Map And Reduce Join的使用案例

未来影子

已于 2022-07-03 17:20:11 修改

阅读量357

点赞数

分类专栏： hadoop 文章标签： hadoop big data mapreduce

于 2022-01-16 16:03:52 首次发布

本文链接：https://blog.csdn.net/mynameisgt/article/details/122524324

版权

hadoop 专栏收录该内容

23 篇文章 0 订阅

订阅专栏

文章目录

Reduce Join

Map端的主要工作：为来自不同表或文件的key/value对，打标签以区别不同来源的记录，然后用连接字段作为key，其余部分和新加的标志作为value，最后进行输出。
Reduce端的主要工作：在Reduce端以链接字段作为key的分组已经完成，我们只需要在每一个分组中将那些来源于不同文件的记录（在Map阶段已经打上标志了）分开，最后进行合并就ok了

1)需求

$[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-cd8OWYxx-1642320134070)(C:\Users\Admin\AppData\Roaming\Typora\typora-user-images\image-20220116150837883.png)]$

$[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-jP5FtrkS-1642320134072)(C:\Users\Admin\AppData\Roaming\Typora\typora-user-images\image-20220116150900471.png)]$

2)需求分析

$[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-4QU2aJJ2-1642320134072)(C:\Users\Admin\AppData\Roaming\Typora\typora-user-images\image-20220116151106176.png)]$

3)编程实现

1.创建Bean类

package com.yingzi.mapreduce.reduceJoin;

import org.apache.hadoop.io.Writable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/**
 * @author 影子
 * @create 2022-01-15-12:45
 **/
public class TableBean implements Writable {

    private String id;  //订单id
    private String pid; //产品id
    private int amount;  //产品数量
    private String pname;   //产品名称
    private String flag;    //判断是order表还是pd表的标志字段

    public TableBean() {
    }

    public String getId() {
        return id;
    }

    public void setId(String id) {
        this.id = id;
    }

    public String getPid() {
        return pid;
    }

    public void setPid(String pid) {
        this.pid = pid;
    }

    public int getAmount() {
        return amount;
    }

    public void setAmount(int amount) {
        this.amount = amount;
    }

    public String getPname() {
        return pname;
    }

    public void setPname(String pname) {
        this.pname = pname;
    }

    public String getFlag() {
        return flag;
    }

    public void setFlag(String flag) {
        this.flag = flag;
    }

    @Override
    public String toString() {
        return id + "\t" + pname + "\t" + amount;
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(id);
        dataOutput.writeUTF(pid);
        dataOutput.writeInt(amount);
        dataOutput.writeUTF(pname);
        dataOutput.writeUTF(flag);

    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.id = dataInput.readUTF();
        this.pid = dataInput.readUTF();
        this.amount = dataInput.readInt();
        this.pname = dataInput.readUTF();
        this.flag = dataInput.readUTF();

    }
}

2.创建Mapper类

package com.yingzi.mapreduce.reduceJoin;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;

/**
 * @author 影子
 * @create 2022-01-15-12:54
 **/
public class TableMapper extends Mapper<LongWritable, Text,Text,TableBean> {

    private String filename;
    private Text outK= new Text();
    private TableBean outV = new TableBean();

    @Override
    protected void setup(Mapper<LongWritable, Text, Text, TableBean>.Context context) throws IOException, InterruptedException {
        //获取对应文件名称
        InputSplit split = context.getInputSplit();
        FileSplit fileSplit = (FileSplit) split; //向下强转
        filename = fileSplit.getPath().getName();
    }

    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, TableBean>.Context context) throws IOException, InterruptedException {

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

        //判断是哪个文件
        if (filename.contains("order")){//订单表的处理
            String[] split = line.split("\t");;
            //封装outK,outV
            outK.set(split[1]);
            outV.setId(split[0]);
            outV.setPid(split[1]);
            outV.setAmount(Integer.parseInt(split[2]));
            outV.setPname("");
            outV.setFlag("order");

        }else{//商品表的处理
            String[] split = line.split("\t");
            //封装outk,outV
            outK.set(split[0]);
            outV.setId("");
            outV.setPid(split[0]);
            outV.setAmount(0);
            outV.setPname(split[1]);
            outV.setFlag("pd");
        }
        //写出outK,outV
        context.write(outK,outV);
    }
}

3.创建Reducer类

package com.yingzi.mapreduce.reduceJoin;

import org.apache.commons.beanutils.BeanUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.lang.reflect.InvocationTargetException;
import java.util.ArrayList;

/**
 * @author 影子
 * @create 2022-01-15-13:23
 **/
public class TableReducer extends Reducer<Text,TableBean,TableBean, NullWritable> {

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

        ArrayList<TableBean> orderBeans = new ArrayList<>();
        TableBean pdBean = new TableBean();

        for (TableBean value : values) {

            //判断数据来自哪个表
            if("order".equals(value.getFlag())){//订单表

                //创建一个临时TableBean对象接收value
                TableBean tmpOrderBean = new TableBean();

                try {
                    BeanUtils.copyProperties(tmpOrderBean,value);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }
                orderBeans.add(tmpOrderBean);
            }else {//商品表
                try {
                    BeanUtils.copyProperties(pdBean,value);
                } catch (IllegalAccessException e) {
                    e.printStackTrace();
                } catch (InvocationTargetException e) {
                    e.printStackTrace();
                }
            }
        }
        //循环遍历orderBeans,替换掉每个orderBean的pid为pname,然后写出
        for (TableBean orderBean : orderBeans) {
            orderBean.setPname(pdBean.getPname());

            //写出修改后的orderBean对象
            context.write(orderBean,NullWritable.get());
        }
    }
}

4.创建Driver类

package com.yingzi.mapreduce.reduceJoin;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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;

/**
 * @author 影子
 * @create 2022-01-15-13:45
 **/
public class TableDriver {

    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        Job job = Job.getInstance(new Configuration());

        job.setJarByClass(TableDriver.class);
        job.setMapperClass(TableMapper.class);
        job.setReducerClass(TableReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(TableBean.class);

        job.setOutputKeyClass(TableBean.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.setInputPaths(job,new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\11_input\\inputtable"));
        FileOutputFormat.setOutputPath(job,new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\_output\\output10"));

        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

4)查看结果

$[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-1eWvNDlV-1642320134073)(C:\Users\Admin\AppData\Roaming\Typora\typora-user-images\image-20220116151445038.png)]$

5)总结

缺点：这种方式中，合并的操作是在Reduce阶段完成，Reduce端的处理压力太大，Map节点的运算负载则很低，资源利用率不高，且在Reduce阶段极易产生数据倾斜
解决方案：Map端实现数据合并

Mapper Join

(1)使用场景：Map Join适用于一张表十分小、一张表很大的场景

(2)优点：在Reduce端处理过多的表，非常容易产生数据倾斜，怎么办？
		在Map端缓存多张表，提前处理业务逻辑，这样增加Map端业务，减少Reduce端数据的压力尽可能减少数据倾斜。
		
(3)具体办法：采用DistributeCache
	a)在Mapper的setup阶段，将文件读取到缓存集合中
	b)在Driver驱动类中加载缓存
	//缓存普通文件到 Task 运行节点。
	job.addCacheFile(new URI("file:///e:/cache/pd.txt"));
	//如果是集群运行,需要设置 HDFS 路径
	job.addCacheFile(new URI("hdfs://hadoop102:8020/cache/pd.txt"));

2)需求分析

$[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-XYAZG8SI-1642320134074)(C:\Users\Admin\AppData\Roaming\Typora\typora-user-images\image-20220116152450003.png)]$

3)编程实现

1.创建Bean类：

和上例无差别

package com.yingzi.mapreduce.mapJoin;

import org.apache.hadoop.io.Writable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/**
 * @author 影子
 * @create 2022-01-15-12:45
 **/
public class TableBean implements Writable {

    private String id;  //订单id
    private String pid; //产品id
    private int amount;  //产品数量
    private String pname;   //产品名称
    private String flag;    //判断是order表还是pd表的标志字段

    public TableBean() {
    }

    public String getId() {
        return id;
    }

    public void setId(String id) {
        this.id = id;
    }

    public String getPid() {
        return pid;
    }

    public void setPid(String pid) {
        this.pid = pid;
    }

    public int getAmount() {
        return amount;
    }

    public void setAmount(int amount) {
        this.amount = amount;
    }

    public String getPname() {
        return pname;
    }

    public void setPname(String pname) {
        this.pname = pname;
    }

    public String getFlag() {
        return flag;
    }

    public void setFlag(String flag) {
        this.flag = flag;
    }

    @Override
    public String toString() {
        return id + "\t" + pname + "\t" + amount;
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(id);
        dataOutput.writeUTF(pid);
        dataOutput.writeInt(amount);
        dataOutput.writeUTF(pname);
        dataOutput.writeUTF(flag);

    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.id = dataInput.readUTF();
        this.pid = dataInput.readUTF();
        this.amount = dataInput.readInt();
        this.pname = dataInput.readUTF();
        this.flag = dataInput.readUTF();

    }
}

2.创建JoinMapper类

package com.yingzi.mapreduce.mapJoin;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URI;
import java.util.HashMap;
import java.util.Map;

/**
 * @author 影子
 * @create 2022-01-15-14:19
 **/
public class MapJoinMapper extends Mapper<LongWritable, Text,Text, NullWritable> {
    private HashMap<String, String> pdMap = new HashMap<>();
    private Text outK = new Text();

    @Override
    protected void setup(Mapper<LongWritable, Text, Text, NullWritable>.Context context) throws IOException, InterruptedException {
        //  获取缓存的文件，并把文件内容封装到pd.txt
        URI[] cacheFiles = context.getCacheFiles();
        Path path = new Path(cacheFiles[0]);

        //获取文件系统对象，并开流
        FileSystem fs = FileSystem.get(context.getConfiguration());
        FSDataInputStream fis = fs.open(path);

        //通过包装流转换为reader，方便按行读取
        BufferedReader reader = new BufferedReader(new InputStreamReader(fis, "UTF-8"));
        //逐行读取，按行处理
        String line;
        while (StringUtils.isNotEmpty(line = reader.readLine())){
            //切割
            String[] fields = line.split("\t");
            pdMap.put(fields[0],fields[1]);
        }
        //关流
        IOUtils.closeStream(reader);
    }

    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, NullWritable>.Context context) throws IOException, InterruptedException {

        //读取大表数据
        String[] fields = value.toString().split("\t");
        //通过大表每行数据的pid，去pdMap里面去除pname
        String pname = pdMap.get(fields[1]);
        //将大表每行数据的pid替换为pname
        outK.set(fields[0] + "\t" + pname + "\t" + fields[2]);
        //写出
        context.write(outK,NullWritable.get());
    }
}

3.创建JoinDriver类

package com.yingzi.mapreduce.mapJoin;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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;
import java.net.URI;
import java.net.URISyntaxException;

/**
 * @author 影子
 * @create 2022-01-15-14:06
 **/
public class MapJoinDriver {

    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException, URISyntaxException {

        //1.获取job信息
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //2.设置加载jar包路径
        job.setJarByClass(MapJoinDriver.class);
        //3.关联mapper
        job.setMapperClass(MapJoinMapper.class);
        //4.设置Map输出KV类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        //5.设置最终输出KV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        //加载缓存数据
        job.addCacheFile(new URI("file:///G:/计算机资料/大数据开发/尚硅谷大数据技术之Hadoop3.x/资料/11_input/tablecache/pd.txt"));
        //Map端Join的逻辑不需要Reduce阶段，设置reduceTask数量为0
        job.setNumReduceTasks(0);

        //6.设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\11_input\\inputtable"));
        FileOutputFormat.setOutputPath(job,new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\_output\\output13"));
        //7.提交job对象
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0:1);

    }
}

4)查看结果

在这里插入图片描述

未来影子

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
Map And Reduce Join的使用案例

文章目录Reduce Join1)需求2)需求分析3)编程实现1.创建Bean类2.创建Mapper类3.创建Reducer类4.创建Driver类4)查看结果5)总结Mapper Join2)需求分析3)编程实现1.创建Bean类：2.创建JoinMapper类3.创建JoinDriver类4)查看结果Reduce JoinMap端的主要工作：为来自不同表或文件的key/value对，打标签以区别不同来源的记录，然后用连接字段作为key，其余部分和新加的标志作为value，最后进行输出。Reduc
复制链接

扫一扫