第二个案例实操——创建Bean类

1.需求：

准备一个phone_data.txt文档，内容如下：

1	13736230513	192.196.100.1	www.atguigu.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.atguigu.com	1527	2106	200
6 	84188413	192.168.100.3	www.atguigu.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.atguigu.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

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

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

2.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.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
7 	13560436666	120.196.100.99		1116		 954			200
(2)抽取手机号、上行流量、下行流量
13560436666	1116 954
(3)以手机号key,bean对象为value输出，即context.write(手机号,bean) 注：bean对象实现序列化才能传输

5.Reduce阶段
累加上行流量和下行流量得到总流量
13560436666 1116 + 954 = 2070
手机号码	上行流量 下行流量 总流量

3.编程实现

创建包名：com.yingzi.mapreduce.writable

3.1.创建Bean类

package com.yingzi.mapreduce.writable;

/**
 * @author 影子
 * @create 2022-01-13-15:57
 **/

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


/**
 * 1、定义类实现writable接口
 * 2、重写序列化和反序列化方法
 * 3、重写空参构造
 * 4、toString方法
 */
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

    //  空参构造
    public FlowBean(){
    }

    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;
    }

    @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();
    }

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

3.2.创建Mapper类

package com.yingzi.mapreduce.writable;

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

import java.io.IOException;

/**
 * @author 影子
 * @create 2022-01-13-16:12
 **/
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, Mapper<LongWritable, Text, Text, FlowBean>.Context context) throws IOException, InterruptedException {

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

        //  2.切割
        //  1,13736230513,192.196.100.1,www.atguigu.com	2481,24681,200
        String[] split = line.split("\t");

        //  3.抓取想要的数据
        //  手机号：13736230513
        //  上行流量：2481 下行流量：24681
        String phone = split[1];
        String up = split[split.length - 3];
        String down = split[split.length - 2];

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

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

3.3.创建Reducer类

package com.yingzi.mapreduce.writable;

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

import java.io.IOException;

/**
 * @author 影子
 * @create 2022-01-13-16:32
 **/
public class FlowReducer extends Reducer<Text,FlowBean,Text,FlowBean>{

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

        //  1.遍历集合累加值
        long totalUp = 0;
        long totalDown = 0;
        for (FlowBean value : values) {
            totalUp += value.getUpFlow();
            totalDown += value.getDownFlow();
        }
        //  2.封装outK,outV
        outV.setUpFlow(totalUp);
        outV.setDownFlow(totalDown);
        outV.setSumFlow();

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

3.4.创建Driver类

package com.yingzi.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;


/**
 * @author 影子
 * @create 2022-01-13-16:40
 **/
public class FlowDriver {

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

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

        //  2.设置jar
        job.setJarByClass(FlowDriver.class);

        //  3.关联Mapper、Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //  4.设置mapper,输出的key和value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //  5.设置最终数据输出的key和value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //  6.设置数据的输入和输出路径
        FileInputFormat.setInputPaths(job,new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\11_input\\inputflow"));
        FileOutputFormat.setOutputPath(job,new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\_output\\output1"));

        //  7.提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0:1);

    }
}

4.查看结果

说明：上传至集群同第一个案例最后操作一样，就不再操作了
链接如下：https://blog.csdn.net/mynameisgt/article/details/122484444