MapReduce案例四：共同好友

目录

一、数据样式

  人：好友1,好友2...

A:B,C,D,F,E,O
B:A,C,E,K
C:F,A,D,I
D:A,E,F,L
E:B,C,D,M,L
F:A,B,C,D,E,O,M
G:A,C,D,E,F
H:A,C,D,E,O
I:A,O
J:B,O
K:A,C,D
L:D,E,F
M:E,F,G
O:A,H,I,J

二、需求

  求出哪些人两两之间有共同好友，及他俩的共同好友都有谁？

三、分析

  • 1、先求出A、B、C、….等是谁的好友，比如说现在是人:好友1，好友2...的形式，先求好友--人1，人2...的结果。即先求出那些人有哪些共同好友。

  • 2、以好友--人1，人2...的形式作为第二次MapReduce的数据源，然后求出两个人之间的共同好友，即人1-人2 好友1 好友2...,人1-人3 好友1 好友2...的形式。

四、程序实现

  • 1、第一次Mapper,创建 OneShareFriendsMapper 类：
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class OneShareFriendsMapper extends Mapper<LongWritable, Text, Text, Text>{
    
    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
            throws IOException, InterruptedException {
        // 1 获取一行 A:B,C,D,F,E,O
        String line = value.toString();
        
        // 2 切割
        String[] fileds = line.split(":");
        
        // 3 获取person和好友
        String person = fileds[0];
        String[] friends = fileds[1].split(",");
        
        // 4写出去
        for(String friend: friends){
            // 输出 <好友，人>
            context.write(new Text(friend), new Text(person));
        }
    }
}
  • 2、第一次Reducer,创建 OneShareFriendsReducer 类：
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class OneShareFriendsReducer extends Reducer<Text, Text, Text, Text>{
    
    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context)
            throws IOException, InterruptedException {
        
        StringBuffer sb = new StringBuffer();
        //1 拼接
        for(Text person: values){
            sb.append(person).append(",");
        }
        
        //2 写出
        context.write(key, new Text(sb.toString()));
    }
}
  • 3、第一次Driver，创建 OneShareFriendsDriver 类：
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 OneShareFriendsDriver {

    public static void main(String[] args) throws Exception {

        args = new String[]{"D:\\大数据API\\friends.txt", "D:\\大数据API\\dataone"};

        // 1 获取job对象
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);
        
        // 2 指定jar包运行的路径
        job.setJarByClass(OneShareFriendsDriver.class);

        // 3 指定map/reduce使用的类
        job.setMapperClass(OneShareFriendsMapper.class);
        job.setReducerClass(OneShareFriendsReducer.class);
        
        // 4 指定map输出的数据类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        
        // 5 指定最终输出的数据类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        
        // 6 指定job的输入原始所在目录
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
        // 7 提交
        boolean result = job.waitForCompletion(true);
        
        System.exit(result?1:0);
    }
}
  • 4、第二次Mapper，创建 TwoShareFriendsMapper 类：
import java.io.IOException;
import java.util.Arrays;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class TwoShareFriendsMapper extends Mapper<LongWritable, Text, Text, Text>{
    
    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        // A I,K,C,B,G,F,H,O,D,
        // 友 人，人，人
        String line = value.toString();
        String[] friend_persons = line.split("\t");

        String friend = friend_persons[0];
        String[] persons = friend_persons[1].split(",");

        Arrays.sort(persons);

        for (int i = 0; i < persons.length - 1; i++) {
            
            for (int j = i + 1; j < persons.length; j++) {
                // 发出 <人-人，好友> ，这样，相同的“人-人”对的所有好友就会到同1个reduce中去
                context.write(new Text(persons[i] + "-" + persons[j]), new Text(friend));
            }
        }
    }
}
  • 5、第二次Reducer,创建 TwoShareFriendsReducer 类：
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class TwoShareFriendsReducer extends Reducer<Text, Text, Text, Text>{
    
    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context)
            throws IOException, InterruptedException {
        
        StringBuffer sb = new StringBuffer();

        for (Text friend : values) {
            sb.append(friend).append(" ");
        }
        
        context.write(key, new Text(sb.toString()));
    }
}
  • 6、第二次Driver，创建 TwoShareFriendsDriver 类：
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 TwoShareFriendsDriver {

    public static void main(String[] args) throws Exception {

        args = new String[]{"D:\\大数据API\\dataone", "D:\\大数据API\\datatwo"};

        // 1 获取job对象
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);
        
        // 2 指定jar包运行的路径
        job.setJarByClass(TwoShareFriendsDriver.class);

        // 3 指定map/reduce使用的类
        job.setMapperClass(TwoShareFriendsMapper.class);
        job.setReducerClass(TwoShareFriendsReducer.class);
        
        // 4 指定map输出的数据类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        
        // 5 指定最终输出的数据类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        
        // 6 指定job的输入原始所在目录
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
        // 7 提交
        boolean result = job.waitForCompletion(true);
        
        System.exit(result?1:0);
    }
}
  • 补充

第一次MapReduce的结果图：

第二次MapReduce的结果图：

五、两次job串联

  如果不想写多次driver代码，可以把两次job并联，代码如下:

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.jobcontrol.ControlledJob;
import org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class AllShareFriendsReducer {
    public static void main(String[] args) throws IOException {

        args = new String[]{"D:\\大数据API\\friends.txt","D:\\大数据API\\dataone1","D:\\大数据API\\\\datatwo1"};

        Configuration conf = new Configuration();
        Job job1 = Job.getInstance(conf);

        job1.setMapperClass(OneShareFriendsMapper.class);
        job1.setReducerClass(OneShareFriendsReducer.class);

        job1.setMapOutputKeyClass(Text.class);
        job1.setMapOutputValueClass(Text.class);
        job1.setOutputKeyClass(Text.class);
        job1.setOutputValueClass(Text.class);

        FileInputFormat.setInputPaths(job1, new Path(args[0]));
        FileOutputFormat.setOutputPath(job1, new Path(args[1]));

        Job job2 = Job.getInstance(conf);

        job2.setMapperClass(TwoShareFriendsMapper.class);
        job2.setReducerClass(TwoShareFriendsReducer.class);

        job2.setMapOutputKeyClass(Text.class);
        job2.setMapOutputValueClass(Text.class);
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(Text.class);

        FileInputFormat.setInputPaths(job2, new Path(args[1]));
        FileOutputFormat.setOutputPath(job2, new Path(args[2]));

        JobControl control = new JobControl("Andy");
        ControlledJob ajob = new ControlledJob(job1.getConfiguration());
        ControlledJob bjob = new ControlledJob(job2.getConfiguration());
        bjob.addDependingJob(ajob);
        control.addJob(ajob);
        control.addJob(bjob);
        Thread thread = new Thread(control);
        thread.start();
    }
}
posted @ 2020-02-04 21:57  落花桂  阅读(699)  评论(0)  编辑  收藏  举报
返回顶端
Live2D