Hadoop-9_hadoop 9-优快云博客

本文介绍了一种使用MapReduce处理订单数据的方法，旨在找出每个订单中价格最高的商品。通过自定义OrderBean类、OrderMapper、OrderReducer、OrderPartitioner和OrderGroupingComparator，实现了对订单数据的高效处理和分析。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

3.3 求每个订单中最贵的商品（GroupingComparator）

1）需求
有如下订单数据
在这里插入图片描述
2）输入数据

Order_0000001	Pdt_01	222.8
Order_0000002	Pdt_05	722.4
Order_0000001	Pdt_05	25.8
Order_0000003	Pdt_01	222.8
Order_0000003	Pdt_01	33.8
Order_0000002	Pdt_03	522.8
Order_0000002	Pdt_04	122.4

输出数据预期：

part-r-00000.txt:

Order_0000001	222.8

part-r-00001.txt:

Order_0000002	722.4

part-r-00002.txt:

Order_0000003	222.8

3）分析
（1）利用“订单id和成交金额”作为key，可以将map阶段读取到的所有订单数据按照id分区，按照金额排序，发送到reduce。
（2）在reduce端利用groupingcomparator将订单id相同的kv聚合成组，然后取第一个即是最大值。
在这里插入图片描述
4）实现
定义订单信息OrderBean

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.WritableComparable;
public class OrderBean implements WritableComparable<OrderBean> {

	private String orderId; // 订单id
	private Double price; // 商品价格

	public OrderBean() {
		super();
	}

	public OrderBean(String orderId, Double price) {
		super();
		this.orderId = orderId;
		this.price = price;
	}

	public String getOrderId() {
		return orderId;
	}

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

	public Double getPrice() {
		return price;
	}

	public void setPrice(Double price) {
		this.price = price;
	}

	@Override
	public void write(DataOutput out) throws IOException {
		out.writeUTF(orderId);
		out.writeDouble(price);
	}
	
	
	@Override
	public void readFields(DataInput in) throws IOException {
		this.orderId = in.readUTF();
		this.price = in.readDouble();
	}

	@Override
	public int compareTo(OrderBean o) {
		//  两次排序
		// 1 按照id号排序
		int comResult = this.orderId.compareTo(o.getOrderId());	
		if (comResult == 0) {
			// 2 按照价格倒序排序
			comResult = this.price > o.getPrice()?-1:1;
		}		
		return comResult;
	}

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

编写OrderMapper处理流程

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class OrderMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable>{
	OrderBean bean = new OrderBean();
	
	@Override
	protected void map(LongWritable key, Text value,
			Context context) throws IOException, InterruptedException {
		// 1 读取数据
		String line = value.toString();
		
		// 2 切割数据
		String[] fields = line.split("\t");
		
		// Order_0000002	Pdt_03	522.8
		// 3 封装bean对象
		bean.setOrderId(fields[0]);
		bean.setPrice(Double.parseDouble(fields[2]));
		
		// 4 写出
		context.write(bean, NullWritable.get());		
	}
}

编写OrderReducer处理流程

import java.io.IOException;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;
public class OrderReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable>{

	@Override
	protected void reduce(OrderBean bean, Iterable<NullWritable> values,
			Context context)	throws IOException, InterruptedException {	
		// 写出
		context.write(bean, NullWritable.get());
	}
}

编写OrderDriver处理流程

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;
public class OrderDriver {
	public static void main(String[] args) throws Exception {
		// 1 获取配置信息
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);

		// 2 设置jar包加载路径
		job.setJarByClass(OrderDriver.class);

		// 3 加载map/reduce类
		job.setMapperClass(OrderMapper.class);
		job.setReducerClass(OrderReducer.class);

		// 4 设置map输出数据key和value类型
		job.setMapOutputKeyClass(OrderBean.class);
		job.setMapOutputValueClass(NullWritable.class);

		// 5 设置最终输出数据的key和value类型
		job.setOutputKeyClass(OrderBean.class);
		job.setOutputValueClass(NullWritable.class);

		// 6 设置输入数据和输出数据路径
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		// 10 关联groupingComparator
		job.setGroupingComparatorClass(OrderGroupingCompartor.class);
		
		// 7 设置分区
		job.setPartitionerClass(OrderPatitioner.class);

		// 8 设置reduce个数
		job.setNumReduceTasks(3);

		// 9 提交
		boolean result = job.waitForCompletion(true);
		System.exit(result ? 0 : 1);
	}
}

编写OrderPartitioner处理流程

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Partitioner;
public class OrderPatitioner extends Partitioner<OrderBean, NullWritable>{

	@Override
	public int getPartition(OrderBean key, NullWritable value, int numPartitions) {
		// 按照key的orderid的hashCode值分区
		 return (key.getOrderId().hashCode() & Integer.MAX_VALUE) % numPartitions;
	}
}

编写OrderGroupingComparator处理流程

import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
public class OrderGroupingCompartor extends WritableComparator {

	// 写一个空参构造
	public OrderGroupingCompartor(){
		super(OrderBean.class, true);
	}
	
	// 重写比较的方法
	@Override
	public int compare(WritableComparable a, WritableComparable b) {
		OrderBean aBean = (OrderBean) a;
		OrderBean bBean = (OrderBean) b;

		// 根据订单id号比较，判断是否是一组
		return aBean.getOrderId().compareTo(bBean.getOrderId());
	}
}