MapReduce基本案例

Posted 2021-11-11 ·落魄书生·

MapReduce基本案例

• 案例1. 单词统计
• 案例2.序列化重写

案例1. 单词统计

对文件里的单词进行计数

输入数据

ss ss
cls cls
jiao
banzhang
xue
hadoop

输出数据

banzhang	1
cls	2
hadoop	1
jiao	1
ss	2
xue	1

注意：包要导对，有些可能导到java包里

代码：
WordCountMapper.java

package com.lmr.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;

/**
* KEYIN, map阶段输入的key的类型：LongWritable
* VALUEIN, map阶段输入value的类型：Text
* KEYOUT, map阶段输出的Key类型：Text
* VALUEOUT, map阶段输出的value的类型：InWritable
*/

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private Text outK = new Text();
    private IntWritable outV = new IntWritable(1);

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

        //1.获取一行
        String line = value.toString();
        
        //2.切割
        String[] words = line.split(" ");

        //3.循环写出
        for (String word : words) {
            // 封装outK
            outK.set(word);

            // 写出
            context.write(outK, outV);
            // 每个单词都写入
        }
    }
}

WordCountReducer.java

package com.lmr.mapreduce.wordcount;

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

import java.io.IOException;
import java.time.temporal.Temporal;

/**
* KEYIN, reduce阶段输入的key的类型：Text
* VALUEIN, reduce阶段输入value的类型：IntWritable
* KEYOUT, reduce阶段输出的Key类型：Text
* VALUEOUT, reduce阶段输出的value的类型：InWritable
*/

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable outV = new IntWritable();

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

        //写出
        context.write(key, outV);
    }
}

驱动函数 WordCountDriver.java

package com.lmr.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, InterruptedException, ClassNotFoundException {

        // 1 获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        // 3 关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4 设置map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 设置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\\\Deskdop\\\\hadoop数据\\\\input\\\\input1"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\\\Deskdop\\\\hadoop数据\\\\output\\\\output1"));

        // 7 提交job
        boolean result = job.waitForCompletion(true);

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

案例2.序列化重写

对文件里的每一个手机号码（存在相同手机号）上行，下行流量进行统计，统计出总上行流量，总下行流量，总流量（上行加下行）

自定义bean对象实现序列化接口（Writable）在企业开发中往往常用的基本序列化类型不能满足所有需求，比如在Hadoop框架内部传递一个bean对象，那么该对象就需要实现序列化接口。
具体实现bean对象序列化步骤如下7步。
（1）必须实现Writable接口
（2）反序列化时，需要反射调用空参构造函数，所以必须有空参构造

public FlowBean() {
    super();
}

（3）重写序列化方法

@Override
public void write(DataOutput out) throws IOException {
    out.writeLong(upFlow);
    out.writeLong(downFlow);
    out.writeLong(sumFlow);
}

（4）重写反序列化方法

@Override
public void readFields(DataInput in) throws IOException {
    upFlow = in.readLong();
    downFlow = in.readLong();
    sumFlow = in.readLong();
}

（5）注意反序列化的顺序和序列化的顺序完全一致
（6）要想把结果显示在文件中，需要重写toString()，可用"\\t"分开，方便后续用。
（7）如果需要将自定义的bean放在key中传输，则还需要实现Comparable接口，因为MapReduce框中的Shuffle过程要求对key必须能排序。详见后面排序案例。

@Override
public int compareTo(FlowBean o) {
    // 倒序排列，从大到小
    return this.sumFlow > o.getSumFlow() ? -1 : 1;
}

输入数据

1	13736230513	192.196.100.1	www.atguigu.com	2481	24681	200
2	13846544121	192.196.100.2			264	0	200
3 	13956435636	192.196.100.3			132	1512	200
4 	13966251146	192.168.100.1			240	0	404
5 	18271575951	192.168.100.2	www.atguigu.com	1527	2106	200
6 	84188413	192.168.100.3	www.atguigu.com	4116	1432	200
7 	13590439668	192.168.100.4			1116	954	200
8 	15910133277	192.168.100.5	www.hao123.com	3156	2936	200
9 	13729199489	192.168.100.6			240	0	200
10 	13630577991	192.168.100.7	www.shouhu.com	6960	690	200
11 	15043685818	192.168.100.8	www.baidu.com	3659	3538	200
12 	15959002129	192.168.100.9	www.atguigu.com	1938	180	500
13 	13560439638	192.168.100.10			918	4938	200
14 	13470253144	192.168.100.11			180	180	200
15 	13682846555	192.168.100.12	www.qq.com	1938	2910	200
16 	13992314666	192.168.100.13	www.gaga.com	3008	3720	200
17 	13509468723	192.168.100.14	www.qinghua.com	7335	110349	404
18 	18390173782	192.168.100.15	www.sogou.com	9531	2412	200
19 	13975057813	192.168.100.16	www.baidu.com	11058	48243	200
20 	13768778790	192.168.100.17			120	120	200
21 	13568436656	192.168.100.18	www.alibaba.com	2481	24681	200
22 	13568436656	192.168.100.19			1116	954	200

输出数据

13470253144	180	180	360
13509468723	7335	110349	117684
13560439638	918	4938	5856
13568436656	3597	25635	29232
13590439668	1116	954	2070
13630577991	6960	690	7650
13682846555	1938	2910	4848
13729199489	240	0	240
13736230513	2481	24681	27162
13768778790	120	120	240
13846544121	264	0	264
13956435636	132	1512	1644
13966251146	240	0	240
13975057813	11058	48243	59301
13992314666	3008	3720	6728
15043685818	3659	3538	7197
15910133277	3156	2936	6092
15959002129	1938	180	2118
18271575951	1527	2106	3633
18390173782	9531	2412	11943
84188413	4116	1432	5548

重写了一个序列化FlowBean用于输出的类型，
相对于案例1，把输出类型改为自己的，在Driver代码里

把Mapper输出的value类型

job.setMapOutputValueClass(IntWritable.class)
改为
job.setMapOutputValueClass(FlowBean.class)，
把最终输出的value类型
job.sebOutputValueClass(IntWritable.class)
改为
job.sebOutputValueClass(FlowBean.class)

还有map代码的输出类型和reduce代码的输入输出类型也要改

为什么要重写序列化？
个人觉得想要自定义最终的输出

代码：
//FlowBean.java
//重写序列化，类型跟IntWritable.class一样，ctrl加鼠标左键点击进去查看继承关系

package com.lmr.mapreduce.writable;

import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/**
* 1.定义类实现writable接口
* 2.重写序列化和反序列化方法
* 3.重写空参构造
* 4.toString方法
*/

public class FlowBean implements Writable {
    private long upFlow; // 上行流量
    private long downFlow; // 下行流量
    private long sumFlow; // 总流量

    //空参构造
    public FlowBean() {
    }

    public long getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(long upFlow) {
        this.upFlow = upFlow;
    }

    public long getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(long downFlow) {
        this.downFlow = downFlow;
    }

    public long getSumFlow() {
        return sumFlow;
    }

    public void setSumFlow(long sumFlow) {
        this.sumFlow = sumFlow;
    }

    public void setSumFlow() {
        this.sumFlow = this.upFlow + this.downFlow;
    }

    @Override
    public void write(DataOutput output) throws IOException {
        output.writeLong(upFlow);
        output.writeLong(downFlow);
        output.writeLong(sumFlow);
    }

    @Override
    public void readFields(DataInput input) throws IOException {
        this.upFlow = input.readLong();
        this.downFlow = input.readLong();
        this.sumFlow = input.readLong();
    }

    @Override
    public String toString() {
        return upFlow + "\\t" + downFlow + "\\t" + sumFlow;
    }
}

FlowMapper.java

package com.lmr.mapreduce.writable;

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

import java.io.IOException;

public class FlowMapper extends Mapper<LongWritable, Text, Text, FlowBean> {

    private Text outK = new Text();
    private FlowBean outV = new FlowBean();

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

        // 1. 获取一行
        String line = value.toString();

        // 2. 切割
        String[] split = line.split("\\t");

        // 3. 抓取想要的数据
        String phone = split[1];
        String up = split[split.length - 3];
        String down = split[split.length - 2];

        // 4. 封装
        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));
        outV.setDownFlow(Long.parseLong(down));
        outV.setSumFlow();
        //这里把值set进去，在reduce里get出来

        // 5. 写出
        context.write(outK, outV);
    }
}

FlowReducer.java

package com.lmr.mapreduce.writable;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;

public class FlowReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
    private FlowBean outV = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {

        // 1. 遍历集合累加值
        long totalUp = 0;
        long totalDown = 0;
        for (FlowBean value : values) {
            totalUp += value.getUpFlow();
            totalDown += value.getDownFlow();
        }

        // 2. 封装outK, outV
        outV.setUpFlow(totalUp);
        outV.setDownFlow(totalDown);
        outV.setSumFlow();

        // 3. 写出outK outV
        context.write(key, outV);
    }
}

FlowDriver.java

package com.lmr.mapreduce.writable;

import com.lmr.mapreduce.wordcount.WordCountMapper;
import orgHadoop框架：MapReduce基本原理和入门案例

 mapreduce 统计PV案例
 Hadoop学习之运行官方案例
 MapReduce程序之序列化原理与Writable案例
 大数据之Hadoop(MapReduce)：MapReduce扩展案例
 MapReduce案例二：好友推荐