Hadoop学习之十MapReduce案例分析二-好友推荐

Posted 2021-02-05 cac2020

环境
　　虚拟机：VMware 10
　　Linux版本：CentOS-6.5-x86_64
　　客户端：Xshell4
　　FTP：Xftp4
　　jdk8
　　hadoop-3.1.1

 

最应该推荐的好友TopN，如何排名？

tom hello hadoop cat
world hadoop hello hive
cat tom hive
mr hive hello
hive cat hadoop world hello mr
hadoop tom hive world
hello tom world hive mr

package test.mr.fof;

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;
import org.apache.hadoop.util.GenericOptionsParser;

public class MyFOF {
    
    /**
     * 最应该推荐的好友TopN，如何排名？

     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {
        
        Configuration conf = new Configuration(true);
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        conf.set("sleep", otherArgs[2]);
        
        Job job = Job.getInstance(conf,"FOF");
        job.setJarByClass(MyFOF.class);
        
        
        //Map
        job.setMapperClass(FMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        
        //Reduce
        job.setReducerClass(FReducer.class);
        
        //HDFS 输入路径
        Path input = new Path(otherArgs[0]);
        FileInputFormat.addInputPath(job, input );
        //HDFS 输出路径
        Path output = new Path(otherArgs[1]);
        if(output.getFileSystem(conf).exists(output)){
            output.getFileSystem(conf).delete(output,true);
        }
        FileOutputFormat.setOutputPath(job, output );
        
        System.exit(job.waitForCompletion(true) ? 0 :1);
    }
//    tom hello hadoop cat
//    world hadoop hello hive
//    cat tom hive
//    mr hive hello
//    hive cat hadoop world hello mr
//    hadoop tom hive world
//    hello tom world hive mr

}

package test.mr.fof;

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;
import org.apache.hadoop.util.StringUtils;

public class FMapper extends Mapper<LongWritable, Text, Text, IntWritable>{

    Text mkey= new Text();
    IntWritable mval = new IntWritable();
    
    @Override
    protected void map(LongWritable key, Text value,Context context)
            throws IOException, InterruptedException {
        
        //value: 0-直接关系  1-间接关系
        //tom       hello hadoop cat   :   hello:hello  1
        //hello     tom world hive mr      hello:hello  0


        String[] strs = StringUtils.split(value.toString(), \' \');
        
        String user=strs[0];
        String user01=null;
        for(int i=1;i<strs.length;i++){
            //与好友清单中好友属于直接关系
            mkey.set(fof(strs[0],strs[i]));  
            mval.set(0); 
            context.write(mkey, mval);  
            
            for (int j = i+1; j < strs.length; j++) {
                Thread.sleep(context.getConfiguration().getInt("sleep", 0));
                //好友列表内 成员之间是间接关系
                mkey.set(fof(strs[i],strs[j]));  
                mval.set(1);  
                context.write(mkey, mval);  
            }
        }
    }
    
    public static String fof(String str1  , String str2){
        
        
        if(str1.compareTo(str2) > 0){
            //hello,hadoop
            return str2+":"+str1;
        }
        //hadoop,hello
        return str1+":"+str2;
    }
    
}

package test.mr.fof;

import java.io.IOException;

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

public class FReducer  extends  Reducer<Text, IntWritable, Text, Text> {
    
    Text rval = new Text();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> vals, Context context)
            throws IOException, InterruptedException 
    {
        //是简单的好友列表的差集吗？
        //最应该推荐的好友TopN，如何排名？

        //hadoop:hello  1
        //hadoop:hello  0
        //hadoop:hello  1
        //hadoop:hello  1
        int sum=0;
        int flg=0;
        for (IntWritable v : vals) 
        {
            //0为直接关系
            if(v.get()==0){
                //hadoop:hello  0
                flg=1;
            }
            sum += v.get();
        }
        
        //只有间接关系才会被输出
        if(flg==0){
            rval.set(sum+"");
            context.write(key, rval);
        }
    }
}