GroupingComparator分组排序

目录

分组排序步骤：

需求：

需求分析：

代码实现：

---

对Reduce阶段的数据根据某一个或几个字段进行分组。

分组排序步骤：

（1）自定义类继承WritableComparator

（2）重写compare()方法

@Override

public int compare(WritableComparable a, WritableComparable b) {

      // 比较的业务逻辑

      return result;

}

（3）创建一个构造将比较对象的类传给父类

protected OrderGroupingComparator() {

      super(OrderBean.class, true);

}

需求：

现在需要求出每一个订单中最贵的商

订单id	商品id	成交金额
0000001	Pdt_01	222.8
	Pdt_02	33.8
0000002	Pdt_03	522.8
	Pdt_04	122.4
	Pdt_05	722.4
0000003	Pdt_06	232.8
	Pdt_02	33.8

输入数据：

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

期望输出数据：

1	222.8
2	722.4
3	232.8

需求分析：

代码实现：

package com.isea.order;

import org.apache.hadoop.io.WritableComparable;

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

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id进行升序排序，如果相同，按照价格进行降序排序
    @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;
    }

}

package com.isea.order;

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;

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");
//0000001	Pdt_01	222.8
//        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());

    }
}

package com.isea.order;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

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());
    }
}

package com.isea.order;

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;

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(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

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

package com.isea.order;

import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;

public 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;
    }
}

运行结果如下：

我们进一步的需求是，输出top2：只需要将Reducer处的代码更为：

package com.isea.order;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class OrderReducer extends Reducer<OrderBean, NullWritable,OrderBean,NullWritable> {
    @Override
    protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        for (int i = 0; i < 2; i++) {
            context.write(key,NullWritable.get());
        }
    }
}

输出的结果为： 

1	222.8
1	222.8
2	722.4
2	722.4
3	232.8
3	232.8