利用mapreduce统计单词出现的次数

需求描述：

利用mapreduce，统计单词出现的次数

设计思路：

代码设计：

目录结构：

 

 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.yanlong</groupId>
    <artifactId>hadoop-04</artifactId>
    <version>1.0-SNAPSHOT</version>

    <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.7.4</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-jar-plugin</artifactId>
                <version>2.4</version>
                <configuration>
                    <archive>
                        <manifest>
                            <addClasspath>true</addClasspath>
                            <classpathPrefix>lib/</classpathPrefix>
                            <mainClass>cn.itcast.mapreduce.flowsum1.WordCountRunner</mainClass>
                        </manifest>
                    </archive>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

WordCountMapper

package cn.itcast.mapreduce.flowsum1;

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

import java.io.IOException;
import java.io.Serializable;

public class WordCountMapper extends Mapper<LongWritable,Text,Text,IntWritable> implements Serializable{

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

        String line = value.toString();

        String[] words = line.split(" ");

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

 

WordCountMapperReducer

package cn.itcast.mapreduce.flowsum1;

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

import java.io.IOException;

public class WordCountMapperReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
    /**
     *
     * todo
     */
    @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));
    }
}

package cn.itcast.mapreduce.flowsum1;

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 WordCountRunner {
    public static void main(String[] args) throws Exception {
        //1.配置参数，用于指定mr运行时相关的参数属性
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "wordcount");

        //2.指定mr运行的类
        job.setJarByClass(WordCountRunner.class);

        //3.指定mr程序的m，r类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountMapperReducer.class);


        //4指定map输出kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //指定ruduce输出的kv类型，也就是mr的最终输出结果
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //指定mr程序的输出路径
        FileInputFormat.addInputPath(job,new Path("/huanhuan/input"));
        FileOutputFormat.setOutputPath(job,new Path("/wordcount/out"));

        //提交文本mr文本程序
        //job.submit();

        boolean result = job.waitForCompletion(true);//提交mr程序，并且开始任务执行监控的功能
        //如果mr程序执行成功，退出0，否则1
        System.exit(result?0:1);

    }
}

生成jar包 ：  

然后把生成的jar上传到服务器上。

hadoop集群测试

查看:

 

补充：

 

 

 

 

 

结果查看：

 

 下载查看以后看到：

 

本地测试：

修改代码：

 

准备数据：

hadoop hive allen 
itcast hadoop
hadoop

 

 

查看计算结果：