实验四：MapReduce中级编程实践

一、实验目的

• L通过实验掌握基本的MapReduce编程方法；
• 掌握用MapReduce解决一些常见的数据处理问题，包括数据去重计数、数据排序。

二、实验平台

• 操作系统：Linux
• Hadoop版本：3.3.1

三、实验步骤

实验所使用的文件链接：
链接：https://pan.baidu.com/s/16zyA_DZwu9anxjwdHnbMOw
提取码：57ky

（一）对访问同一个网站的用户去重计数。

 注：文件userurl_20150911中，数据以”\t”隔开，用户手机号为第三列，网站主域为第17列

package com.user.mapreduce.homework;

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;

import java.io.IOException;

public class UserCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1、获取job
        Configuration conf = new Configuration();

        Job job = Job.getInstance(conf);

        //2、获取jar包路径
        job.setJarByClass(UserCountDriver.class);

        //3、关联mapoer和reducer
        job.setMapperClass(UserCountMapper.class);
        job.setReducerClass(UserCountReducer.class);

        //4、设置map输出的key，value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);

        //5、设置最终输出的key，value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //6、设置输入路径和输出路径
        FileInputFormat.setInputPaths(job,new Path("E:\\BigData\\homework\\hadoop作业\\userurl_20150911"));

        FileOutputFormat.setOutputPath(job,new Path("C:\\Users\\lenovo\\Desktop\\answer"));

        //7、提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

package com.user.mapreduce.homework;

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 java.io.IOException;
import java.util.ArrayList;
import java.util.StringTokenizer;


public class UserCountMapper extends Mapper<Object, Text, Text, Text>{
    private Text outk = new Text();
    private Text outv = new Text();
    @Override
    protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] split = line.split("\t");
        outk.set(split[16]);
        outv.set(split[2]);
        context.write(outk,outv);
    }
}

package com.user.mapreduce.homework;

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

import java.io.IOException;
import java.util.*;

public class UserCountReducer extends Reducer<Text, Text, Text, IntWritable> {
    private IntWritable outv = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        HashMap<String, Boolean> hashMap = new HashMap<String, Boolean>();
        int num = 0;
        for (Text value : values) {
            String phone = value.toString();
            //if (null == phone) continue;
            if(hashMap.get(phone) != null) continue;
            hashMap.put(phone,true);
            ++num;
        }
        outv.set(num);
        context.write(key,outv);
    }
}

（二）对同一个用户不同记录产生的上下行流量求和后进行排序输出。

注：上行流量位于第25列，下行流量位于第26列

package com.user.mapreduce.homework;

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;

import java.io.IOException;

public class FlowDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1、获取job
        Configuration conf = new Configuration();

        Job job = Job.getInstance(conf);

        //2、获取jar包路径
        job.setJarByClass(FlowtDriver.class);

        //3、关联mapoer和reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //4、设置map输出的key，value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //5、设置最终输出的key，value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //6、设置输入路径和输出路径
        FileInputFormat.setInputPaths(job,new Path("E:\\BigData\\homework\\hadoop作业\\userurl_20150911"));
        FileOutputFormat.setOutputPath(job,new Path("C:\\Users\\lenovo\\Desktop\\answer"));

        //7、提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

package com.user.mapreduce.homework;

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 java.io.IOException;
import java.util.ArrayList;
import java.util.StringTokenizer;

public class FlowMapper extends Mapper<Object, Text, Text, IntWritable>{
    private Text outk = new Text();
    private IntWritable outv = new IntWritable();
    @Override
    protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] split = line.split("\t");
        outk.set(split[2]);
        outv.set(Integer.parseInt(split[24]) + Integer.parseInt(split[25]));
        context.write(outk,outv);
    }
}

package com.user.mapreduce.homework;

import com.user.mapreduce.writable.FlowBean;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.*;

public class FlowReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable outv = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        ArrayList<Integer> list = new ArrayList<>();
        for (IntWritable value : values) {
            list.add(value.get());
        }
        Collections.sort(list, new Comparator<Integer>() {
            @Override
            public int compare(Integer o1, Integer o2) {
                if(o1 > o2) return 1;
                if(o1 < o2) return -1;
                return 0;
            }
        });
        for (Integer integer : list) {
            outv.set(integer);
            context.write(key,outv);
        }
    }
}