MapReduce-流量统计求和-FlowBean和Mapper代码编写

流量统计

需求一: 统计求和

统计每个手机号的上行流量总和，下行流量总和，上行总流量之和，下行总流量之和分析：以手机号码作为key值，上行流量，下行流量，上行总流量，下行总流量四个字段作为value值，然后以这个key，和value作为map阶段的输出，reduce阶段的输入

Step 1: 自定义map的输出value对象FlowBean

package cn.learn.mapreduce_flowcount;

import org.apache.hadoop.io.Writable;

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

public class FlowBean  implements Writable {
    private Integer upFlow;
    private Integer  downFlow;
    private Integer upCountFlow;
    private Integer downCountFlow;


    public Integer getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(Integer upFlow) {
        this.upFlow = upFlow;
    }

    public Integer getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(Integer downFlow) {
        this.downFlow = downFlow;
    }

    public Integer getUpCountFlow() {
        return upCountFlow;
    }

    public void setUpCountFlow(Integer upCountFlow) {
        this.upCountFlow = upCountFlow;
    }

    public Integer getDownCountFlow() {
        return downCountFlow;
    }

    public void setDownCountFlow(Integer downCountFlow) {
        this.downCountFlow = downCountFlow;
    }

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

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeInt(upFlow);
        dataOutput.writeInt(downFlow);
        dataOutput.writeInt(upCountFlow);
        dataOutput.writeInt(downCountFlow);
    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow = dataInput.readInt();
        this.downFlow = dataInput.readInt();
        this.upCountFlow = dataInput.readInt();
        this.downCountFlow = dataInput.readInt();
    }
}

Step 2: 定义FlowMapper类

package cn.learn.mapreduce_flowcount;

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

import java.io.IOException;

public class FlowCountMapper extends Mapper<LongWritable,Text,Text,FlowBean> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, 
InterruptedException {
       //1:拆分手机号
        String[] split = value.toString().split("\t");
        String phoneNum = split[1];
        //2:获取四个流量字段
        FlowBean flowBean = new FlowBean();
        flowBean.setUpFlow(Integer.parseInt(split[6]));
        flowBean.setDownFlow(Integer.parseInt(split[7]));
        flowBean.setUpCountFlow(Integer.parseInt(split[8]));
        flowBean.setDownCountFlow(Integer.parseInt(split[9]));

        //3:将k2和v2写入上下文中
        context.write(new Text(phoneNum), flowBean);
    }
}