerMapper.map...
Map key:0 Map value:陈洲立 67
name:陈洲立  scoreInt:67
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:陈东伟 90
TokenizerMapper.map...
Map key:13 Map value:陈东伟 90
name:陈东伟  scoreInt:90
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:李宁 87
TokenizerMapper.map...
Map key:26 Map value:李宁 87
name:李宁  scoreInt:87
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:杨森 86
TokenizerMapper.map...
Map key:36 Map value:杨森 86
name:杨森  scoreInt:86
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:陈东奇 78
TokenizerMapper.map...
Map key:46 Map value:陈东奇 78
name:陈东奇  scoreInt:78
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:谭果 94
TokenizerMapper.map...
Map key:59 Map value:谭果 94
name:谭果  scoreInt:94
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:盖盖 83
TokenizerMapper.map...
Map key:69 Map value:盖盖 83
name:盖盖  scoreInt:83
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:陈洲立 68
TokenizerMapper.map...
Map key:79 Map value:陈洲立 68
name:陈洲立  scoreInt:68
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:陈东伟 96
TokenizerMapper.map...
Map key:92 Map value:陈东伟 96
name:陈东伟  scoreInt:96
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:李宁 82
TokenizerMapper.map...
Map key:105 Map value:李宁 82
name:李宁  scoreInt:82
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:杨森 85
TokenizerMapper.map...
Map key:115 Map value:杨森 85
name:杨森  scoreInt:85
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:陈东奇 72
TokenizerMapper.map...
Map key:125 Map value:陈东奇 72
name:陈东奇  scoreInt:72
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:谭果 97
TokenizerMapper.map...
Map key:138 Map value:谭果 97
name:谭果  scoreInt:97
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:盖盖 82
TokenizerMapper.map...
Map key:148 Map value:盖盖 82
name:盖盖  scoreInt:82
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:陈洲立 46
TokenizerMapper.map...
Map key:158 Map value:陈洲立 46
name:陈洲立  scoreInt:46
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:陈东伟 48
TokenizerMapper.map...
Map key:171 Map value:陈东伟 48
name:陈东伟  scoreInt:48
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:李宁 67
TokenizerMapper.map...
Map key:184 Map value:李宁 67
name:李宁  scoreInt:67
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:杨森 33
TokenizerMapper.map...
Map key:194 Map value:杨森 33
name:杨森  scoreInt:33
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:陈东奇 28
TokenizerMapper.map...
Map key:204 Map value:陈东奇 28
name:陈东奇  scoreInt:28
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:谭果 78
TokenizerMapper.map...
Map key:217 Map value:谭果 78
name:谭果  scoreInt:78
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:盖盖 87
TokenizerMapper.map...
Map key:227 Map value:盖盖 87
name:盖盖  scoreInt:87
context_map:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
line:
TokenizerMapper.map...
Map key:237 Map value:
context_map_111:org.apache.hadoop.mapreduce.Mapper$Context@d4cf771
14/09/20 19:31:16 INFO mapred.MapTask: Starting flush of map output
reducer...
Reducer key:李宁  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@63dbbdf2
score:82
score:87
score:67
key李宁   average:78
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@3d32487
reducer...
Reducer key:杨森  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@63dbbdf2
score:33
score:86
score:85
key杨森   average:68
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@3d32487
reducer...
Reducer key:盖盖  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@63dbbdf2
score:87
score:83
score:82
key盖盖   average:84
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@3d32487
reducer...
Reducer key:谭果  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@63dbbdf2
score:94
score:97
score:78
key谭果   average:89
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@3d32487
reducer...
Reducer key:陈东伟  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@63dbbdf2
score:48
score:90
score:96
key陈东伟   average:78
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@3d32487
reducer...
Reducer key:陈东奇  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@63dbbdf2
score:72
score:78
score:28
key陈东奇   average:59
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@3d32487
reducer...
Reducer key:陈洲立  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@63dbbdf2
score:68
score:67
score:46
key陈洲立   average:60
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@3d32487
14/09/20 19:31:16 INFO mapred.MapTask: Finished spill 0
14/09/20 19:31:16 INFO mapred.Task: Task:attempt_local_0001_m_000000_0 is done. And is in the process of commiting
14/09/20 19:31:17 INFO mapred.JobClient:  map 0% reduce 0%
14/09/20 19:31:19 INFO mapred.LocalJobRunner:
14/09/20 19:31:19 INFO mapred.Task: Task 'attempt_local_0001_m_000000_0' done.
14/09/20 19:31:19 INFO mapred.Task:  Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@5fc24d33
14/09/20 19:31:19 INFO mapred.LocalJobRunner:
14/09/20 19:31:19 INFO mapred.Merger: Merging 1 sorted segments
14/09/20 19:31:19 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 102 bytes
14/09/20 19:31:19 INFO mapred.LocalJobRunner:
reducer...
Reducer key:李宁  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@2407325d
score:78
key李宁   average:78
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@52403ee2
reducer...
Reducer key:杨森  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@2407325d
score:68
key杨森   average:68
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@52403ee2
reducer...
Reducer key:盖盖  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@2407325d
score:84
key盖盖   average:84
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@52403ee2
reducer...
Reducer key:谭果  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@2407325d
score:89
key谭果   average:89
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@52403ee2
reducer...
Reducer key:陈东伟  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@2407325d
score:78
key陈东伟   average:78
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@52403ee2
reducer...
Reducer key:陈东奇  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@2407325d
score:59
key陈东奇   average:59
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@52403ee2
reducer...
Reducer key:陈洲立  Reducer values:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@2407325d
score:60
key陈洲立   average:60
context_reducer:org.apache.hadoop.mapreduce.Reducer$Context@52403ee2
14/09/20 19:31:19 INFO mapred.Task: Task:attempt_local_0001_r_000000_0 is done. And is in the process of commiting
14/09/20 19:31:19 INFO mapred.LocalJobRunner:
14/09/20 19:31:19 INFO mapred.Task: Task attempt_local_0001_r_000000_0 is allowed to commit now
14/09/20 19:31:19 INFO output.FileOutputCommitter: Saved output of task 'attempt_local_0001_r_000000_0' to hdfs://localhost:9000/user/hadoop/score_output
14/09/20 19:31:20 INFO mapred.JobClient:  map 100% reduce 0%
14/09/20 19:31:22 INFO mapred.LocalJobRunner: reduce > reduce
14/09/20 19:31:22 INFO mapred.Task: Task 'attempt_local_0001_r_000000_0' done.
14/09/20 19:31:23 INFO mapred.JobClient:  map 100% reduce 100%
14/09/20 19:31:23 INFO mapred.JobClient: Job complete: job_local_0001
14/09/20 19:31:23 INFO mapred.JobClient: Counters: 22
14/09/20 19:31:23 INFO mapred.JobClient:   Map-Reduce Framework
14/09/20 19:31:23 INFO mapred.JobClient:     Spilled Records=14
14/09/20 19:31:23 INFO mapred.JobClient:     Map output materialized bytes=106
14/09/20 19:31:23 INFO mapred.JobClient:     Reduce input records=7
14/09/20 19:31:23 INFO mapred.JobClient:     Virtual memory (bytes) snapshot=0
14/09/20 19:31:23 INFO mapred.JobClient:     Map input records=22
14/09/20 19:31:23 INFO mapred.JobClient:     SPLIT_RAW_BYTES=116
14/09/20 19:31:23 INFO mapred.JobClient:     Map output bytes=258
14/09/20 19:31:23 INFO mapred.JobClient:     Reduce shuffle bytes=0
14/09/20 19:31:23 INFO mapred.JobClient:     Physical memory (bytes) snapshot=0
14/09/20 19:31:23 INFO mapred.JobClient:     Reduce input groups=7
14/09/20 19:31:23 INFO mapred.JobClient:     Combine output records=7
14/09/20 19:31:23 INFO mapred.JobClient:     Reduce output records=7
14/09/20 19:31:23 INFO mapred.JobClient:     Map output records=21
14/09/20 19:31:23 INFO mapred.JobClient:     Combine input records=21
14/09/20 19:31:23 INFO mapred.JobClient:     CPU time spent (ms)=0
14/09/20 19:31:23 INFO mapred.JobClient:     Total committed heap usage (bytes)=408944640
14/09/20 19:31:23 INFO mapred.JobClient:   File Input Format Counters
14/09/20 19:31:23 INFO mapred.JobClient:     Bytes Read=238
14/09/20 19:31:23 INFO mapred.JobClient:   FileSystemCounters
14/09/20 19:31:23 INFO mapred.JobClient:     HDFS_BYTES_READ=476
14/09/20 19:31:23 INFO mapred.JobClient:     FILE_BYTES_WRITTEN=81132
14/09/20 19:31:23 INFO mapred.JobClient:     FILE_BYTES_READ=448
14/09/20 19:31:23 INFO mapred.JobClient:     HDFS_BYTES_WRITTEN=79
14/09/20 19:31:23 INFO mapred.JobClient:   File Output Format Counters
14/09/20 19:31:23 INFO mapred.JobClient:     Bytes Written=79

5、输出结果：

MapReduce编程系列 — 2：计算平均分的更多相关文章

  1. MapReduce编程系列 — 1：计算单词

    1.代码: package com.mrdemo; import java.io.IOException; import java.util.StringTokenizer; import org.a ...

  2. 【原创】MapReduce编程系列之二元排序

    普通排序实现 普通排序的实现利用了按姓名的排序,调用了默认的对key的HashPartition函数来实现数据的分组.partition操作之后写入磁盘时会对数据进行排序操作(对一个分区内的数据作排序 ...

  3. MapReduce编程系列 — 6：多表关联

    1.项目名称: 2.程序代码: 版本一(详细版): package com.mtjoin; import java.io.IOException; import java.util.Iterator; ...

  4. MapReduce编程系列 — 5：单表关联

    1.项目名称: 2.项目数据: chile    parentTom    LucyTom    JackJone    LucyJone    JackLucy    MaryLucy    Ben ...

  5. MapReduce编程系列 — 4：排序

    1.项目名称: 2.程序代码: package com.sort; import java.io.IOException; import org.apache.hadoop.conf.Configur ...

  6. MapReduce编程系列 — 3：数据去重

    1.项目名称: 2.程序代码: package com.dedup; import java.io.IOException; import org.apache.hadoop.conf.Configu ...

  7. 【原创】MapReduce编程系列之表连接

    问题描述 需要连接的表如下:其中左边是child,右边是parent,我们要做的是找出grandchild和grandparent的对应关系,为此需要进行表的连接. Tom Lucy Tom Jim ...

  8. MapReduce 编程 系列九 Reducer数目

    本篇介绍怎样控制reduce的数目.前面观察结果文件,都会发现通常是以part-r-00000 形式出现多个文件,事实上这个reducer的数目有关系.reducer数目多,结果文件数目就多. 在初始 ...

  9. MapReduce 编程 系列七 MapReduce程序日志查看

    首先,假设须要打印日志,不须要用log4j这些东西,直接用System.out.println就可以,这些输出到stdout的日志信息能够在jobtracker网站终于找到. 其次,假设在main函数 ...

随机推荐

  1. （四）Qt之右键菜单

    1.右键菜单创建和显示 作为一种交互性强.使用方便的右键菜单在程序中是非常常用的,在Qt中可以轻松的实现. QMenu menu; //添加菜单项,指定图标.名称.响应函数 menu.addActio ...

  2. Bugzilla+MySql+IIS+ActivePerl搭建指南

    头在忙着他的技术研究,对团队建设.测试管理.流程规范都不怎么理会,眼见着产品进入后期整合阶段,在测试过错中出现很多Bug,单靠着我一个人用txt来收集整理bug需求,然后整理成word,放在svn上面 ...

  3. [设计模式]Netd中的命令设计模式

    命令模式 有如下的角色: (1)调用者(invoker) (2)命令接收者(receiver) (3)客户端(client) (4)命令对象(command) public interface Com ...

  4. Git快速上手 : Tortoise工具使用

    利用工具快速上手Git 别跟我说什么用命令操作Git,多高大上呀,请不要在这里跟我装逼,就如同,有个小妞在床上眉眼诱惑地,你却TM还要先看个片儿来热热身.... TortoiseGit  名字看着眼熟 ...

  5. AJAX异步请求原理和过程

    AJAX 指异步 JavaScript 及 XML(Asynchronous JavaScript And XML),它不是一种新的编程语言,而是一种使用现有标准的新方法. AJAX 基于 JavaS ...

  6. PHP开发环境和软件

    1/很方便的软件XAMMP集成了PHP+MYSQL+MYPHPADMIN等等软件 2/sublime text 程序员神器,都明白的 ps.如果装了vm虚拟机,80端口有时候会被占用,进程关闭就好.

  7. Git之不明觉厉11－利其器source tree

    前面10篇文章都在用命令行,虽然装逼不错,但是我想说一句,平时我也是用source tree比较多点,命令行一般都是在source tree的图形按钮找不到在哪里,就直接用命令行.对于初次用git的同 ...

  8. Oracle的Import用法

    1. imp 命令介绍   imp 命令可以通过输入各种参数来控制导出方式:  imp keyword=value 或 keyword=(value1,value2,...,valueN) ,例如 i ...

  9. Java Timer, TimerTask

    参考:http://batitan.iteye.com/blog/253483 TimerTask 就是一个run 方法,里边有些操作: Timer 是个线程,按各种调度方法(Timer.schedu ...

  10. 洛谷 P1858 多人背包

    求01背包前k优解的价值和 输入输出格式 Input/output 输入格式:第一行三个数K.V.N(k<=50,v<=5000,n<=200)接下来每行两个数,表示体积和价值输出格 ...