Hadoop学习笔记----序列化案例

最新推荐文章于 2022-01-15 21:04:29 发布

G_A34

最新推荐文章于 2022-01-15 21:04:29 发布

阅读量1k

点赞数

文章标签： hadoop hdfs mapreduce

本文链接：https://blog.csdn.net/G_A34/article/details/121191073

版权

本文介绍了如何使用MapReduce编程模型，通过自定义Writables来处理数据，计算每个手机号的上行、下行及总流量。Mapper负责切割输入数据，Reducer则进行流量累加，最终输出每个手机号的流量统计数据。

摘要由CSDN通过智能技术生成

项目需求

根据给定数据统计每一个手机号耗费的总上行流量、总下行流量、总流量

编写MapReduce程序

编写Bean对象

package com.ljx.mr.writable;

/*
* 1.定义实现writable接口
* 2.重写序列化反序列化方法
* 3.重写空参构造
* 4.toString方法
*
* */


import org.apache.hadoop.io.Writable;

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

public class FlowBean implements Writable {

    private long upFlow;//上行流量
    private long downFlow;//下行流量
    private long sumFlow;//总流量

    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() {
        this.sumFlow = this.upFlow + this.downFlow;
    }

    public FlowBean(){

    }

    @Override
    public void write(DataOutput out) throws IOException {

        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);

    }

    @Override
    public void readFields(DataInput in) throws IOException {

        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();

    }

    @Override
    public String toString() {
        return   upFlow + "\t" + downFlow + "\t" + sumFlow;
    }
}

编写Mapper类

package com.ljx.mr.writable;

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> {


    private Text outK = new Text();
    private FlowBean outV = new FlowBean();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        //获取一行数据
        String line = value.toString();

        //切割
        String[] split = line.split("\t");

        //抓取自己想要的数据
        String phone = split[1];
        String up = split[split.length - 3];
        String down = split[split.length - 2];

        //封装
        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));
        outV.setDownFlow(Long.parseLong(down));
        outV.setSumFlow();

        //写出
        context.write(outK,outV);


    }
}

编写Reducer类

package com.ljx.mr.writable;

import org.apache.hadoop.mapreduce.Reducer;

import javax.xml.soap.Text;
import java.io.IOException;

public class FLowReducer extends Reducer<Text,FlowBean,Text,FlowBean> {

    private FlowBean outV = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {

        //遍历集合累加值

        long totalUp = 0;
        long totalDown = 0;

        for (FlowBean value : values) {
            totalUp += value.getUpFlow();
            totalDown += value.getDownFlow();
        }

        //封装outK,outV
        outV.setUpFlow(totalUp);
        outV.setDownFlow(totalDown);
        outV.setSumFlow();

        context.write(key,outV);
    }

}

编写Driver驱动类

package com.ljx.mr.writable;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import javax.xml.soap.Text;
import java.io.IOException;

public class FlowDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        //获取job
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        //设置jar
        job.setJarByClass(FlowDriver.class);

        //关联mapper和reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FLowReducer.class);

        //设置mapper 输出的key和value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //设置最终数据输出的key和value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //设置数据的输入路径和输出路径
        FileInputFormat.setInputPaths(job,new Path("E:\\input\\inputword"));
        FileOutputFormat.setOutputPath(job,new Path("E:\\input\\output1"));

        //提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);

    }

}