MapReduce中词频统计简单实现

输入数据

test1
test2 test2
test3 test3 test3
test5 test5 test4
test5 test5 test4 test5
test4 test4

Maven必须配置

注意：Windos本地运行需要确定本地有Hadoop依赖并确保和Pom配置文件中版本一致，WordCountDriver中第6点输入输出需要自行修改

<?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.test2</groupId>
    <artifactId>mapredceDemo1</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <!-- Hadoop 本地客户端 -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.0.1</version>
        </dependency>
        <!-- 测试相关组件 -->
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <!-- 日志打印组件 -->
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.30</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <!-- maven 打包插件 -->
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <!-- maven 打包插件-附带依赖打包 -->
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

resources目录下log4j.properties 配置

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

自定义Mapper类实现(WordCountMapper)

package com.atguigu.mapreduce.wordcount;

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> {

    // 定义一个Text对象，封装数据
    private Text k = new Text();
    // 定义一个IntWritable对象，直接封装1为值
    private IntWritable v = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 1. 读取每一行
        String line = value.toString();
        // 2. 字符串切割
        String[] words = line.split(" ");
        // 3. 循环设置并输出
        for (String word : words) {
            k.set(word);
            context.write(k, v);
        }
    }
}

 自定义Reducer类实现(WordCountReducer)

package com.test.mapreduce.wordcount;

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> {

    // 定义变量统计词频
    int sum;
    // 定义一个IntWritable对象，以便封装数据
    IntWritable v = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        // 1. 初始化词频
        sum = 0;
        // 2. 统计词频
        for (IntWritable count : values) sum += count.get();
        // 3. 封装value
        v.set(sum);
        // 4. 输出
        context.write(key, v);
    }
}

自定义Driver类实现(WordCountDriver)

package com.atguigu.mapreduce.wordcount;

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;

import java.io.IOException;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 1.创建配置信息Configuration对象并获取Job单例对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2.设置关联本Driver程序的jar
        job.setJarByClass(WordCountDriver.class);

        // 3.设置关联Mapper和Reducer的jar
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4.设置Mapper输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5. 设置最终输出的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6.设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 7.提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

Linux集群环境下运行命令（代码打包后改名为wc.jar）：

hadoop jar wc.jar com.atguigu.mapreduce.wordcount.WordCountDriver /input /output

输出数据

test1 1
test2 2
test3 3
test4 4
test5 5