流量统计案例代码

首先，先得在maven_2023下建一个目录data,在data下建一个log.txt文件。

接着点开log.txt文件，把数据填入，内容可以用豆包或者Kimi搜索出来，必须是三个属性：手机号，上行流量，下行流量，用空格隔开。

然后，创建如图下的f目录和目录下Java类。

//1.FlowBean.java代码

package com.example.flow;

import org.apache.hadoop.io.Writable;

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

//hadoop 序列化
//三个属性：手机号，上行流量，下行流量
public class FlowBean implements Writable {
    private String phone;
    private long upFlow;
    private long downFlow;
    public FlowBean(String phone, long upFlow, long downFlow) {
        this.phone = phone;
        this.upFlow = upFlow;
        this.downFlow = downFlow;
    }
    //定义get/set方法
    public String getPhone() {
        return phone;
    }
    public void setPhone(String phone) {
        this.phone = phone;
    }
    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;
    }
    //定义无参构造
    public FlowBean() {}
    //定义一个获取总流量的方法
    public long getSumFlow() {
        return upFlow + downFlow;
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(phone);
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
    }

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

//2.FlowDriver.java代码

package com.example.flow;


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;

//提交job的类，一共做7件事
public class FlowDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //1.获取配置，得到job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //2.设置jar包路径
        job.setJarByClass(FlowDriver.class);
        //3.关联Mapper和Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);
        //4.设置Mapper输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
        //5.设置resucer的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        //6.设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path("data"));
        FileOutputFormat.setOutputPath(job, new Path("output"));
        // 7. 提交job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

//3.FlowMapper.java代码

package com.example.flow;

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

import java.io.IOException;

//1.继承Mapper
//2.重写map函数
public class FlowMapper extends Mapper<LongWritable, Text,Text,FlowBean> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1.获取一行数据,使用空格拆分
        //手机号就是第一个元素
        //上行流量就是第二个元素
        //下行流量就是第三个元素
        String[] split = value.toString().split(" ");
        String phone = split[0];
        Long upFlow = Long.parseLong(split[1]);
        Long downFlow = Long.parseLong(split[2]);
        //2.封装对象
        FlowBean flowBean = new FlowBean(phone,upFlow,downFlow);
        //3.写入手机号为key，值就是这个对象
        context.write(new Text(phone),flowBean);
    }

}

//4.FlowReducer.java代码

package com.example.flow;

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

import java.io.IOException;

//1.继承reducer
//2.重写reduce函数
public class FlowReducer extends Reducer<Text,FlowBean,Text, Text> {
    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        //1.遍历集合，取出每一个元素，计算上行流量和下行流量的汇总
        long upFlowSum = 0L;
        long downFlowSum = 0L;
        long sumFlow = 0L;
        for (FlowBean flowBean : values) {
            upFlowSum += flowBean.getUpFlow();
            downFlowSum += flowBean.getDownFlow();
            sumFlow+= flowBean.getSumFlow();//计算总的汇总

        }

        String flowDesc=String.format("总的上行流量是：%d，总的下行流量是：%d，总流量是：%d",upFlowSum,downFlowSum,sumFlow);

        context.write(key,new Text(flowDesc));


    }
}