大数据之路(二)——MapReduce 编程案例(Topn)

数据形式

如上为某一个人在某一天访问的网站

目标

求被访问次数最多的前5个页面
reduce task 在调用完reduce方法之后并不是马上就结束任务，而是要再调用一下cleanup函数。所以我们可以将reduce方法处理之后的数据放到hashMap函数中处理一下，再调用cleanup函数输出，就会得到相应的topN数据。

//mapper方法实现
import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class PageTopnMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
	
	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
			throws IOException, InterruptedException {
		String line = value.toString();
		String[] split = line.split(" ");
		context.write(new Text(split[1]), new IntWritable(1));
	}

}
//
public class PageCount implements Comparable<PageCount>{
	
	private String page;
	private int count;
	
	public void set(String page, int count) {
		this.page = page;
		this.count = count;
	}
	
	public String getPage() {
		return page;
	}
	public void setPage(String page) {
		this.page = page;
	}
	public int getCount() {
		return count;
	}
	public void setCount(int count) {
		this.count = count;
	}

	@Override
	public int compareTo(PageCount o) {
		
		return o.getCount()-this.count==0?this.page.compareTo(o.getPage()):o.getCount()-this.count;
	}
	
	

}

//reduce方法实现
import java.io.IOException;
import java.util.Map.Entry;
import java.util.Set;
import java.util.TreeMap;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class PageTopnReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
	
	TreeMap<PageCount, Object> treeMap = new TreeMap<>();
	
	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,
			Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
		int count = 0;
		for (IntWritable value : values) {
			count += value.get();
		}
		PageCount pageCount = new PageCount();
		pageCount.set(key.toString(), count);
		
		treeMap.put(pageCount,null);
		
	}
	
	
	@Override
	protected void cleanup(Context context)
			throws IOException, InterruptedException {
		Configuration conf = context.getConfiguration();
		int topn = conf.getInt("top.n", 5);
		
		
		Set<Entry<PageCount, Object>> entrySet = treeMap.entrySet();
		int i= 0;
		
		for (Entry<PageCount, Object> entry : entrySet) {
			context.write(new Text(entry.getKey().getPage()), new IntWritable(entry.getKey().getCount()));
			i++;
			if(i==topn) return;
		}
		
		
	}
	

}