Hadoop序列化_大数据系统

1.自定义bean对象实现序列化接口（Writable）

具体实现bean对象序列化步骤如下7步。

（1）必须实现Writable接口

public class FLowBean implements Writable

（2）反序列化时，需要反射调用空参构造函数，所以必须有空参构造

    public FLowBean() {
    }

（3）重写序列化方法

    
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }

（4）重写反序列化方法

    
    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow = dataInput.readLong();
        this.downFlow = dataInput.readLong();
        this.sumFlow = dataInput.readLong();

    }

（5）注意反序列化的顺序和序列化的顺序完全一致

（6）要想把结果显示在文件中，需要重写toString()，可用”t”分开，方便后续用

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

（7）如果需要将自定义的bean放在key中传输，则还需要实现Comparable接口，因为MapReduce框中的Shuffle过程要求对key必须能排序。

    
    @Override
    public int compareTo(FLowBean o) {
        return Long.compare(o.sumFlow,this.sumFlow);
    }

序列化案例实操

1. 需求

统计每一个手机号耗费的总上行流量、下行流量、总流量输出流量使用量在前10的用户信息

（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）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

2.需求分析

1）统计每个手机号的上行流量下行流量总流量

2）输入格式 id 手机号码网络ip 上行流量下行流量网络状态码

3）期望输出数据格式手机号码上行流量下行流量总流量

4）Map阶段 1.拿到一行数据 2.切分 3.封装手机号码上行流量下行流量总流量

5）reduce阶段累加流量

3.编写MapReduce程序

（1）编写流量统计的Bean对象

3.编写MapReduce程序

（1）编写流量统计的Bean对象

package com.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() {
    }

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

    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;
    }

    
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }

    
    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow = dataInput.readLong();
        this.downFlow = dataInput.readLong();
        this.sumFlow = dataInput.readLong();

    }
}

（2）编写Mapper类

package com.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 {

    private Text phone = new Text();
    private FLowBean fLow = new FLowBean();


    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1.拿到1行数据
        String line = value.toString();
        //2.切分
        String[] fields = line.split("t");
        //3.封装
        phone.set(fields[1]);
        fLow.set(
                Long.parseLong(fields[fields.length-3]),
                Long.parseLong(fields[fields.length-2]));
        context.write(phone,fLow);

    }
}

（3）编写Reducer类

package com.flow;

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

import java.io.IOException;

public class FlowReducer extends Reducer {
    private FLowBean flow = new FLowBean();

    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
        //累加流量
        long sumUpFlow = 0;
        long sumDownFlow = 0;

        for (FLowBean value : values) {
            sumUpFlow += value.getUpFlow();
            sumDownFlow += value.getDownFlow();
        }
        //封装flow类型
        flow.set(sumUpFlow, sumDownFlow);

        context.write(key, flow);

    }
}

（4）编写Driver驱动类

package com.flow;

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 FlowDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1.先获取Job实例
        Job job = Job.getInstance(new Configuration());
        //2.设置Jar包
        job.setJarByClass(FlowDriver.class);
        //3.设置Mapper和Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);
        //4.设置Map和Reduce的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FLowBean.class);

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

        //5.设置输入输出文件
        //5-1)设置输入路径
        FileInputFormat.setInputPaths(job,new Path("D:\input\phone_data.txt"));
        FileOutputFormat.setOutputPath(job,new Path("D:\output"));

        //6.提交Job
       boolean b = job.waitForCompletion(true);

        System.exit(b ? 0 : 1);
    }
}

Hadoop序列化

大数据系统相关栏目本月热门文章