开发笔记:大数据之Hadoop(MapReduce)：GroupingComparator分组案例实操

有如下订单数据&＃xff0c;现在需要求出每一个订单中最贵的商品。
&＃xff08;1&＃xff09;输入数据 GroupingComparator.txt

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


&＃xff08;2&＃xff09;期望输出数据

1 222.8
2 722.4
3 232.8

2.需求分析

&＃xff08;1&＃xff09;利用“订单id和成交金额”作为key&＃xff0c;可以将Map阶段读取到的所有订单数据按照id升序排序&＃xff0c;如果id相同再按照金额降序排序&＃xff0c;发送到Reduce。
&＃xff08;2&＃xff09;在Reduce端利用groupingComparator将订单id相同的kv聚合成组&＃xff0c;然后取第一个即是该订单中最贵商品&＃xff0c;如图4-18所示。

&＃xff08;1&＃xff09;定义订单信息OrderBean类

package com.jinghang.mapreduce.order;
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 int order_id; // 订单id号
private double price; // 价格
public OrderBean() {
super();
}
public OrderBean(int order_id, double price) {
super();
this.order_id &＃61; order_id;
this.price &＃61; price;
}
&＃64;Override
public void write(DataOutput out) throws IOException {
out.writeInt(order_id);
out.writeDouble(price);
}
&＃64;Override
public void readFields(DataInput in) throws IOException {
order_id &＃61; in.readInt();
price &＃61; in.readDouble();
}
&＃64;Override
public String toString() {
return order_id &＃43; "\\t" &＃43; price;
}
public int getOrder_id() {
return order_id;
}
public void setOrder_id(int order_id) {
this.order_id &＃61; order_id;
}
public double getPrice() {
return price;
}
public void setPrice(double price) {
this.price &＃61; price;
}
// 二次排序
&＃64;Override
public int compareTo(OrderBean o) {
int result;
if (order_id > o.getOrder_id()) {
result &＃61; 1;
} else if (order_id < o.getOrder_id()) {
result &＃61; -1;
} else {
// 价格倒序排序
result &＃61; price > o.getPrice() ? -1 : 1;
}
return result;
}
}


&＃xff08;2&＃xff09;编写OrderSortMapper类

package com.jinghang.mapreduce.order;
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 k &＃61; new OrderBean();

&＃64;Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

// 1 获取一行
String line &＃61; value.toString();

// 2 截取
String[] fields &＃61; line.split("\\t");

// 3 封装对象
k.setOrder_id(Integer.parseInt(fields[0]));
k.setPrice(Double.parseDouble(fields[2]));

// 4 写出
context.write(k, NullWritable.get());
}
}


&＃xff08;3&＃xff09;编写OrderSortGroupingComparator类

package com.jinghang.mapreduce.order;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
public class OrderGroupingComparator extends WritableComparator {
protected OrderGroupingComparator() {
super(OrderBean.class, true);
}
&＃64;Override
public int compare(WritableComparable a, WritableComparable b) {
OrderBean aBean &＃61; (OrderBean) a;
OrderBean bBean &＃61; (OrderBean) b;
int result;
if (aBean.getOrder_id() > bBean.getOrder_id()) {
result &＃61; 1;
} else if (aBean.getOrder_id() < bBean.getOrder_id()) {
result &＃61; -1;
} else {
result &＃61; 0;
}
return result;
}
}


&＃xff08;4&＃xff09;编写OrderSortReducer类

package com.jinghang.mapreduce.order;
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> {
&＃64;Override
protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {

context.write(key, NullWritable.get());
}
}


&＃xff08;5&＃xff09;编写OrderSortDriver类

package com.jinghang.mapreduce.order;
import java.io.IOException;
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, IOException {
// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
args &＃61; new String[]{"e:/input/inputorder" , "e:/output1"};
// 1 获取配置信息
Configuration conf &＃61; new Configuration();
Job job &＃61; 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]));
// 8 设置reduce端的分组
job.setGroupingComparatorClass(OrderGroupingComparator.class);
// 7 提交
boolean result &＃61; job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}