MapReduce实现单词计数(含分区和Combiner)

数智侠

已于 2024-08-08 17:05:54 修改

阅读量205

点赞数 7

分类专栏： Hadoop生态文章标签： mapreduce 大数据 hadoop

于 2024-07-26 09:14:48 首次发布

本文链接：https://blog.csdn.net/taogumo/article/details/140705403

版权

Hadoop生态专栏收录该内容

57 篇文章 0 订阅

订阅专栏

一、创建项目工程

二、添加pom.xml依赖

<?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.soft863</groupId>
    <artifactId>mrdemo</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <hadoop.version>3.2.0</hadoop.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.10</version>
            <!--<scope>test</scope>-->
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.6.4</version>
        </dependency>

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

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

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

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

</project>

三、创建包

创建com.soft863包，并在包下面创建以下几个类

WordCountMapper

package com.soft863;

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

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 {
        System.out.println("key:"+key.toString());
       System.out.println("value:"+value.toString());
        String line = value.toString();
        String[] words = line.split(" ");
        for(String word:words){
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

WordCountReducer

package com.soft863;

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

import java.io.IOException;

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;
        for(IntWritable value:values){
            count+=value.get();
        }
        context.write(key,new IntWritable(count));
    }
}

WordCountPatitioner

package com.soft863;

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

public class WordCountPatitioner extends Partitioner<Text, IntWritable> {
    public int getPartition(Text text, IntWritable intWritable, int numPartitions) {
        if(text.toString().startsWith("h")){
            return 1;
        }
        return 0;
    }
}

WordCountCombiner

package com.soft863;

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

import java.io.IOException;

public class WordCountCombiner extends Reducer<Text, IntWritable,Text,IntWritable> {

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
       int count=0;
       for(IntWritable value:values){
           count+=value.get();
       }
       context.write(key,new IntWritable(count));
    }
}

WordCountDriver

package com.soft863;

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.io.IOException;


public class WordCountDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://hadoop100:9000");
        Job job = Job.getInstance(conf);

        //重要：指定本job所在的jar包
        job.setJarByClass(WordCountDriver.class);
        //设置wordCountJob所用的mapper逻辑类为哪个类
        job.setMapperClass(WordCountMapper.class);
        //设置wordCountJob所用的reducer逻辑类为哪个类
        job.setReducerClass(WordCountReducer.class);

        //设置map阶段输出的kv数据类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置最终输出的kv数据类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置要处理的文本数据所存放的路径
        Path sourceFile = new Path(args[0]);
        Path targetFile = new Path(args[1]);
        FileInputFormat.setInputPaths(job, sourceFile);
        FileOutputFormat.setOutputPath(job, targetFile);

        job.setPartitionerClass(WordCountPatitioner.class);
        job.setNumReduceTasks(2);

        job.setCombinerClass(WordCountCombiner.class);
        //WordCountCombiner与WordCountReducer代码相同，可以直接复用
        // wordCountJob.setCombinerClass(WordCountReducer.class);

        // 获取文件系统
        FileSystem fs = FileSystem.get(conf);
        //输出路径文件夹不能存在，如果存在则发生错误，所以在此先进行删除
        if (fs.exists(targetFile)) {
            fs.delete(targetFile, true);
        }

        //提交job给hadoop集群
        boolean success = job.waitForCompletion(true);
        System.exit(success ? 0 : 1);
    }
}

四、添加log4j.properties文件

在resources资源文件夹下创建log4j.properties（可选项，为了输出过程日志）

log4j.rootLogger=INFO, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=target/spring.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

五、执行程序

打开Edit Configurations，配置参数路径

hdfs://hadoop100:9000//bigdata/EnglishPaper.txt hdfs://hadoop100:9000/result1

点击执行，查看结果

项目打包

六、jar包提交到集群

将jar包上传至Linux系统/usr/local/app/目录下

集群运行MR

cd /usr/local/app/
hadoop jar mrdemo-1.0-SNAPSHOT.jar com.soft863.WordCountDriver hdfs://hadoop100:9000//bigdata/EnglishPaper.txt hdfs://hadoop100:9000/result1