3. 自定义分组求取topN
分组是mapreduce当中reduce端的一个功能组件,主要的作用是决定哪些数据作为一组,调用一次reduce的逻辑,默认是每个不同的key,作为多个不同的组,每个组调用一次reduce逻辑,我们可以自定义分组实现不同的key作为同一个组,调用一次reduce逻辑
3.1 需求
有如下订单数据
订单id | 商品id | 成交金额 |
---|---|---|
Order_0000001 | Pdt_01 | 222.8 |
Order_0000001 | Pdt_05 | 25.8 |
Order_0000002 | Pdt_03 | 522.8 |
Order_0000002 | Pdt_04 | 122.4 |
Order_0000002 | Pdt_05 | 722.4 |
Order_0000003 | Pdt_01 | 222.8 |
现在需要求出每一个订单中成交金额最大的一笔交易
3.2 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端利用分组将订单id相同的kv聚合成组,然后取第一个即是最大值
3.3 实现
**第一步:**定义OrderBean
定义一个OrderBean,里面定义两个字段,第一个字段是我们的orderId,第二个字段是我们的金额(注意金额一定要使用Double或者DoubleWritable类型,否则没法按照金额顺序排序)
package demo03;
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 String orderid;
private Double price;
@Override
public String toString() {
return orderid+ "\t"+ 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;
}
//指定javabean排序规则
@Override
public int compareTo(OrderBean orderBean) {
//先去计较订单ID,如果订单id相同,排序订单金额
int i = this.orderid.compareTo(orderBean.orderid);
if (i==0){
i = this.price.compareTo(orderBean.price)*-1;
}
return i;
}
//实现对象序列化
@Override
public void write(DataOutput dataOutput) throws IOException {
dataOutput.writeUTF(orderid);
dataOutput.writeDouble(price);
}
//实现对象的反序列化
@Override
public void readFields(DataInput dataInput) throws IOException {
this.orderid=dataInput.readUTF();
this.price=dataInput.readDouble();
}
}
第二步: 定义Mapper类
package demo03;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class GroupMapper extends Mapper<LongWritable, Text,OrderBean,Text> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String[] split = value.toString().split("\t");
OrderBean orderBean = new OrderBean();
orderBean.setOrderid(split[0]);
orderBean.setPrice(Double.valueOf(split[2]));
context.write(orderBean,value);
}
}
第三步:自定义分区
自定义分区,按照订单id进行分区,把所有订单id相同的数据,都发送到同一个reduce中去
package demo03;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
public class OrderPartition extends Partitioner<OrderBean, Text> {
//分区规则:根据订单的ID分区
@Override
public int getPartition(OrderBean orderBean, Text text, int i) {
return (orderBean.getOrderid().hashCode() & 2147483647) % i;
}
}
第四步:自定义分组
按照我们自己的逻辑进行分组,通过比较相同的订单id,将相同的订单id放到一个组里面去,进过分组之后当中的数据,已经全部是排好序的数据,我们只需要取前topN即可
package demo03;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
/*
* 1:继承WritableComparator
* 2:调用父类的有参构造
* 3.指定分组的规则(重写方法)
* */
public class OrderGroupComparator extends WritableComparator {
// 2:调用父类的有参构造
public OrderGroupComparator() {
super(OrderBean.class,true);
}
//分组的规则
@Override
public int compare(WritableComparable a, WritableComparable b) {
//3.1对形参做强制类型转换
OrderBean first=(OrderBean)a;
OrderBean second=(OrderBean)b;
//3.2指定分组规则
return first.getOrderid().compareTo(second.getOrderid());
}
}
第五步:定义Reducer类
public class GroupReducer extends Reducer<OrderBean,Text,Text,NullWritable> {
@Override
protected void reduce(OrderBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
int i = 0;
//获取集合中的前N条数据
for (Text value : values) {
context.write(value, NullWritable.get());
i++;
if(i >= 1){
break;
}
}
}
}
第六步:程序main函数入口
package demo03;
import demo02.MyOutFormatMapper;
import demo02.MyOutputFormat;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class Jobmain extends Configured implements Tool {
@Override
public int run(String[] strings) throws Exception {
Job job = Job.getInstance(super.getConf(), "mygroup_job");
//设置输入类和输入路径
job.setInputFormatClass(TextInputFormat.class);
TextInputFormat.addInputPath(job,new Path("file:///D:\\input\\mygroup_input"));
//设置Mapper和数据类型
job.setMapperClass(GroupMapper.class);
job.setMapOutputKeyClass(OrderBean.class);
job.setMapOutputValueClass(Text.class);
//shuffle 阶段
job.setPartitionerClass(OrderPartition.class);
job.setGroupingComparatorClass(OrderGroupComparator.class);
//设置ruducer
job.setReducerClass(GroupReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
//第八步:设置输出类和输出的路径
job.setOutputFormatClass(TextOutputFormat.class);
MyOutputFormat.setOutputPath(job,new Path("file:///D:\\out\\myogroup_out"));
boolean b = job.waitForCompletion(true);
return b ? 0:1;
}
public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
int run = ToolRunner.run(configuration, new Jobmain(), args);
System.exit(run);
}
}