MapReduce综合练习之上网流量统计

====
MapReduce综合练习之上网流量统计

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
代码定义如下：
第一步：自定义map的输出value对象FlowBean
package cn.itcast.mr.demo3.flow;

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;

    /**
     * 序列化的方法
     * @param out
     * @throws IOException
     */
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(upFlow);
        out.writeInt(downFlow);
        out.writeInt(upCountFlow);
        out.writeInt(downCountFlow);

    }

    /**
     * 反序列化的方法
     * @param in
     * @throws IOException
     */
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readInt();
        this.downFlow = in.readInt();
        this.upCountFlow = in.readInt();
        this.downCountFlow = in.readInt();

    }

    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;
    }
}

第二步：定义FlowMapper类
package cn.itcast.mr.demo3.flow;

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>{

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] split = value.toString().split("\t");
        String phon = split[1];
        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]));
        context.write(new Text(phon),flowBean);

    }
}

第三步：定义FlowReducer类
package cn.itcast.mr.demo3.flow;

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> {

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        int upFlow = 0;
        int downFlow = 0;
        int upCountFlow = 0;
        int downCountFlow = 0;
        for (FlowBean value : values) {
            upFlow += value.getUpFlow();
            downFlow += value.getDownFlow();
            upCountFlow += value.getUpCountFlow();
            downCountFlow += value.getDownCountFlow();