大数据-统计每一个手机号耗费的总上行流量、下行流量、总流量

一、需求

根据数据日志统计每一个手机号耗费的总上行流量、下行流量、总流量

二、数据准备

1、输入数据

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

2、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

三、使用idea创建一个Maven项目

如果大家还不知道怎么创建一个Maven项目，可以自行百度以下，这里不在过多叙述。
下面这是我的一个普通的Maven项目

pom.xml文件

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.zhenghui</groupId>
    <artifactId>hdfs</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <hadoop.version>2.8.0</hadoop.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.7</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.7</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.7</version>
        </dependency>
    </dependencies>

</project>

创建如下文件

FlowBean.java文件

package com.zhenghui.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 long upFlow;

    private long downFlow;

    private long sumFlow;

    public FlowBean() {
    }

    public void set(long upFlow, long downFlow){
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow + downFlow;
    }

    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;
    }

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

    /**
     * 序列化方法
     * @param out  框架给我们提供的数据出口
     * @throws IOException
     */
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

    /**
     * 反序列化方法
     * @param in 框架提供的数据来源
     * @throws IOException
     */
    public void readFields(DataInput in) throws IOException {
        //顺序：怎么序列化的顺序就应该怎么反序列化的顺序
        upFlow = in.readLong();
        downFlow = in.readLong();
        sumFlow = in.readLong();
    }


}

FlowDriver.java文件

package com.zhenghui.flow;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 FlowDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1、获取一个Job实例
        Job job = Job.getInstance(new Configuration());

        //2、设置我们的类路径CLasspath
        job.setJarByClass(FlowDriver.class);

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

        //4、设置Mapper和Reducer的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //5、设置输入输出数据
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        //6、提交我们的Job
        boolean b = job.waitForCompletion(true);

        System.exit(b?0:1);

    }

}

FlowMapper.java文件

package com.zhenghui.flow;

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

import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class FlowMapper extends Mapper<LongWritable, Text,Text,FlowBean> {

    private Text phone = new Text();
    private FlowBean flow = new FlowBean();


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

        String data = value.toString();
        System.out.println("line="+data);
        //1	13736230513	192.196.100.1 www.atguigu.com 2481 24681 200
        String[] s = data.split(",");
        System.out.println("手机号："+s[1]);
        phone.set(s[1]);
        long upFlow = Long.parseLong(s[s.length - 3]);
        long downFlow = Long.parseLong(s[s.length - 2]);

        flow.set(upFlow,downFlow);

        context.write(phone,flow);
    }
}

FlowReducer.java文件

package com.zhenghui.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> {

    private FlowBean sumFlow = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        long sumUpFlow = 0;
        long sumDownFlow = 0;

        for (FlowBean value : values) {
            sumUpFlow += value.getUpFlow();
            sumDownFlow += value.getDownFlow();
        }

        sumFlow.set(sumUpFlow,sumDownFlow);

        context.write(key,sumFlow);
    }

}

设置数据源

windows10 中idea中的运行结果