大数据学习（八）：mapreduce编程案例-计算访问次数最多的5个网站

数据

2017/07/28 qq.com/a
2017/07/28 qq.com/bx
2017/07/28 qq.com/by
2017/07/28 qq.com/by3
2017/07/28 qq.com/news
2017/07/28 sina.com/news/socail
2017/07/28 163.com/ac
2017/07/28 sina.com/news/socail
2017/07/28 163.com/sport
2017/07/28 163.com/ac
2017/07/28 sina.com/play
2017/07/28 163.com/sport
2017/07/28 163.com/ac
2017/07/28 sina.com/movie
2017/07/28 sina.com/play
2017/07/28 sina.com/movie
2017/07/28 163.com/sport
2017/07/28 sina.com/movie
2017/07/28 163.com/ac
2017/07/28 163.com/ac
2017/07/28 163.com/acc
2017/07/28 qq.com/by
2017/07/28 qq.com/by3
2017/07/28 qq.com/news
2017/07/28 163.com/sport
2017/07/28 sina.com/news/socail
2017/07/28 163.com/sport
2017/07/28 sina.com/movie
2017/07/28 sina.com/news/socail
2017/07/28 sina.com/movie
2017/07/28 qq.com/news
2017/07/28 163.com/bb
2017/07/28 163.com/cc
2017/07/28 sina.com/lady/
2017/07/28 163.com/cc
2017/07/28 qq.com/news
2017/07/28 qq.com/by
2017/07/28 qq.com/by3
2017/07/28 sina.com/lady/
2017/07/28 qq.com/by3
2017/07/28 sina.com/lady/
2017/07/28 qq.com/by3
2017/07/28 qq.com/news
2017/07/28 qq.com/by3
2017/07/28 163.com/sport
2017/07/28 163.com/sport
2017/07/28 sina.com/news/socail
2017/07/28 sina.com/lady/
2017/07/28 sina.com/play
2017/07/28 sina.com/movie
2017/07/28 sina.com/music
2017/07/28 sina.com/sport
2017/07/28 sina.com/sport
2017/07/28 163.com/sport
2017/07/28 sina.com/news/socail
2017/07/28 sohu.com/lady/
2017/07/28 sohu.com/play
2017/07/28 sohu.com/movie
2017/07/28 sohu.com/music
2017/07/28 sohu.com/sport
2017/07/28 sohu.com/sport
2017/07/28 sina.com/news/socail
2017/07/28 baidu.com/lady/
2017/07/28 baidu.com/play
2017/07/28 baidu.com/movie
2017/07/28 baidu.com/music
2017/07/28 baidu.com/movie
2017/07/28 baidu.com/music
2017/07/28 baidu.com/movie
2017/07/28 baidu.com/music
2017/07/28 baidu.com/movie
2017/07/28 baidu.com/music
2017/07/28 baidu.com/movie
2017/07/28 baidu.com/music
2017/07/28 baidu.com/music
2017/07/28 baidu.com/movie
2017/07/28 baidu.com/music
2017/07/28 baidu.com/sport
2017/07/28 baidu.com/sport

package com.bigdata.mapreduce.topn;

/**
 * 排序
 * @author 90669
 *
 */
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;
	}

}

package com.bigdata.mapreduce.topn;

import java.io.IOException;
import java.util.Map;
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>{

	Map<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);
		int topn = 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;
		}
	}
}

package com.bigdata.mapreduce.topn;

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));
	}
}

package com.bigdata.mapreduce.topn;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;


public class JobSubmitter {
	
	public static void main(String[] args) throws Exception {
		/**
		 * 通过加载classpath下的*-site.xml文件解析参数
		 */
		
		Configuration conf = new Configuration();
		conf.addResource("fs-site.xml");
		
		Job job = Job.getInstance(conf);
		
		job.setJarByClass(JobSubmitter.class);
		
		job.setMapperClass(PageTopnMapper.class);
		job.setReducerClass(PageTopnReducer.class);
		
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		FileInputFormat.setInputPaths(job, new Path("D:\\mrdata\\url\\input"));
		FileOutputFormat.setOutputPath(job, new Path("D:\\mrdata\\url\\output"));
		
		job.waitForCompletion(true);
	}

}

计算结果

163.com/sport	8
baidu.com/music	7
sina.com/news/socail	7
baidu.com/movie	6
qq.com/by3	6
sina.com/movie	6