GroupingComparator 自定义分组
图示说明:
![](https://img2018.cnblogs.com/blog/1800342/201909/1800342-20190914205659754-1219816279.png)
有如下订单数据:
现在需要求出每一个订单中最贵的商品。
(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。
代码实现:
定义订单信息OrderBean
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
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 = order_id;
this.price = price;
}
@Override
public void write(DataOutput out) throws IOException {
out.writeInt(order_id);
out.writeDouble(price);
}
@Override
public void readFields(DataInput in) throws IOException {
order_id = in.readInt();
price = in.readDouble();
}
@Override
public String toString() {
return order_id + "\t" + price;
}
public int getOrder_id() {
return order_id;
}
public void setOrder_id(int order_id) {
this.order_id = order_id;
}
public double getPrice() {
return price;
}
public void setPrice(double price) {
this.price = price;
}
// todo 排序规则 根据订单号正序进行排序 如果订单号相同 则根据价格倒序排序
@Override
public int compareTo(OrderBean o) {
int result ;
if (order_id > o.getOrder_id()) {
result = 1;
} else if (order_id < o.getOrder_id()) {
result = -1;
} else {
// 价格倒序排序
result = price > o.getPrice() ? -1 : 1;
}
return result;
}
}
69
1
import java.io.DataInput;
2
import java.io.DataOutput;
3
import java.io.IOException;
4
5
public class OrderBean implements WritableComparable<OrderBean> {
6
private int order_id; // 订单id号
7
private double price; // 价格
8
9
public OrderBean() {
10
super();
11
}
12
13
public OrderBean(int order_id, double price) {
14
super();
15
this.order_id = order_id;
16
this.price = price;
17
}
18
19
20
public void write(DataOutput out) throws IOException {
21
out.writeInt(order_id);
22
out.writeDouble(price);
23
}
24
25
26
public void readFields(DataInput in) throws IOException {
27
order_id = in.readInt();
28
price = in.readDouble();
29
}
30
31
32
public String toString() {
33
return order_id + "\t" + price;
34
}
35
36
public int getOrder_id() {
37
return order_id;
38
}
39
40
public void setOrder_id(int order_id) {
41
this.order_id = order_id;
42
}
43
44
public double getPrice() {
45
return price;
46
}
47
48
public void setPrice(double price) {
49
this.price = price;
50
}
51
52
// todo 排序规则 根据订单号正序进行排序 如果订单号相同 则根据价格倒序排序
53
54
public int compareTo(OrderBean o) {
55
56
int result ;
57
58
if (order_id > o.getOrder_id()) {
59
result = 1;
60
} else if (order_id < o.getOrder_id()) {
61
result = -1;
62
} else {
63
// 价格倒序排序
64
result = price > o.getPrice() ? -1 : 1;
65
}
66
67
return result;
68
}
69
}
编写OrderMapper处理流程
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 OrderMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable> {
OrderBean k = new OrderBean();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 获取一行
String line = value.toString();
// 2 截取
String[] fields = 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());
}
}
27
1
import org.apache.hadoop.io.LongWritable;
2
import org.apache.hadoop.io.NullWritable;
3
import org.apache.hadoop.io.Text;
4
import org.apache.hadoop.mapreduce.Mapper;
5
6
import java.io.IOException;
7
8
public class OrderMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable> {
9
OrderBean k = new OrderBean();
10
11
12
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
13
14
// 1 获取一行
15
String line = value.toString();
16
17
// 2 截取
18
String[] fields = line.split("\t");
19
20
// 3 封装对象
21
k.setOrder_id(Integer.parseInt(fields[0]));
22
k.setPrice(Double.parseDouble(fields[2]));
23
24
// 4 写出
25
context.write(k, NullWritable.get());
26
}
27
}
编写OrderPartitioner处理流程
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Partitioner;
//todo 重新分区规则 订单号一样的 来到同一个分区中
public class OrderPartitioner extends Partitioner<OrderBean, NullWritable> {
@Override
public int getPartition(OrderBean key, NullWritable value, int numReduceTasks) {
return (key.getOrder_id() & Integer.MAX_VALUE) % numReduceTasks;
}
}
12
1
import org.apache.hadoop.io.NullWritable;
2
import org.apache.hadoop.mapreduce.Partitioner;
3
4
//todo 重新分区规则 订单号一样的 来到同一个分区中
5
public class OrderPartitioner extends Partitioner<OrderBean, NullWritable> {
6
7
8
public int getPartition(OrderBean key, NullWritable value, int numReduceTasks) {
9
10
return (key.getOrder_id() & Integer.MAX_VALUE) % numReduceTasks;
11
}
12
}
编写OrderGroupingComparator处理流程
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
//todo 自定义分组规则 订单号一样的来到同一个分组中
public class OrderGroupingComparator extends WritableComparator {
protected OrderGroupingComparator() {
super(OrderBean.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
OrderBean aBean = (OrderBean) a;
OrderBean bBean = (OrderBean) b;
int result;
if (aBean.getOrder_id() > bBean.getOrder_id()) {
result = 1;
} else if (aBean.getOrder_id() < bBean.getOrder_id()) {
result = -1;
} else {
result = 0;
}
return result;
}
}
29
1
import org.apache.hadoop.io.WritableComparable;
2
import org.apache.hadoop.io.WritableComparator;
3
4
//todo 自定义分组规则 订单号一样的来到同一个分组中
5
public class OrderGroupingComparator extends WritableComparator {
6
7
protected OrderGroupingComparator() {
8
super(OrderBean.class, true);
9
}
10
11
12
public int compare(WritableComparable a, WritableComparable b) {
13
14
OrderBean aBean = (OrderBean) a;
15
OrderBean bBean = (OrderBean) b;
16
17
int result;
18
19
if (aBean.getOrder_id() > bBean.getOrder_id()) {
20
result = 1;
21
} else if (aBean.getOrder_id() < bBean.getOrder_id()) {
22
result = -1;
23
} else {
24
result = 0;
25
}
26
27
return result;
28
}
29
}
编写OrderReducer处理流程
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class OrderReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable> {
@Override
protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context)
throws IOException, InterruptedException {
System.out.println(key);
for (NullWritable value : values) {
System.out.println(value);
}
context.write(key, NullWritable.get());
}
}
18
1
import org.apache.hadoop.io.NullWritable;
2
import org.apache.hadoop.mapreduce.Reducer;
3
4
import java.io.IOException;
5
6
public class OrderReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable> {
7
8
9
protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context)
10
throws IOException, InterruptedException {
11
System.out.println(key);
12
for (NullWritable value : values) {
13
System.out.println(value);
14
}
15
16
context.write(key, NullWritable.get());
17
}
18
}
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;
import java.io.IOException;
public class OrderDriver {
public static void main(String[] args) throws Exception, IOException {
// 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("D:\\TiePiHeTao\\input"));
FileOutputFormat.setOutputPath(job, new Path("D:\\TiePiHeTao\\output"));
// // 10 设置reduce端的分组
job.setGroupingComparatorClass(OrderGroupingComparator.class);
// 7 设置分区
job.setPartitionerClass(OrderPartitioner.class);
// 8 设置reduce个数
job.setNumReduceTasks(3);
// 9 提交
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
49
1
import org.apache.hadoop.conf.Configuration;
2
import org.apache.hadoop.fs.Path;
3
import org.apache.hadoop.io.NullWritable;
4
import org.apache.hadoop.mapreduce.Job;
5
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
6
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
7
import java.io.IOException;
8
9
public class OrderDriver {
10
11
public static void main(String[] args) throws Exception, IOException {
12
13
// 1 获取配置信息
14
Configuration conf = new Configuration();
15
Job job = Job.getInstance(conf);
16
17
// 2 设置jar包加载路径
18
job.setJarByClass(OrderDriver.class);
19
20
// 3 加载map/reduce类
21
job.setMapperClass(OrderMapper.class);
22
job.setReducerClass(OrderReducer.class);
23
24
// 4 设置map输出数据key和value类型
25
job.setMapOutputKeyClass(OrderBean.class);
26
job.setMapOutputValueClass(NullWritable.class);
27
28
// 5 设置最终输出数据的key和value类型
29
job.setOutputKeyClass(OrderBean.class);
30
job.setOutputValueClass(NullWritable.class);
31
32
// 6 设置输入数据和输出数据路径
33
FileInputFormat.setInputPaths(job, new Path("D:\\TiePiHeTao\\input"));
34
FileOutputFormat.setOutputPath(job, new Path("D:\\TiePiHeTao\\output"));
35
36
//// 10 设置reduce端的分组
37
job.setGroupingComparatorClass(OrderGroupingComparator.class);
38
39
// 7 设置分区
40
job.setPartitionerClass(OrderPartitioner.class);
41
42
// 8 设置reduce个数
43
job.setNumReduceTasks(3);
44
45
// 9 提交
46
boolean result = job.waitForCompletion(true);
47
System.exit(result ? 0 : 1);
48
}
49
}
总结:
- 默认规则:key相同 为一组
- 自定义分组:
-
继承 WritableComparator 重写compare方法 根据该方法返回的结果来判断是否相等 只要你指定返回为0 那么mr就认为相等
31继承 WritableComparator
2重写compare方法 根据该方法返回的结果来判断是否相等
3只要你指定返回为0 那么mr就认为相等
- 自定义分组如何生效
-
job.setGroupingComparatorClass(OrderGrouping.class);
11job.setGroupingComparatorClass(OrderGrouping.class);
- 自定义排序和自定义分组的梳理
- 自定义排序 正数 大于 、负数小于、零等于
- 自定义分组 零相等 、非零不相等
本文版权归作者和博客园共有,欢迎转载,但必须给出原文链接,并保留此段声明,否则保留追究法律责任的权利。