MR案例之自定义序列化

需求分析

统计每一个手机号耗费的总上传流量、下载流量、总流量

数据准备

输入数据格式：

要求输出数据格式：

思路分析

Map阶段

（1）读取一行数据，切分字段
（2）抽取手机号、上行流量、下行流量
（3）以手机号为key，bean对象为value输出，即context.write(手机号,bean);

Reduce阶段

（1）累加上行流量和下行流量得到总流量。
（2）实现自定义的bean来封装流量信息，并将bean作为map输出的key来传输
（3）MR程序在处理数据的过程中会对数据排序(map输出的kv对传输到reduce之前，会排序)，排序的依据是map输出的key

代码编写

自定义序列化FlowBean

package flowwb;

import org.apache.hadoop.io.Writable;

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

public class FlowBean implements Writable {

    //alt + insert 自动生成get/set()
    //上传流量，用来作为排序依据
    private long upflow;
    //下载流量
    private long downflow;
    //总流量
    private long sumflow;

    public long getUpflow() {
        return upflow;
    }

    public void setUpflow(long upflow) {
        this.upflow = upflow;
    }

    public long getDownflow() {
        return downflow;
    }

    public void setDownflow(long downflow) {
        this.downflow = downflow;
    }

    public long getSumflow() {
        return sumflow;
    }

    public void setSumflow(long sumupflow) {
        this.sumflow = sumupflow;
    }

    //空参构造器，满足自定义序列化需要
    public FlowBean(){

    }
    //自定义构造器
    public FlowBean(long upflow,long downflow){
        this.upflow=upflow;
        this.downflow=downflow;
        this.sumflow=upflow+downflow;


    }
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(this.upflow);
        dataOutput.writeLong(this.downflow);
        dataOutput.writeLong(this.sumflow);

    }

    public void readFields(DataInput dataInput) throws IOException {

        this.upflow = dataInput.readLong();
        this.downflow = dataInput.readLong();
        this.sumflow = dataInput.readLong();
    }
    public String toString(){
        return this.upflow+"\t"+this.downflow+"\t"+this.sumflow;
    }
}

Mapper

package flowwb;

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

import java.io.IOException;

public class FlowMapper extends Mapper<LongWritable,Text,Text,FlowBean> {
    //ctrl+o 重写继承类中某方法
    //alt+insert也可以


    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取数据
        String line = value.toString();
        //切分数据
        String[] fields = line.split("\t");
        int n=fields.length;
        //封装数据
        FlowBean flowBean = new FlowBean(Long.parseLong(fields[n-3]),Long.parseLong(fields[n-2]));
        //用手机号码作reduce的key
        context.write(new Text(fields[1]),flowBean);

    }
}

Reducer

package flowwb;

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

import java.io.IOException;

public class FlowReducer extends Reducer<Text,FlowBean,Text,FlowBean> {
    //传过来的数据已经按照key值去重了
    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        //定义总上传流量和下载流量
        long sumupflow=0;
        long sumdownflow=0;
        //遍历每个key（电话号码）的流量数据，计算出总流量
        for(FlowBean f:values){
            sumupflow+=f.getUpflow();
            sumdownflow+=f.getDownflow();

        }
        FlowBean flowBean = new FlowBean(sumupflow, sumdownflow);
        context.write(key,flowBean);
    }
}

Driver

package flowwb;

import LogClean.CleanDriver;
import LogClean.CleanMapper;
import Partition.MyPartition;
import Partition.PartitionDriver;
import Partition.PartitionMapper;
import Partition.PartitionReduce;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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 java.io.IOException;

public class FlowDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //实例化配置文件
        Configuration conf = new Configuration();
        //定义一个job任务
        Job job = Job.getInstance(conf);
        //配置job的信息
        job.setJarByClass(FlowDriver.class);
        //指定自定义的mapper、mapper的数据类型到job中
        job.setMapperClass(FlowMapper.class);
        job.setOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //指定自定义的reduce以及reduce的输出数据类型，总输出类型

        job.setReducerClass(FlowReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);


        //配置输入数据的路径，这一部分演示的在本地运行
        FileInputFormat.setInputPaths(job,new Path("D:\\BigdataTest\\PhoneData\\phone_data.txt"));

        //配置输出数据的路径
        FileOutputFormat.setOutputPath(job,new Path("D:\\BigdataTest\\PhoneData\\FlowWritable"));

        /*//配置输入数据的路径,这一部分是打包上传到集群运行
        FileInputFormat.setInputPaths(job,new Path(args[0]));

        //配置输出数据的路径
        FileOutputFormat.setOutputPath(job,new Path(args[1]));*/

        //提交任务
        job.waitForCompletion(true);
    }
}

结果展示