统计每一个用户所耗费的总上行流量，下行流量，总流量

最新推荐文章于 2024-07-09 09:08:22 发布

chenyanlong_v

最新推荐文章于 2024-07-09 09:08:22 发布

阅读量1.4k

点赞数 2

如有不足，欢迎纠正

本文链接：https://blog.csdn.net/longyanchen/article/details/96835494

版权

数据：

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	视频网站	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.360.cn	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.cnzz.com	站点统计	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	站点统计	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.flash2-http.qq.com	综合门户	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	综合门户	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
1363157985066 	13726238888	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157993055 	13560436666	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200

需求：

思路分析：

具备知识：

FlowBean javabean

添加代码：

package cn.itcast.mapreduce.flowcount;

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  totalFlow;

    public FlowBean() {
    }

    public FlowBean(long upFlow, long downFlow, long totalFlow) {
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.totalFlow = totalFlow;
    }

    //与map对应
    public FlowBean(long upFlow, long downFlow) {
        this.upFlow=upFlow;
        this.downFlow=downFlow;
        this.totalFlow=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 getTotalFlow() {
        return totalFlow;
    }

    public void setTotalFlow(long totalFlow) {
        this.totalFlow = totalFlow;
    }

    /**
     *
     * @param dataOutput
     * @throws IOException
     */
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(totalFlow);
    }

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

    //reduce需要使用
    public void set(long upFlow, long downFlow) {
        this.upFlow= upFlow;
        this.downFlow=downFlow;
        this.totalFlow=upFlow+downFlow;
    }


   /* @Override
    public String toString() {
        return "FlowBean{" +
                "upFlow=" + upFlow +
                ", downFlow=" + downFlow +
                ", totalFlow=" + totalFlow +
                '}';
    }*/
   @Override
   public String toString() {
       return upFlow+"\t" +downFlow+"\t" +totalFlow ;
   }
}

FlowCountMapper:

优化一下：

package cn.itcast.mapreduce.flowcount;

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

import java.io.IOException;

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

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] fields = line.split("\t");

        String phoNum = fields[1];

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

        context.write(new Text(phoNum),new FlowBean(upFlow,downFlow));
    }
}

FlowCountReducer:

package cn.itcast.mapreduce.flowcount;

import cn.itcast.mapreduce.flowsum1.WordCountMapper;
import cn.itcast.mapreduce.flowsum1.WordCountMapperReducer;
import cn.itcast.mapreduce.flowsum1.WordCountRunner;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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 FlowCountRunner {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1.配置参数，用于指定mr运行时相关的参数属性
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "wordcount");

        //2.指定mr运行的类
        job.setJarByClass(FlowCountRunner.class);

        //3.指定mr程序的m，r类
        job.setMapperClass(FlowCountMapper.class);
        job.setReducerClass(FlowCountReducer.class);


        //4指定map输出kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //指定ruduce输出的kv类型，也就是mr的最终输出结果
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //指定mr程序的输出路径
        FileInputFormat.addInputPath(job,new Path("D:\\data\\input"));
        FileOutputFormat.setOutputPath(job,new Path("D:\\data\\output_2"));


        boolean result = job.waitForCompletion(true);//提交mr程序，并且开始任务执行监控的功能
        //如果mr程序执行成功，退出0，否则1
        System.exit(result?0:1);

    }
}

本地模式运行：