MapReduce Partition Group 自定义类型输出排序 代码示例

给定电影数据，求出每个电影得分排名前二十的数据

1.自定义Movie类

想要在MapReduce类输入输出自定义类型，需要实现Writable类

想要对自定义类输出排序，需要实现WritableComparable类，自定义排序规则

package nue.edu.ls;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;
/**
 * Writable hadoop 序列化接口
 * 能够排序
 * @author root
 *
 */
public class MovieBean implements WritableComparable<MovieBean>{
	//{"movie":"1193","rate":"5","timeStamp":"978300760","uid":"1"}
	private String movie;
	private int rate;
	private String timeStamp;
	private String uid;

	@Override
	public int compareTo(MovieBean o) {
		if(o.getMovie().compareTo(this.getMovie())==0){
			return o.getRate() - this.getRate();
		}else{
			return o.getMovie().compareTo(this.getMovie());
		}
		//return 0;
	}
	
	public void set(String movie,int rate,String timeStamp,String uid){
		this.movie = movie;
		this.rate = rate;
		this.timeStamp = timeStamp;
		this.uid = uid;
	}
	
	@Override
	public void write(DataOutput out) throws IOException {
		out.writeUTF(movie);
		out.writeInt(rate);
		out.writeUTF(timeStamp);
		out.writeUTF(uid);
		
	}
	@Override
	public void readFields(DataInput in) throws IOException {
		movie = in.readUTF();
		rate = in.readInt();
		timeStamp = in.readUTF();
		uid = in.readUTF();
	}
	
	
	public String getMovie() {
		return movie;
	}
	public void setMovie(String movie) {
		this.movie = movie;
	}
	public int getRate() {
		return rate;
	}
	public void setRate(int rate) {
		this.rate = rate;
	}
	public String getTimeStamp() {
		return timeStamp;
	}
	public void setTimeStamp(String timeStamp) {
		this.timeStamp = timeStamp;
	}
	public String getUid() {
		return uid;
	}
	public void setUid(String uid) {
		this.uid = uid;
	}
	@Override
	public String toString() {
		return "MovieBean [movie=" + movie + ", rate=" + rate + ", timeStamp=" + timeStamp + ", uid=" + uid + "]";
	}
	public void set(MovieBean movieBean) {
		this.movie = movieBean.getMovie();
		this.rate = movieBean.getRate();
		this.timeStamp = movieBean.getTimeStamp();
		this.uid = movieBean.getUid();
		
	}

	
	
	
	

}

2.Partitioner类

用于决定map提交到哪个reduce任务。

在本次代码中，求每个电影前二十位的数据。如果不设置，同一个电影的数据很可能被提交到两个不同的reduce中，会得出2*20条数据，违背了需求。

需自定义一个类，继承Partitioner类。根据getPartitioner的返回值0或者1，决定分配到哪个reduce，避免上面所说的情况。

(key.getMovie().hashCode() & Integer.MAX_VALUE)%numPartitions;     根据MovieId的hashCode值与reduce个数取余，结果不是1就是2，很好的分配了reduce。其中 &Integer.MAX_VALUE保证了hashCode不为负数

设置Partitioner类，还需在提交任务的类中设置job.setPartitionerClass(MyPartition.class)

package nue.edu.ls;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Partitioner;

/**
 * 分区的：
 * 把想要的数据分到相同的reduce里面
 * @author root
 *
 */
public class MyPartition extends Partitioner<MovieBean, NullWritable>{
	/**
	 * munPartitions 代表有多少个reducetask
	 * key map端输出的key
	 * value map端输出的value
	 */
	@Override
	public int getPartition(MovieBean key, NullWritable value, int numPartitions) {
		//防止hashCode是负数
		return (key.getMovie().hashCode() & Integer.MAX_VALUE)%numPartitions;
	}

}

3.Group

设置Group类，是为了避免混乱分组的情况。

比如（a,1),(a,1)两个输入，reduce会识别到key为字符a，将其分为一组

然而（Bean,1)(Bean,1)两个输入，两个自定义类型reduce并不会认为相等，分为一组。

因为在Java中，两个new Bean()，即使内容完全相同，地址值也是不同的，对象之间的比较并不等同于数据类型的比较

在本次代码中，不做Group类，每一个MovieBean都会被认为是不同对的一组，最会会输出所有的MovieBean，而不是前二十位

自定义Group类需继承WritableComparator类且需对无参构造进行改动

package nue.edu.ls;

import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
/**
 * 分组：movieid相同的分到一起
 *
 */
public class MyGroup extends WritableComparator{
	
	public MyGroup() {
		super(MovieBean.class,true);
	}
	
	@Override
	public int compare(WritableComparable a, WritableComparable b) {
		MovieBean bean1 = (MovieBean)a;
		MovieBean bean2 = (MovieBean)b;
		return bean1.getMovie().compareTo(bean2.getMovie());
	}

}

4.任务类

package nue.edu.ls;

import java.io.File;
import java.io.IOException;

import org.apache.commons.io.FileUtils;
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;
import org.codehaus.jackson.map.ObjectMapper;

import com.alibaba.fastjson.JSON;

public class TopN3 {
	public static class MapTask extends Mapper<LongWritable, Text, MovieBean, NullWritable>{
		@Override
		protected void map(LongWritable key, Text value,
				Mapper<LongWritable, Text, MovieBean, NullWritable>.Context context)
				throws IOException, InterruptedException {
			try {
				ObjectMapper mapper = new ObjectMapper();
				//JSON.parseObject(text, clazz)
				MovieBean bean = mapper.readValue(value.toString(), MovieBean.class);
				context.write(bean, NullWritable.get());
			} catch (Exception e) {
			}
		}
	}
	
	public static class ReduceTask extends Reducer<MovieBean, NullWritable, MovieBean, NullWritable>{
		@Override
		protected void reduce(MovieBean key, Iterable<NullWritable> values,
				Reducer<MovieBean, NullWritable, MovieBean, NullWritable>.Context context)
				throws IOException, InterruptedException {
			int num = 0;
			//虽然是一个空的，但是key能够根据迭代进行相应的得到对应空值的结果
			for (NullWritable nullWritable : values) {
				if(num>=20){
					break;
				}
				num++;
				context.write(key, NullWritable.get());
			}
		}
	}
	
	public static void main(String[] args) throws Exception{
		System.setProperty("HADDOP_USER_NAME", "root");
		Configuration conf = new Configuration();
		
		Job job = Job.getInstance(conf, "topn3");
		
		//设置map和reduce，以及提交的jar
		job.setMapperClass(MapTask.class);
		job.setReducerClass(ReduceTask.class);
		job.setJarByClass(TopN3.class);
		job.setNumReduceTasks(2);
		job.setPartitionerClass(MyPartition.class);
		job.setGroupingComparatorClass(MyGroup.class);
		
		
		//设置输入输出类型
		job.setMapOutputKeyClass(MovieBean.class);
		job.setMapOutputValueClass(NullWritable.class);
		
		job.setOutputKeyClass(MovieBean.class);
		job.setOutputValueClass(NullWritable.class);
		
		//输入和输出目录
		FileInputFormat.addInputPath(job, new Path("d:/rating.json"));
		FileOutputFormat.setOutputPath(job, new Path("d:\\data\\out\\topN3"));
		
		//判断文件是否存在
		File file = new File("d:\\data\\out\\topN3");
		if(file.exists()){
			FileUtils.deleteDirectory(file);
		}
		
		//提交任务
		boolean completion = job.waitForCompletion(true);
		System.out.println(completion?"你很优秀！！！":"滚去调bug！！");
	}

}

5.结果