MapReduce统计每个用户的使用总流量

1、原始数据

2、使用java程序

　　1）新建项目

　　2）导包
　　hadoop-2.7.3\share\hadoop\mapreduce

　　+hsfs的那些包

　　+common

3、写项目

　　1）实体类

注：属性直接定义为String和 Long定义更方便

package com.zy.flow;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;

public class Flow implements Writable{//Writable可序列化的（序列化：把对象变成二进制流   反序列化：把二进制流变成对象）
//包含 电话 上行流量 下行流量 总流量
    private Text phone;
    private LongWritable upflow;//上行
    private LongWritable downflow;//下行
    private LongWritable sumflow;//总流量
    //这个对象以后要在集群中传输，所以要可序列化

    //序列化反序列化顺序要一致
    @Override//反序列化时会调用该方法
    public void readFields(DataInput in) throws IOException {
        phone=new Text(in.readUTF());
        upflow=new LongWritable(in.readLong());
        downflow=new LongWritable(in.readLong());
        sumflow=new LongWritable(in.readLong());
    }

    @Override//序列化时会调用该方法
    public void write(DataOutput out) throws IOException {
        out.writeUTF(phone.toString());
        out.writeLong(upflow.get());
        out.writeLong(downflow.get());
        out.writeLong(sumflow.get());

    }
    public Text getPhone() {
        return phone;
    }
    public void setPhone(Text phone) {
        this.phone = phone;
    }
    public LongWritable getUpflow() {
        return upflow;
    }
    public void setUpflow(LongWritable upflow) {
        this.upflow = upflow;
    }
    public LongWritable getDownflow() {
        return downflow;
    }
    public void setDownflow(LongWritable downflow) {
        this.downflow = downflow;
    }
    public LongWritable getSumflow() {
        return sumflow;
    }
    public void setSumflow(LongWritable sumflow) {
        this.sumflow = sumflow;
    }
    public Flow() {

    }
    public Flow(Text phone, LongWritable upflow, LongWritable downflow, LongWritable sumflow) {
        super();
        this.phone = phone;
        this.upflow = upflow;
        this.downflow = downflow;
        this.sumflow = sumflow;
    }
    public Flow(LongWritable upflow, LongWritable downflow, LongWritable sumflow) {
        super();
        this.upflow = upflow;
        this.downflow = downflow;
        this.sumflow = sumflow;
    }

    @Override//toString最后就是reduce中输出值的样式
    public String toString() {
　　　　//输出样式
        return upflow+"\t"+downflow+"\t"+sumflow;
    }

}

　　2）FlowMap类

package com.zy.flow;

import java.io.IOException;

import javax.security.auth.callback.LanguageCallback;

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

public class FlowMap extends Mapper<LongWritable, Text, Text, Flow>{

    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Flow>.Context context)
            throws IOException, InterruptedException {
        //输入的值 value
        //切分value 寻找有价值的列
        String[] split = value.toString().split("\t");
        int length=split.length;
        //取哪几列split[1] split[length-3] split[length-2]
        String phone=split[1];
        Long upflow=Long.parseLong(split[length-3]);
        Long downflow=Long.parseLong(split[length-2]);
        Long sumflow=upflow+downflow;
        //输出
        context.write(new Text(phone), new Flow(new Text(phone), new LongWritable(upflow), new LongWritable(downflow),new LongWritable(sumflow)));
        //对象里虽然用不到phone但是要给它赋值，不然序列化时会报空指针异常
    }
}

　　3）Part（分区）类

package com.zy.flow;
import java.util.HashMap;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

//  map的输出是suffer的输入
public class Part extends Partitioner<Text, Flow> {//分区
    //逻辑自己写

    HashMap<String,Integer> map = new HashMap();

    public void setMap(){
    map.put("135",0);
    map.put("136", 1);
    map.put("137",2);
    map.put("138", 3);
    map.put("139",4);
    }
// 生成的文件 part-00000   part的编号的结尾就是这个int类型的返回值；
    @Override
    public int getPartition(Text key, Flow value, int arg2) {

        setMap();
        //从输入的数据中获得电话的前三位跟map对比。决定分到哪个区中
        String substring = key.toString().substring(0, 3);//例如截取135

        return map.get(substring)==null?5:map.get(substring);//根据键取值 键135 取出0
        //其他号码分到（编号为5）第6个区中
    }
    //在这个逻辑下partition分了6个区，所以以后要指定6个reducetask

}

　　4）FlowReduce类

package com.zy.flow;

import java.io.IOException;

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

public class FlowReduce extends Reducer<Text, Flow, Text, Flow>{
    @Override
    protected void reduce(Text key, Iterable<Flow> value, Reducer<Text, Flow, Text, Flow>.Context context)
            throws IOException, InterruptedException {
        //累加
        long allup=0;
        long alldown=0;
        for (Flow flow : value) {
            allup+=Long.parseLong(flow.getUpflow().toString());//同一个电话的上行流量累加
            alldown+=Long.parseLong(flow.getDownflow().toString());//同一个电话的下行流量累加

        }
        long allsum=allup+alldown;
        context.write(key, new Flow(new Text(key), new LongWritable(allup),  new LongWritable(alldown),  new LongWritable(allsum)));
    }

}

　　5）FlowApp类

package com.zy.flow;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 FlowApp {

    public static void main(String[] args) throws Exception {
        //创建配置对象
        Configuration configuration = new Configuration();
        //得到job实例
        Job job = Job.getInstance(configuration);
        //指定job运行类
        job.setJarByClass(FlowApp.class);

        //指定job中的mapper
        job.setMapperClass(FlowMap.class);
        //指定mapper中的输出键和值类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Flow.class);

        //指定job中的reducer
        job.setReducerClass(FlowReduce.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Flow.class);

        //-----
        //指定Partitioner使用的类
        job.setPartitionerClass(Part.class);
        //指定ReduceTask数量
        job.setNumReduceTasks(6);
        //-----

        //指定输入文件
        FileInputFormat.setInputPaths(job, new Path(args[0]));//运行时填入参数
        //指定输出文件
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        //提交作业
        job.waitForCompletion(true);

    }

}

4、运行

　　1）打包

　　2）上传到linux

　　3）运行