MapReduce编程小案例.6th—高效求分组topn的代码实现
需求:有如下一组数据:
order001,u001,小米6,1999.9,2
order001,u001,雀巢咖啡,99.0,2
order001,u001,安慕希,250.0,2
order001,u001,经典红双喜,200.0,4
order001,u001,防水电脑包,400.0,2
order002,u002,小米手环,199.0,3
order002,u002,榴莲,15.0,10
order002,u002,苹果,4.5,20
order002,u002,肥皂,10.0,40
order003,u001,小米6,1999.9,2
order003,u001,雀巢咖啡,99.0,2
order003,u001,安慕希,250.0,2
order003,u001,经典红双喜,200.0,4
order003,u001,防水电脑包,400.0,2
需要得到如下数据:
order001,u001,小米6,1999.9,2,3999.8
order001,u001,防水电脑包,400.0,2,800.0
order001,u001,经典红双喜,200.0,4,800.0
order003,u001,小米6,1999.9,2,3999.8
order003,u001,经典红双喜,200.0,4,800.0
order003,u001,防水电脑包,400.0,2,800.0
order002,u002,小米手环,199.0,3,597.0
order002,u002,肥皂,10.0,40,400.0
order002,u002,榴莲,15.0,10,150.0
把同一个orderID的数据分组,并且列出前三项花费最多的数据行
高效求分组topn的代码实现如下:
1.OrderBean类代码
package cn.edu360.mr.order.topn.grouping;
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;
private String userId;
private String pdtName;
private float price;
private int number;
private float amountFee;
public void set(String orderId, String userId, String pdtName, float price, int number) {
this.orderId = orderId;
this.userId = userId;
this.pdtName = pdtName;
this.price = price;
this.number = number;
this.amountFee = price * number;
}
public String getOrderId() {
return orderId;
}
public void setOrderId(String orderId) {
this.orderId = orderId;
}
public String getUserId() {
return userId;
}
public void setUserId(String userId) {
this.userId = userId;
}
public String getPdtName() {
return pdtName;
}
public void setPdtName(String pdtName) {
this.pdtName = pdtName;
}
public float getPrice() {
return price;
}
public void setPrice(float price) {
this.price = price;
}
public int getNumber() {
return number;
}
public void setNumber(int number) {
this.number = number;
}
public float getAmountFee() {
return amountFee;
}
public void setAmountFee(float amountFee) {
this.amountFee = amountFee;
}
@Override
public String toString() {
return this.orderId + "," +this.userId + "," +this.pdtName +"," + this.price + "," +this.number + "," +this.amountFee;
}
public void readFields(DataInput in) throws IOException {
this.orderId = in.readUTF();
this.userId = in.readUTF();
this.pdtName = in.readUTF();
this.price = in.readFloat();
this.number = in.readInt();
this.amountFee = this.price * this.number ;
}
public void write(DataOutput out) throws IOException {
out.writeUTF(this.orderId);
out.writeUTF(this.userId);
out.writeUTF(this.pdtName);
out.writeFloat(this.price);
out.writeInt(this.number);
}
public int compareTo(OrderBean o) {
return this.orderId.compareTo(o.getOrderId()) == 0 ? Float.compare(o.getAmountFee(), this.getAmountFee()):this.orderId.compareTo(o.getOrderId());
}
}
2.OrderIdPartitioner类
package cn.edu360.mr.order.topn.grouping;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Partitioner;
public class OrderIdPartitioner extends Partitioner<OrderBean, NullWritable>{
@Override
public int getPartition(OrderBean key, NullWritable value, int numPartitions) {
return (key.getOrderId().hashCode() & Integer.MAX_VALUE) % numPartitions;
}
}
3.OrderIdGroupingComparator类
package cn.edu360.mr.order.topn.grouping;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
public class OrderIdGroupingComparator extends WritableComparator{
public OrderIdGroupingComparator() {
super(OrderBean.class,true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
OrderBean o1 = (OrderBean)a;
OrderBean o2 = (OrderBean)b;
return o1.getOrderId().compareTo(o2.getOrderId());
}
}
4.最后的MapReduce主类实现:
package cn.edu360.mr.order.topn.grouping;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class OrderTopn {
public static class OrderTopnMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable>{
OrderBean orderBean = new OrderBean();
NullWritable v = NullWritable.get();
@Override
protected void map(LongWritable key, Text value,
Mapper<LongWritable, Text, OrderBean, NullWritable>.Context context)
throws IOException, InterruptedException {
String[] fields = value.toString().split(",");
orderBean.set(fields[0], fields[1], fields[2], Float.parseFloat(fields[3]), Integer.parseInt(fields[4]));
context.write(orderBean, v);
}
}
public static class OrderTopnReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable>{
/*
* 虽然reduce方法中的参数key只有一个,但是只要迭代器迭代一次,key的值就会变化
*/
@Override
protected void reduce(OrderBean key, Iterable<NullWritable> values,
Reducer<OrderBean, NullWritable, OrderBean, NullWritable>.Context context)
throws IOException, InterruptedException {
int i = 0;
for (NullWritable v : values) {
context.write(key, v);
if(++i == 3) return ;
}
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration(); // 默认只加载core-default.xml core-site.xml
conf.setInt("order.top.n", 2);
Job job = Job.getInstance(conf);
job.setJarByClass(OrderTopn.class);
job.setMapperClass(OrderTopnMapper.class);
job.setReducerClass(OrderTopnReducer.class);
job.setPartitionerClass(OrderIdPartitioner.class);
job.setGroupingComparatorClass(OrderIdGroupingComparator.class);
job.setNumReduceTasks(2);
job.setMapOutputKeyClass(OrderBean.class);
job.setMapOutputValueClass(NullWritable.class);
job.setOutputKeyClass(OrderBean.class);
job.setOutputValueClass(NullWritable.class);
FileInputFormat.setInputPaths(job, new Path("F:\\mrdata\\order\\input"));
FileOutputFormat.setOutputPath(job, new Path("F:\\mrdata\\order\\out2"));
job.waitForCompletion(true);
}
}