MR 分组 案例

一、需求分析

1、需求

a、输入文件

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

b、期望输出文件

1    222.8
2    722.4
3    232.8

注意：输出每个ID的价格最大值

2、分析

a、二次排序，ID 价格

b、排序必须要设置成Key

c、自定义Hadoop序列化

d、使用分组

二、代码

1、自定义Hadoop序列化

package com.group;

import org.apache.hadoop.io.WritableComparable;

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

public class GroupBean implements WritableComparable<GroupBean> {
    private int orderID;
    private double price;

    public GroupBean() {
    }

    public GroupBean(int orderID, double price) {
        this.orderID = orderID;
        this.price = price;
    }

    // 比较, 二次排序
    public int compareTo(GroupBean bean) {
        int result;
        if (this.orderID > bean.getOrderID()){
            result = 1;
        }else if (this.orderID < bean.getOrderID()){
            result = -1;
        }else {
            if (this.price > bean.getPrice()){
                result = -1;
            }else if (this.price < bean.getPrice()){
                result = 1;
            }else {
                result = 0;
            }
        }
        return result;
    }

    // 序列化
    public void write(DataOutput out) throws IOException {
        out.writeInt(orderID);
        out.writeDouble(price);
    }

    // 反序列化
    public void readFields(DataInput in) throws IOException {
        this.orderID =  in.readInt();
        this.price = in.readDouble();
    }

    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;
    }

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

2、Mapper

package com.group;

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 GroupMapper extends Mapper<LongWritable, Text, GroupBean, NullWritable> {
    GroupBean k = new GroupBean();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 1. 读取一行
        String line = value.toString();
        // 2.切割
        String[] fields = line.split("\t");
        // 3.设置 key
        k.setOrderID(Integer.parseInt(fields[0]));
        k.setPrice(Double.parseDouble(fields[2]));
        // 4.写入
        context.write(k, NullWritable.get());
    }
}

3、分组

package com.group;

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

public class GroupCompare extends WritableComparator {

    // 1.创建一个构造将比较对象的类传给父类
    public GroupCompare() {
        super(GroupBean.class, true);
    }

    // 2.核心逻辑
    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        int result;
        GroupBean aBean = (GroupBean) a;
        GroupBean bBean = (GroupBean) b;
        if (aBean.getOrderID() > bBean.getOrderID()){
            result = 1;
        }else if (aBean.getOrderID() < bBean.getOrderID()){
            result = -1;
        }else {
            result = 0;
        }
        return result;
    }
}

4、Reducer

package com.group;

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

import java.io.IOException;

public class GroupReducer extends Reducer<GroupBean, NullWritable,GroupBean, NullWritable> {
    @Override
    protected void reduce(GroupBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        // 1. 写入
        context.write(key,  NullWritable.get());
    }
}

5、Driver

package com.group;

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 GroupDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"E:\\a\\input\\GroupingComparator.txt", "E:\\a\\output"};
        // 1.job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        // 2.设置jar
        job.setJarByClass(GroupDriver.class);
        // 3.关联mapper和reducer
        job.setMapperClass(GroupMapper.class);
        job.setReducerClass(GroupReducer.class);
        // 4.设置 mapper 输出 的 kv
        job.setMapOutputKeyClass(GroupBean.class);
        job.setOutputValueClass(NullWritable.class);
        // 5.设置结果输出 的 kv
        job.setOutputKeyClass(GroupBean.class);
        job.setOutputValueClass(NullWritable.class);
        // 8.设置Group驱动
        job.setGroupingComparatorClass(GroupCompare.class);
        // 6.设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        // 7.提交任务
        boolean wait = job.waitForCompletion(true);
        System.exit(wait? 0: 1);
    }
}