Hadoop实例学习(十)GroupingComparator分组

---

什么是GroupingComparator分组

!!!对Reduce阶段的数据根据某一个或几个字段进行分组!!!

分组的步骤

• 自定义类继承WritableComparator
• 重写compare()方法

@Override
public int compare(WritableComparable a, WritableComparable b) {
		// 比较的业务逻辑
		return result;
}

• 创建一个构造将比较对象的类传给父类

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

解决的问题

数据类型如下:

输入数据为:

0000001	Pdt_01	222.8         
0000002	Pdt_05	722.4
0000001	Pdt_02	33.8
0000003	Pdt_06	232.8
0000003	Pdt_02	33.8
0000002	Pdt_03	522.8
0000002	Pdt_04	122.4

输出数据为:

1	222.8
2	722.4
3	232.8

基本机制

输入数据

MapTask

• 获取一行数据对其切割出每个字段并封装成bean对象
• 二次排序:先根据id1进行排序,如碰到id相同再根据金额进行降序排序
  

ReduceTask

• 辅助排序:对从map端拉取过来的数据再次进行排序,只要id相同就认为是相同的key
• reduce方法只把一组key的第一个抛出
  

实例

编写Bean类

package GroupingComparator;
import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
 * @author 公羽
 * @time : 2020/11/6 23:29
 * @File : OrderBean.java
 */
public class OrderBean implements WritableComparable<OrderBean> {
    private int orderId;
    private double price;

    public OrderBean() {
    }

    public OrderBean(int orderId, double price) {
        this.orderId = orderId;
        this.price = price;
    }

    public int getOrderId() {
        return orderId;
    }

    public void setOrderId(int orderId) {
        this.orderId = orderId;
    }

    public double getPrice() {
        return price;
    }

    public void setPrice(double price) {
        this.price = price;
    }
    //    先按照id1进行升序排序，如果相同，按照金额进行降序排序
    @Override
    public int compareTo(OrderBean o) {
        int result;
        if (orderId > o.getOrderId()) {
            result = 1;
        }else if (orderId < o.getOrderId()){
            result = -1;
        }else {
            if (price > o.getPrice()){
                result = -1;
            }else  if (price < o.getPrice()){
                result  = 1;
            }else {
                result = 0;
            }
        }
        return result;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(orderId);
        out.writeDouble(price);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        orderId = in.readInt();
        price = in.readDouble();
    }

    @Override
    public String toString() {
        return orderId + "\t" + price;
    }
}

编写Mapper类

package GroupingComparator;

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;
/**
 * @author 公羽
 * @time : 2020/11/6 23:31
 * @File : OrderMapper.java
 */
public class OrderMapper extends Mapper<LongWritable, Text,OrderBean, NullWritable> {
    private OrderBean k = new OrderBean();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//        切分一行
        String line = value.toString();

//        划分切片
        String[] splits = line.split("\t");

//        封装成为对象
        int orderId = Integer.parseInt(splits[0]);
        double price = Double.parseDouble(splits[2]);

        k.setOrderId(orderId);
        k.setPrice(price);
        context.write(k,NullWritable.get());

    }
}

编写SortGroupingComparator类

package GroupingComparator;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
/**
 * @author 公羽
 * @time : 2020/11/6 23:32
 * @File : OrderComparator.java
 */
class OrderGroupingComparator extends WritableComparator {


    public OrderGroupingComparator() {
        super(OrderBean.class, true);
    }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {
//        只要是id相同就认为是相同的key
        OrderBean aBean = (OrderBean) a;
        OrderBean bBean = (OrderBean) b;

        int result;
        if (aBean.getOrderId() > bBean.getOrderId()){
            result = 1;
        }else if (aBean.getOrderId() < bBean.getOrderId()){
            result = -1;
        }else{
            result = 0;
        }
        return result;
    }
}

编写Reducer类

package GroupingComparator;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
import java.util.Iterator;
/**
 * @author 公羽
 * @time : 2020/11/6 23:33
 * @File : OrderReducer.java
 */
public class OrderReducer extends Reducer<OrderBean, NullWritable,OrderBean,NullWritable> {
    @Override
    protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        context.write(key,NullWritable.get());
    }
}

编写Driver类

package GroupingComparator;
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 公羽
 * @time : 2020/11/6 23:36
 * @File : OrderDriver.java
 */
public class OrderDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"g:/input/GroupingComparator.txt","g:/output5"};

        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        job.setJarByClass(OrderDriver.class);

        job.setMapperClass(OrderMapper.class);
        job.setReducerClass(OrderReducer.class);

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

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

//        设置reduce端的分组
        job.setGroupingComparatorClass(OrderGroupingComparator.class);

        FileInputFormat.setInputPaths(job,new Path("E:\\hadoop\\mapreducedemo\\GroupingComparator_input"));
        FileOutputFormat.setOutputPath(job,new Path("E:\\hadoop\\mapreducedemo\\GroupingComparator_output"));

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

运行结果