hadoop_mapreduce02-序列化与反序列化-计算上下行流量

hadoop_mapreduce02-序列化与反序列化-计算上下行流量

注：仅做笔记。

（一）需求

统计每一个手机号耗费的总上行流量、下行流量、总流量。

phone_data.txt

1	13736230513	192.196.100.1	www.at.com	2481	24681	200
2	13846544121	192.196.100.2			264	0	200
3 	13956435636	192.196.100.3			132	1512	200
4 	13966251146	192.168.100.1			240	0	404
5 	18271575951	192.168.100.2	www.at.com	1527	2106	200
6 	84188413	192.168.100.3	www.at.com	4116	1432	200
7 	13590439668	192.168.100.4			1116	954	200
8 	15910133277	192.168.100.5	www.hao123.com	3156	2936	200
9 	13729199489	192.168.100.6			240	0	200
10 	13630577991	192.168.100.7	www.shouhu.com	6960	690	200
11 	15043685818	192.168.100.8	www.baidu.com	3659	3538	200
12 	15959002129	192.168.100.9	www.at.com	1938	180	500
13 	13560439638	192.168.100.10			918	4938	200
14 	13470253144	192.168.100.11			180	180	200
15 	13682846555	192.168.100.12	www.qq.com	1938	2910	200
16 	13992314666	192.168.100.13	www.gaga.com	3008	3720	200
17 	13509468723	192.168.100.14	www.qinghua.com	7335	110349	404
18 	18390173782	192.168.100.15	www.sogou.com	9531	2412	200
19 	13975057813	192.168.100.16	www.baidu.com	11058	48243	200
20 	13768778790	192.168.100.17			120	120	200
21 	13568436656	192.168.100.18	www.alibaba.com	2481	24681	200
22 	13568436656	192.168.100.19			1116	954	200

预期返回结果

phone_num upFlow downFlow sumFlow
13470253144	180 180 360
13509468723 7335 110349 117684
...

需求分析

1、需求：统计每一个手机号耗费的总上行流量、下行流量、总流量

2、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

3、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

4、Map阶段

（1）读取一行数据，切分字段

（2）抽取手机号、上行流量、下行流量

（3）以手机号为key，bean对象为value输 出，

即context.write(手机号,bean);

5、Reduce阶段

（1）累加上行流量和下行流量得到总流量。

（4）bean对象要想能够传输，必须实现序列化接口

7 13560436666 120.196.100.99 1116 954 200

13560436666 1116 954

手机号码 上行流量 下行流量

13560436666 1116 + 954 = 2070

手机号码 上行流量 下行流量 总流量

（二）编写程序

1）FlowBean

package com.art.mapreduce.flowcount;


import org.apache.hadoop.io.Writable;

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

// 1.实现writable接口
public class FlowBean implements Writable {

    private long upFlow;
    private long downFlow;
    private long sumFlow;

    // 2.反序列化的时候需要用空参构造函数，所以必须有【快捷键：构造函数 Alt+Shirft+s/cmd+N/control+enter】
    public FlowBean() {
        super();
    }


    public FlowBean(long upFlow, long downFlow) {
        super();
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow + downFlow;
    }


    // 3.写序列化方法(接口一定要重写的方法)
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

    // 4.反序列化方法(接口一定要重写的方法)
    // 5.反序列化方法读顺序必须和写序列化方法的写顺序一致（队列）
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }


    // 6.编写toString方法，方便后续打印到文本
    @Override
    public String toString() {
        return "FlowBean{" +
                "upFlow=" + upFlow +
                ", downFlow=" + downFlow +
                ", sumFlow=" + sumFlow +
                '}';
    }

    // 7.get和set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 set (long upFlow, long downFlow){
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow +downFlow;
    }


}

2）FlowCountMapper

package com.art.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> {

    FlowBean v = new FlowBean();
    Text k = new Text();


    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 1.获取一行数据
        // 1	13736230513	192.196.100.1	www.at.com	2481	24681	200
        String line = value.toString();

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

        // 3.封装
        String phoNum = fields[1];
        long upFlow = Long.parseLong(fields[fields.length - 3]);
        long downFlow = Long.parseLong(fields[fields.length - 2]);

        k.set(phoNum);
//        v.setUpFlow(upFlow);
//        v.setDownFlow(downFlow);
        // 如果要使用  需要在FlowBean中补充一个方法set
        v.set(upFlow, downFlow); // 因为现在这种方法更好理解 所以先用该方法


        // 4.写出
        context.write(k, v);

    }


}

3）FlowCountReducer

package com.art.mapreduce.flowcount;

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

import java.io.IOException;


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

    @Override
    public void reduce(Text key2, Iterable<FlowBean> value2, Context context) throws IOException, InterruptedException {
        long sum_upFlow = 0;
        long sum_downFlow = 0;


        // 1. 遍历迭代器, 将上行流量和下行流量分别累加
        for (FlowBean flowBean : value2) {
            sum_upFlow += flowBean.getUpFlow();
            sum_downFlow += flowBean.getDownFlow();
        }


        // 2. 封装
        Text key3 = key2;
        FlowBean value3 = new FlowBean(sum_upFlow, sum_downFlow);

        // 3. 写出
        context.write(key3, value3);


    }


}

4）FlowSumDriver

package com.art.mapreduce.flowcount;

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

        // 输入输出路径，根据运行环境填写，也可以跟在jar后面
        args = new String[]{"/Users/art/Documents/demo_datas/flowcount_inputs","/Users/art/Documents/demo_datas/flowcount_outputs"};

        // 1. 设置job和配置项
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2. 设置map类和写出类
        job.setMapperClass(FlowCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        // 3. 设置reduce类和写出类
        job.setReducerClass(FlowCountReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        // 4.指定本程序jar包所在本地路径
        job.setJarByClass(FlowSumDriver.class);

        // 5. 读入写出的的路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        // 6. 将job中配置的相关参数，以及job所用的java类所在的jar包提交诶yarn去运行
        boolean result = job.waitForCompletion(true);
        System.exit((result)? 0:1);


    }
}

（三）测试

过程略，参见wordcount

返回结果

13470253144	FlowBean{upFlow=180, downFlow=180, sumFlow=360}
13509468723	FlowBean{upFlow=7335, downFlow=110349, sumFlow=117684}
13560439638	FlowBean{upFlow=918, downFlow=4938, sumFlow=5856}
13568436656	FlowBean{upFlow=3597, downFlow=25635, sumFlow=29232}
13590439668	FlowBean{upFlow=1116, downFlow=954, sumFlow=2070}
13630577991	FlowBean{upFlow=6960, downFlow=690, sumFlow=7650}
13682846555	FlowBean{upFlow=1938, downFlow=2910, sumFlow=4848}
13729199489	FlowBean{upFlow=240, downFlow=0, sumFlow=240}
13736230513	FlowBean{upFlow=2481, downFlow=24681, sumFlow=27162}
13768778790	FlowBean{upFlow=120, downFlow=120, sumFlow=240}
13846544121	FlowBean{upFlow=264, downFlow=0, sumFlow=264}
13956435636	FlowBean{upFlow=132, downFlow=1512, sumFlow=1644}
13966251146	FlowBean{upFlow=240, downFlow=0, sumFlow=240}
13975057813	FlowBean{upFlow=11058, downFlow=48243, sumFlow=59301}
13992314666	FlowBean{upFlow=3008, downFlow=3720, sumFlow=6728}
15043685818	FlowBean{upFlow=3659, downFlow=3538, sumFlow=7197}
15910133277	FlowBean{upFlow=3156, downFlow=2936, sumFlow=6092}
15959002129	FlowBean{upFlow=1938, downFlow=180, sumFlow=2118}
18271575951	FlowBean{upFlow=1527, downFlow=2106, sumFlow=3633}
18390173782	FlowBean{upFlow=9531, downFlow=2412, sumFlow=11943}
84188413	FlowBean{upFlow=4116, downFlow=1432, sumFlow=5548}