MapReduce怎么處理手機通信流量統計

本篇內容主要講解“MapReduce怎么處理手機通信流量統計”，感興趣的朋友不妨來看看。本文介紹的方法操作簡單快捷，實用性強。下面就讓小編來帶大家學習“MapReduce怎么處理手機通信流量統計”吧!

模擬元數據如下 HTTP_20130313143750.dat

1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200

1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200

1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200

1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200

1363157993044 18211575961 94-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99 iface.qiyi.com 視頻網站 15 12 1527 2106 200

1363157995074 84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 20 16 4116 1432 200

1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200

1363157995033 15920133257 5C-0E-8B-C7-BA-20:CMCC 120.197.40.4 sug.so.# 信息安全 20 20 3156 2936 200

1363157983019 13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 4 0 240 0 200

1363157984041 13660577991 5C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4 s19.# 站點統計 24 9 6960 690 200

1363157973098 15013685858 5C-0E-8B-C7-F7-90:CMCC 120.197.40.4 rank.ie.sogou.com 搜索引擎 28 27 3659 3538 200

1363157986029 15989002119 E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99 www.umeng.com 站點統計 3 3 1938 180 200

1363157992093 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 15 9 918 4938 200

1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 3 3 180 180 200

1363157984040 13602846565 5C-0E-8B-8B-B6-00:CMCC 120.197.40.4 2052.flash3-http.qq.com 綜合門戶 15 12 1938 2910 200

1363157995093 13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 12 12 3008 3720 200

1363157982040 13502468823 5C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99 y0.ifengimg.com 綜合門戶 57 102 7335 110349 200

1363157986072 18320173382 84-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99 input.shouji.sogou.com 搜索引擎 21 18 9531 2412 200

1363157990043 13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜索引擎 69 63 11058 48243 200

1363157988072 13760778710 00-FD-07-A4-7B-08:CMCC 120.196.100.82 2 2 120 120 200

1363157985079 13823070001 20-7C-8F-70-68-1F:CMCC 120.196.100.99 6 3 360 180 200

1363157985069 13600217502 00-1F-64-E2-E8-B1:CMCC 120.196.100.55 18 138 1080 186852 200

上面日志的格式如下

MapReduce代碼如下

package MapReduce;

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;

public class KpiApp {
    static final String INPUT_PATH = "hdfs://hadoop:9000/wlan";
    static final String OUT_PATH = "hdfs://hadoop:9000/outwlan";
    public static void main(String[] args) throws Exception{
        final Job job = new Job(new Configuration(), KpiApp.class.getSimpleName());
        //1.1 指定輸入文件路徑
        FileInputFormat.setInputPaths(job, INPUT_PATH);
        //指定哪個類用來格式化輸入文件
        job.setInputFormatClass(TextInputFormat.class);
        
        //1.2指定自定義的Mapper類
        job.setMapperClass(MyMapper.class);
        //指定輸出<k2,v2>的類型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(KpiWritable.class);
        
        //1.3 指定分區類
        job.setPartitionerClass(HashPartitioner.class);
        job.setNumReduceTasks(1);
        
        //1.4 TODO 排序、分區
        
        //1.5  TODO （可選）合并
        
        //2.2 指定自定義的reduce類
        job.setReducerClass(MyReducer.class);
        //指定輸出<k3,v3>的類型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(KpiWritable.class);
        
        //2.3 指定輸出到哪里
        FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
        //設定輸出文件的格式化類
        job.setOutputFormatClass(TextOutputFormat.class);
        
        //把代碼提交給JobTracker執行
        job.waitForCompletion(true);
    }

    static class MyMapper extends Mapper<LongWritable, Text, Text, KpiWritable>{
        protected void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper<LongWritable,Text,Text,KpiWritable>.Context context) throws IOException ,InterruptedException {
            final String[] splited = value.toString().split("\t");
            final String msisdn = splited[1];
            final Text k2 = new Text(msisdn);
            final KpiWritable v2 = new KpiWritable(splited[6],splited[7],splited[8],splited[9]);
            context.write(k2, v2);
        };
    }
    
    static class MyReducer extends Reducer<Text, KpiWritable, Text, KpiWritable>{
        /**
         * @param    k2    表示整個文件中不同的手機號碼    
         * @param    v2s    表示該手機號在不同時段的流量的集合
         */
        protected void reduce(Text k2, java.lang.Iterable<KpiWritable> v2s, org.apache.hadoop.mapreduce.Reducer<Text,KpiWritable,Text,KpiWritable>.Context context) throws IOException ,InterruptedException {
            long upPackNum = 0L;
            long downPackNum = 0L;
            long upPayLoad = 0L;
            long downPayLoad = 0L;
            
            for (KpiWritable kpiWritable : v2s) {
                upPackNum += kpiWritable.upPackNum;
                downPackNum += kpiWritable.downPackNum;
                upPayLoad += kpiWritable.upPayLoad;
                downPayLoad += kpiWritable.downPayLoad;
            }
            
            final KpiWritable v3 = new KpiWritable(upPackNum+"", downPackNum+"", upPayLoad+"", downPayLoad+"");
            context.write(k2, v3);
        };
    }
}

class KpiWritable implements Writable{
    long upPackNum;
    long downPackNum;
    long upPayLoad;
    long downPayLoad;
    
    public KpiWritable(){}
    
    public KpiWritable(String upPackNum, String downPackNum, String upPayLoad, String downPayLoad){
        this.upPackNum = Long.parseLong(upPackNum);
        this.downPackNum = Long.parseLong(downPackNum);
        this.upPayLoad = Long.parseLong(upPayLoad);
        this.downPayLoad = Long.parseLong(downPayLoad);
    }
    
    
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upPackNum = in.readLong();
        this.downPackNum = in.readLong();
        this.upPayLoad = in.readLong();
        this.downPayLoad = in.readLong();
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upPackNum);
        out.writeLong(downPackNum);
        out.writeLong(upPayLoad);
        out.writeLong(downPayLoad);
    }
    
    @Override
    public String toString() {
        return upPackNum + "\t" + downPackNum + "\t" + upPayLoad + "\t" + downPayLoad;
    }
}

將HTTP_20130313143750.dat上傳至hadoop HDFS文件系統中

運行MapReduce代碼，查看輸出的/outwlan/part-*文件下的內容

到此，相信大家對“MapReduce怎么處理手機通信流量統計”有了更深的了解，不妨來實際操作一番吧！這里是億速云網站，更多相關內容可以進入相關頻道進行查詢，關注我們，繼續學習！