hodoop中使用MapReduce实例

86 阅读 0 评论 57 点赞

我是靠谱客的博主无私煎饼，最近开发中收集的这篇文章主要介绍hodoop中使用MapReduce实例，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

网址：

1、http://hadoop.apache.org/docs/stable/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html

2、http://eric-gcm.iteye.com/blog/1807468

3、https://www.cnblogs.com/hehaiyang/p/4484442.html

4、http://hadoop.apache.org/docs/r1.0.4/cn/mapred_tutorial.html

一、类：WordCount

package com.wave;

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool{

//map
public static class StatisMapper extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one =new IntWritable(1);
private Text word =new Text();

@Override
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
StringTokenizer itr =new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}

//reduce
public static class StatisReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result =new IntWritable();

@Override
public void reduce(Text key, Iterable<IntWritable> values,Context context
) throws IOException, InterruptedException {
int sum =0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}

//客户端job的配置
@Override
public int run(String[] args)throws Exception{
Configuration conf = new Configuration();

String[] otherArgs =new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length !=2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}

Job job =new Job(conf, "word count"); //设置一个用户定义的job名称
job.setJarByClass(WordCount.class);
job.setMapperClass(StatisMapper.class); //为job设置Mapper类
job.setCombinerClass(StatisReducer.class); //为job设置Combiner类
job.setReducerClass(StatisReducer.class); //为job设置Reducer类

job.setOutputKeyClass(Text.class); //为job的输出数据设置Key类
job.setOutputValueClass(IntWritable.class); //为job输出设置value类
FileInputFormat.addInputPath(job, new Path(otherArgs[0])); //为job设置输入路径
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));//为job设置输出路径

//提交作业
return job.waitForCompletion(true) ? 0 : 1;
}

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

try {
int result = ToolRunner.run(new WordCount(), args);
System.exit(result);
} catch (Exception e) {
e.printStackTrace();
}

}
}

二、intellij IDE 配置设置输入输出目录

Program arguments: input/ output/

三、pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>

<groupId>com.wave</groupId>
<artifactId>testMapReduce</artifactId>
<version>1.0-SNAPSHOT</version>

<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<version>2.7.3</version>
</dependency>

<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.7.3</version>
</dependency>

<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.3.1</version>
<scope>provided</scope>
</dependency>

<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-common</artifactId>
<version>2.4.1</version>
</dependency>

<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-jobclient</artifactId>
<version>2.4.1</version>
</dependency>

<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-cli</artifactId>
<version>2.1.1</version>
<scope>provided</scope>
</dependency>

</dependencies>>

</project>