MapReduce编程详解

MapReduce编程模型

将作业拆分为Map和Reduce两个阶段

• 准备map处理的输入数据
• Mapper处理
• Shuffle
• Reduce处理
• 结果输出
  

入门：编写MapReduce程序

编写wordcount程序

1. 编辑pom.xml，添加jar包

<dependency>
  <groupId>org.apache.hadoop</groupId>
  <artifactId>hadoop-client</artifactId>
  <version>${hadoop.version}</version>
</dependency>

2. 编写Mapper类

package com.biezhi.bigdata.hadoop.hdfs.mapreduce;

import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;

import java.io.IOException;
public class WordCountMapper extends Mapper<LongWritable,Text,Text,IntWritable>{


    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 把value对应的行数据按照指定的分隔符拆开
        String[] words = value.toString().split("\t");


        for(String word : words) {
            // (hello,1)  (world,1)
            context.write(new Text(word.toLowerCase()), new IntWritable(1));
        }
    }
}

3. 编写Reducer类

package com.biezhi.bigdata.hadoop.hdfs.mapreduce;

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

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

public class WordCountReduce 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();

        //<1,1,1>
        while (iterator.hasNext()) {
            IntWritable value = iterator.next();
            count += value.get();
        }

        context.write(key, new IntWritable(count));
    }
}

4. 编写主类，提交MR作业

package com.biezhi.bigdata.hadoop.hdfs.mapreduce;

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;

import java.net.URI;


/**
 * 使用MR统计HDFS上的文件对应的词频
 *
 * Driver: 配置Mapper，Reduce的相关属性
 *
 */
public class WordCountApp {


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

        System.setProperty("HADOOP_USER_NAME", "hadoop");

        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://192.168.2.131:8020");


        // 创建一个Job
        Job job = Job.getInstance(configuration);

        // 设置Job对应的参数: 主类
        job.setJarByClass(WordCountApp.class);

        // 设置Job对应的参数: 设置自定义的Mapper和Reducer处理类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReduce.class);

        // 设置Job对应的参数: Mapper输出key和value的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 设置Job对应的参数: Reduce输出key和value的类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 如果输出目录已经存在，则先删除
        FileSystem fileSystem = FileSystem.get(new URI("hdfs://192.168.2.131:8020"),configuration, "hadoop");
        Path outputPath = new Path("/wordcount/output");
        if(fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath,true);
        }

        // 设置Job对应的参数: Mapper输出key和value的类型：作业输入和输出的路径
        FileInputFormat.setInputPaths(job, new Path("/wordcount/input"));
        FileOutputFormat.setOutputPath(job, outputPath);

        // 提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : -1);

    }
}

进阶：实战词频统计

数据下载及源码下载