MapReduce快速入门系列(13) | MapReduce之reduce端join与map端join算法实现

2020-10-28 15:25:42 浏览数 (1)

本片博文博主为大家讲解MapReduce之Join的多种应用。

一. Reduce Join

1.1 Reduce Join 工作原理

  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val，最后进行输出。

  Reduce端的主要工作：在Reduce端以连接字段作为key的分组已经完成，我们只需要在每一个分组当中将那些来源于不同文件的记录(在Mao阶段已经打标志)分开，最后进行合并就ok了。

1.2 Reduce Join 案例

1. 需求

将商品信息表中数据根据商品pid合并到订单数据表中。 最终形式如下表：

id

pname

amount

1001

小米

1

1004

小米

4

1002

华为

2

1005

华为

5

1003

格力

3

1006

格力

6

2. 需求分析

  通过将关联条件作为Map输出的key，将两表满足Join条件的数据并携带数据所来源的文件信息，发往同一个ReduceTask，在Reduce中进行数据的串联，如下图所示。

3. 完成代码

  • 1. 创建商品和订合并后的OrderBean类
代码语言：javascript复制
package com.buwenbuhuo.reducejoin;

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
 * @author 卜温不火
 * @create 2020-04-25 17:24
 * com.buwenbuhuo.reducejoin - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class OrderBean implements WritableComparable<OrderBean> {
    private String id;
    private String pid;
    private int amount;
    private String pname;

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

    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;
    }

    @Override
    public int compareTo(OrderBean o) {
        int compare = this.pid.compareTo(o.pid);

        if (compare == 0) {
            return o.pname.compareTo(this.pname);
        } else {
            return compare;
        }
    }

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

    @Override
    public void readFields(DataInput in) throws IOException {
        this.id = in.readUTF();
        this.pid = in.readUTF();
        this.amount = in.readInt();
        this.pname = in.readUTF();
    }
}
  • 2. 编写RJMapper类
代码语言：javascript复制
package com.buwenbuhuo.reducejoin;

import com.buwenbuhuo.reducejoin.OrderBean;
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 org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;
/**
 * @author 卜温不火
 * @create 2020-04-25 17:24
 * com.buwenbuhuo.reducejoin - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class RJMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable> {

    private OrderBean orderBean = new OrderBean();

    private String filename;

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        FileSplit fs = (FileSplit) context.getInputSplit();
        filename = fs.getPath().getName();
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fields = value.toString().split("t");
        if (filename.equals("order.txt")) {
            orderBean.setId(fields[0]);
            orderBean.setPid(fields[1]);
            orderBean.setAmount(Integer.parseInt(fields[2]));
            orderBean.setPname("");
        } else {
            orderBean.setPid(fields[0]);
            orderBean.setPname(fields[1]);
            orderBean.setId("");
            orderBean.setAmount(0);
        }
        context.write(orderBean, NullWritable.get());
    }
}
  • 3. 编写RJReducer类
代码语言：javascript复制
package com.buwenbuhuo.reducejoin;

import com.buwenbuhuo.reducejoin.OrderBean;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.Iterator;
/**
 * @author 卜温不火
 * @create 2020-04-25 17:24
 * com.buwenbuhuo.reducejoin - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class RJReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable> {

    @Override
    protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        //拿到迭代器
        Iterator<NullWritable> iterator = values.iterator();
        //数据指针下移，获取第一个OrderBean
        iterator.next();
        //从第一个OrderBean中取出品牌名称
        String pname = key.getPname();

        //遍历剩下的OrderBean，设置品牌名称并写出
        while (iterator.hasNext()) {
            iterator.next();
            key.setPname(pname);
            context.write(key, NullWritable.get());
        }
    }
}
  • 4. 编写 RJComparator类(构造器)
代码语言：javascript复制
package com.buwenbuhuo.reducejoin;

import com.buwenbuhuo.reducejoin.OrderBean;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
/**
 * @author 卜温不火
 * @create 2020-04-25 17:24
 * com.buwenbuhuo.reducejoin - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class RJComparator extends WritableComparator {

    protected RJComparator() {
        super(OrderBean.class, true);
    }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        OrderBean oa = (OrderBean) a;
        OrderBean ob = (OrderBean) b;
        return oa.getPid().compareTo(ob.getPid());
    }
}
  • 5. 编写RJDriver类
代码语言：javascript复制
package com.buwenbuhuo.reducejoin;

import com.buwenbuhuo.reducejoin.OrderBean;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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 卜温不火
 * @create 2020-04-25 17:24
 * com.buwenbuhuo.reducejoin - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class RJDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Job job = Job.getInstance(new Configuration());

        job.setJarByClass(RJDriver.class);

        job.setMapperClass(RJMapper.class);
        job.setReducerClass(RJReducer.class);

        job.setMapOutputKeyClass(OrderBean.class);
        job.setMapOutputValueClass(NullWritable.class);

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

        job.setGroupingComparatorClass(RJComparator.class);

        FileInputFormat.setInputPaths(job, new Path("d:\input"));
        FileOutputFormat.setOutputPath(job, new Path("d:\output"));

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

4. 查看运行结果

  • 1. 运行
  • 2. 结果

结果正确,说明我们的reducer端的join算法算是成功实现了！！！

二. Map Join

2.1 使用场景

Map Join适用于一张表十分小、一张表很大的场景。

2.2 优点

思考：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，尽可能的减少数据倾斜。

2.3 具体办法：采用DistributedCache

  • （1）在Mapper的setup阶段，将文件读取到缓存集合中。
  • （2）在驱动函数中加载缓存。
代码语言：javascript复制
// 缓存普通文件到Task运行节点。
job.addCacheFile(new URI("file://d:/cache/pd.txt"));

2.4 Map Join案例

1. 需求

将商品信息表中数据根据商品pid合并到订单数据表中。

id

pname

amount

1001

小米

1

1004

小米

4

1002

华为

2

1005

华为

5

1003

格力

3

1006

格力

6

2. 需求分析

MapJoin适用于关联表中有小表的情形。

3. 代码实现

  • 1. 创建MJMapper类
代码语言：javascript复制
package com.buwenbuhuo.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.IOException;
import java.net.URI;
import java.util.HashMap;
import java.util.Map;
/**
 * @author 卜温不火
 * @create 2020-04-25 17:54
 * com.buwenbuhuo.mapjoin - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class MJMapper extends Mapper<LongWritable, Text, Text, NullWritable> {

    private Map<String, String> pMap = new HashMap<>();

    private Text k = new Text();

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        URI[] cacheFiles = context.getCacheFiles();
        String path = cacheFiles[0].getPath().toString();
        FileSystem fileSystem = FileSystem.get(context.getConfiguration());
        FSDataInputStream bufferedReader = fileSystem.open(new Path(path));
        String line;
        while (StringUtils.isNotEmpty(line = bufferedReader.readLine())) {
            String[] fields = line.split("t");
            pMap.put(fields[0], fields[1]);
        }
        IOUtils.closeStream(bufferedReader);
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fields = value.toString().split("t");
        String pname = pMap.get(fields[1]);
        if (pname == null) {
            pname = "NULL";
        }
        k.set(fields[0]   "t"   pname   "t"   fields[2]);
        context.write(k, NullWritable.get());
    }
}
  • 2. 创建MJDriver类
代码语言：javascript复制
package com.buwenbuhuo.mapjoin;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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;
/**
 * @author 卜温不火
 * @create 2020-04-25 17:54
 * com.buwenbuhuo.mapjoin - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class MJDriver {

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

        job.setJarByClass(MJDriver.class);

        job.setMapperClass(MJMapper.class);
        job.setNumReduceTasks(0);

        job.addCacheFile(URI.create("file:///d:/input/pd.txt"));

        FileInputFormat.setInputPaths(job, new Path("d:\input\order.txt"));
        FileOutputFormat.setOutputPath(job, new Path("d:\output"));

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

4. 运行及查看结果

  • 1. 运行
  • 2. 查看结果

结果正确,说明我们的map端的join算法算是成功实现了！！！

mapreduce 缓存

0 人点赞