Hadoop序列化案例实操

最新推荐文章于 2024-08-08 16:54:44 发布

枫落@

最新推荐文章于 2024-08-08 16:54:44 发布

阅读量97

点赞数

文章标签： hadoop 大数据分布式

本文链接：https://blog.csdn.net/qq_42053753/article/details/131826383

版权

该文章介绍了一个使用HadoopMapReduce进行流量统计的程序。首先定义了一个FlowBean，包含上行、下行流量和总流量属性，实现了Writable接口。接着，Mapper类解析输入数据，提取手机号和流量信息，并输出到Reducer。Reducer类则对相同手机号的流量进行求和，计算总流量。最后，Driver类配置并运行Job，处理输入输出路径。

摘要由CSDN通过智能技术生成

1、输入数据格式

7 13560436666 120.196.100.99 1116 954 200

id 手机号码网络ip 上行流量下行流量网络状态码

2、期望输出数据格式

13560436666 1116 954 2070

手机号码上行流量下行流量总流量

3、编写MapReduce程序

（1）编写流量统计的Bean对象

package com.atguigu.mapreduce.writable;

import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

//1 继承Writable接口
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

    //2 提供无参构造
    public FlowBean() {
    }

    //3 提供三个参数的getter和setter方法
    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 sumFlow) {
        this.sumFlow = sumFlow;
    }

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

    //4 实现序列化和反序列化方法,注意顺序一定要保持一致
    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow = dataInput.readLong();
        this.downFlow = dataInput.readLong();
        this.sumFlow = dataInput.readLong();
    }

    //5 重写ToString
    @Override
    public String toString() {
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }
}

（2）编写Mapper类

package com.atguigu.mapreduce.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 {

        //1 获取一行数据,转成字符串
        String line = value.toString();

        //2 切割数据
        String[] split = line.split("\t");

        //3 抓取我们需要的数据:手机号,上行流量,下行流量
        String phone = split[1];
        String up = split[split.length - 3];
        String down = split[split.length - 2];

        //4 封装outK outV
        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));
        outV.setDownFlow(Long.parseLong(down));
        outV.setSumFlow();

        //5 写出outK outV
        context.write(outK, outV);
    }
}

（3）编写Reducer类

package com.atguigu.mapreduce.writable;

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

        long totalUp = 0;
        long totalDown = 0;

        //1 遍历values,将其中的上行流量,下行流量分别累加
        for (FlowBean flowBean : values) {
            totalUp += flowBean.getUpFlow();
            totalDown += flowBean.getDownFlow();
        }

        //2 封装outKV
        outV.setUpFlow(totalUp);
        outV.setDownFlow(totalDown);
        outV.setSumFlow();

        //3 写出outK outV
        context.write(key,outV);
    }
}

（4）编写Driver驱动类

package com.atguigu.mapreduce.writable;

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;
import java.io.IOException;

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

        //1 获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //2 关联本Driver类
        job.setJarByClass(FlowDriver.class);

        //3 关联Mapper和Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);
        
//4 设置Map端输出KV类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
        
//5 设置程序最终输出的KV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        
//6 设置程序的输入输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\inputflow"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\flowoutput"));
        
//7 提交Job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

本地测试