大資料開發之Mapper Reduce序列化案例實操

1. 統計每一個手機號耗費的總上行流量、下行流量、總流量
   （1）輸入資料

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

編寫MapReduce程式

（1）編寫流量統計的Bean物件

package MRS.xuleihua;

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

import org.apache.hadoop.io.Writable;

public class FlowBean implements Writable {

    private long upFlow;// 上行流量
    private long downFlow;// 下行流量
    private long sumFlow;// 總流量

    // 空參構造， 為了後續反射用
    public FlowBean() {
        super();
    }

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

    // 序列化方法
    @Override
    public void write(DataOutput out) throws IOException {

        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

    // 反序列化方法
    @Override
    public void readFields(DataInput in) throws IOException {
        // 必須要求和序列化方法順序一致
        upFlow = in.readLong();
        downFlow = in.readLong();
        sumFlow = in.readLong();
    }

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

    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 upFlow2, long downFlow2) {

        upFlow = upFlow2;
        downFlow = downFlow2;
        sumFlow = upFlow2 + downFlow2;

    }
}

（2）編寫Mapper類

package MRS.xuleihua;

import java.io.IOException;

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

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

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

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 7 13560436666 120.196.100.99 1116 954 200

        // 1 獲取一行
        String line = value.toString();

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

        // 3 封裝物件
        k.set(fields[1]);// 封裝手機號

        long upFlow = Long.parseLong(fields[fields.length - 3]);
        long downFlow = Long.parseLong(fields[fields.length - 2]);

        v.setUpFlow(upFlow);
        v.setDownFlow(downFlow);
//		v.set(upFlow,downFlow);

        // 4 寫出
        context.write(k, v);
    }
}

（3）編寫Reducer類

package MRS.xuleihua;

import java.io.IOException;

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

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

    FlowBean v = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context)
            throws IOException, InterruptedException {
//		13568436656	2481	24681    30000
//		13568436656	1116	954	 20000

        long sum_upFlow = 0;
        long sum_downFlow = 0;

        // 1 累加求和
        for (FlowBean flowBean : values) {

            sum_upFlow += flowBean.getUpFlow();
            sum_downFlow += flowBean.getDownFlow();
        }

        v.set(sum_upFlow, sum_downFlow);

        // 2 寫出
        context.write(key, v);
    }
}

（4）編寫Driver驅動類

package MRS.xuleihua;

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 {
        args = new String[]{"/home/master/Documents/app/demo/","/home/master/Documents/app/output013"};

        Configuration conf = new Configuration();
        //獲取job物件
        Job job = Job.getInstance(conf);
        //設定jar路徑
        job.setJarByClass(FlowsumDriver.class);
        //關聯mapper和reducer
        job.setMapperClass(FlowCountMapper.class);
        job.setReducerClass(FlowCountReducer.class);
        //設定最終輸出key和value
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        //設定輸入輸出路徑
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result?0 :1);
    }
}