大数据学习（七）：mapreduce实现wordcount计数

maven项目pom文件配置

<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 https://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.bigdata</groupId>
  <artifactId>mapreduce</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  
  
    <name>mapreduce</name>
  <url>http://maven.apache.org</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  </properties>

  <dependencies>
	
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-client</artifactId>
			<version>2.8.1</version>
		</dependency>

	</dependencies>
  
</project>

一、在eclipse使用main方法提交给集群yarn运行mapreduce

1、计数mapper实现

package com.bigdata.mapreduce;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
/**
 * 
 *KEYIN : map task读取到得数据key的类型，是一行的起始偏移量Long
 *VALUEIN：map task读取到得数据的value的类型，是一行的内容String
 *
 *KEYOUT:是用户的自定义mapfangfa要返回的结果kv数据的key的类型，在wordcount逻辑中，我们需要返回的是单词String
 *VALUEOUT:是用户的自定义map方法要返回的结果kv数据的value的类型，在wordcount逻辑中，我们需要返回的是整体Integer
 *
 *但是，在mapreduce中，map产生的数据需要传输给reduce，需要进行序列化和反序列化，而jdk中的原生序列化机制产生的数据量比较冗余，就会导致数据在mapreduce运行过程中传输效率低下
 *所以，hadoop专门设计了自己的序列化机制，那么mapreduce中传输的数据类型必须实现hadoop自己的序列化接口
 *
 *hadoop为jdk中常用基本类型Long String Integer Float等数据类型封住了自己的实现了hadoop序列化接口的类型:LongWritable,Text,IntWritabe,FloatWritable
 */
public class WordcountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{

	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		
		//切单词
		String line = value.toString();
		String[] words = line.split(" ");
		for (String word : words) {
			context.write(new Text(word), new IntWritable(1));
		}
	}
}

2、计数reduce实现

package com.bigdata.mapreduce;

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

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordcountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
	
	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,
			Context context) throws IOException, InterruptedException {
		int count = 0;
		Iterator<IntWritable> iterator = values.iterator();
		while(iterator.hasNext()) {
			IntWritable value = iterator.next();
			count += value.get();
		}
		
		context.write(key, new IntWritable(count));
		
	}

}

3、运行方法

package com.bigdata.mapreduce;

import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;


/**
 * 用于提交mapreduce job的客户端程序
 * 功能:
 * 		1、封装本次job运行时所需要的必须参数
 * 		2、跟yarn进行交互将mapreduce程序成功的启动、运行
 * @author 90669
 *
 */
public class JobSubmitter {
	
	
public static void main(String[] args) throws Exception {
		
		// 在代码中设置JVM系统参数，用于给job对象来获取访问HDFS的用户身份
		System.setProperty("HADOOP_USER_NAME", "root");
		
		
		Configuration conf = new Configuration();
		// 1、设置job运行时要访问的默认文件系统
		conf.set("fs.defaultFS", "hdfs://spark1:9000");
		// 2、设置job提交到哪去运行
		conf.set("mapreduce.framework.name", "yarn");
		conf.set("yarn.resourcemanager.hostname", "spark1");
		// 3、如果要从windows系统上运行这个job提交客户端程序，则需要加这个跨平台提交的参数
		conf.set("mapreduce.app-submission.cross-platform","true");
		
		Job job = Job.getInstance(conf);
		
		// 1、封装参数：jar包所在的位置
		job.setJar("d:/wc.jar");
		//job.setJarByClass(JobSubmitter.class);
		
		// 2、封装参数： 本次job所要调用的Mapper实现类、Reducer实现类
		job.setMapperClass(WordcountMapper.class);
		job.setReducerClass(WordcountReducer.class);
		
		// 3、封装参数：本次job的Mapper实现类、Reducer实现类产生的结果数据的key、value类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		
		
		Path output = new Path("/wordcount/output");
		FileSystem fs = FileSystem.get(new URI("hdfs://spark1:9000"),conf,"root");
		if(fs.exists(output)){
			fs.delete(output, true);
		}
		
		// 4、封装参数：本次job要处理的输入数据集所在路径、最终结果的输出路径
		FileInputFormat.setInputPaths(job, new Path("/wordcount/input"));
		FileOutputFormat.setOutputPath(job, output);  // 注意：输出路径必须不存在
		
		
		// 5、封装参数：想要启动的reduce task的数量
		job.setNumReduceTasks(2);
		
		// 6、提交job给yarn
		boolean res = job.waitForCompletion(true);
		
		System.exit(res?0:-1);
		
	}
}

4、注意事项

需要将项目打成jar包并重名为wc.jar放在D盘

二、在linux服务器上运行mapreduce计数程序

1、mapper实现和reduce实现不变，只需要修改运行方法即可

package com.bigdata.mapreduce;

import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;



public class JobSubmitter2 {
	
	
public static void main(String[] args) throws Exception {
		
		
		
		Configuration conf = new Configuration();

		
		Job job = Job.getInstance(conf);
		
		
		job.setJarByClass(JobSubmitter2.class);
		
		// 2、封装参数： 本次job所要调用的Mapper实现类、Reducer实现类
		job.setMapperClass(WordcountMapper.class);
		job.setReducerClass(WordcountReducer.class);
		
		// 3、封装参数：本次job的Mapper实现类、Reducer实现类产生的结果数据的key、value类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		
		
	
		// 4、封装参数：本次job要处理的输入数据集所在路径、最终结果的输出路径
		FileInputFormat.setInputPaths(job, new Path("/wordcount/input"));
		FileOutputFormat.setOutputPath(job, new Path("/wordcount/output"));
		
		
		// 5、封装参数：想要启动的reduce task的数量
		job.setNumReduceTasks(3);
		
		// 6、提交job给yarn
		boolean res = job.waitForCompletion(true);
		
		System.exit(res?0:-1);
		
	}

}

2、将项目打成jar包，并上传至linux服务器上

将项目进行打包，并通winscp将jar包上传至/usr/local目录

3、使用hadoop jar命令运行程序

hadoop jar jar包名称 运行方法全路径

hadoop jar mapreduce24-0.0.1-SNAPSHOT.jar com.bigdata.mapreduce.JobSubmitter2

运行成功：

三、在windows本地运行mapreduce程序

package com.bigdata.mapreduce;

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

public class JobSubmitterWindowsToLocal {

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

		conf.set("fs.defaultFS", "file:///");
		conf.set("mapreduce.framework.name", "local");

		Job job = Job.getInstance(conf);
		
		job.setJarByClass(JobSubmitterWindowsToLocal.class);
		
		job.setMapperClass(WordcountMapper.class);
		job.setReducerClass(WordcountReducer.class);
		
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		FileInputFormat.setInputPaths(job, new Path("D:/mrdata/wordcount/input"));
		FileOutputFormat.setOutputPath(job, new Path("D:/mrdata/wordcount/output"));
		
		job.setNumReduceTasks(3);
		
		boolean res = job.waitForCompletion(true);
		System.exit(res?0:1);
		
	}
}