MapReduce实践—流量统计(大数据学习12)

最新推荐文章于 2023-01-08 18:43:32 发布

3分钟秒懂大数据

最新推荐文章于 2023-01-08 18:43:32 发布

阅读量950

点赞数

分类专栏： MapReduce

本文链接：https://blog.csdn.net/weixin_38201936/article/details/88125680

版权

MapReduce 专栏收录该内容

6 篇文章 1 订阅

订阅专栏

FlowCount示例编写

需求：在一堆给定的文本文件中统计出每个用户的上行流量和下行流量

使用IDEA编写代码：定义三个类分别为：FlowCount，FlowCountMapper，FlowCountReducer

package com.lyz.bigdata.mr.flowsun;


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.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.output.FileOutputFormat;

import java.io.IOException;

/**
 *@Author:759057893@qq.com Lyz
 *@Date: 2019/2/28 21:28
 *@Description:
 **/
public class FlowCount {

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

        @Override
        protected  void map(LongWritable key, Text value,Context context) throws IOException, InterruptedException{
            //将一行内容转成string
            String line =value.toString();
            //切分字段
            String[] fields =line.split("\t");
            //取出手机号
            String phone =fields[1];
            //取出上行流量下行流量
            long upFlow = Long.parseLong(fields[fields.length-3]);
            long dFlow = Long.parseLong(fields[fields.length-2]);

            context.write(new Text(phone),new FlowBean(upFlow,dFlow));
        }

    }


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

        @Override
        protected  void reduce(Text key,Iterable<FlowBean> values,Context context) throws IOException, InterruptedException{

            long sum_upFlow = 0;
            long sum_dFlow = 0;

            //遍历所有bean，将其中的上行流量，下行流量分别累加
            for(FlowBean  bean :values){
                sum_upFlow +=  bean.getUpFlow();
                sum_dFlow  += bean.getdFlow();
            }

             FlowBean resultBean    =   new FlowBean(sum_upFlow,sum_dFlow);
            context.write(key,resultBean);


        }

    }

    public static void main(String[] args) throws Exception {

        // 1 获取job信息
        Configuration configuration = new Configuration();

        Job job = Job.getInstance(configuration);

        // 2 获取jar包位置
        job.setJarByClass(FlowCount.class);

        // 3 关联自定义的mappper和reducer
        job.setMapperClass(FlowCountMapper.class);
        job.setReducerClass(FlowCountReducer.class);

        // 4 设置map输出数据类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        // 5 设置最终输出数据类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);


        // 6 设置数据输入和输出文件路径
        FileInputFormat.setInputPaths(job,  new Path(args[0]));
        FileOutputFormat.setOutputPath(job,  new Path(args[1]));

        // 7 提交代码
        // job.submit();
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }

}

定义一个对象，将上行流量和下行流量封装到对象中

package com.lyz.bigdata.mr.flowsun;/**
 * @Author:759057893@qq.com Lyz
 * @Date: ${Date} 21:31
 * @Description:
 **/

import org.apache.hadoop.io.Writable;

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

/**
 *@Author:759057893@qq.com Lyz
 *@Date: 2019/2/28 21:31
 *@Description:
 **/
public class FlowBean implements Writable {

    private long upFlow;
    private long dFlow;
    private long sumFlow;

    public FlowBean() { }

    public long getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(long upFlow) {
        this.upFlow = upFlow;
    }

    public long getdFlow() {
        return dFlow;
    }

    public void setdFlow(long dFlow) {
        this.dFlow = dFlow;
    }

    public long getSumFlow() {
        return sumFlow;
    }

    public void setSumFlow(long sumFlow) {
        this.sumFlow = sumFlow;
    }

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

    @Override
    public String toString() {

        return  upFlow + "\t" + dFlow + "\t" + sumFlow;
    }

    /**
     * 序列化方法
     */
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(dFlow);
        out.writeLong(sumFlow);

    }

    /**
     * 反序列化方法
     * 注意：反序列化的顺序跟序列化的顺序完全一致
     */
    @Override
    public void readFields(DataInput in) throws IOException {
        upFlow = in.readLong();
        dFlow = in.readLong();

    }


}

然后用IDEA进行打包打包方式请看博主写的https://blog.csdn.net/weixin_38201936/article/details/88018493 文章

打包成功后首先在hdfs 中创建文件

hadoop fs -mkdir -p /flowsum/input

创建成功后在网页上查看是否创建成功

然后创建一个文件，将需要统计的数据集粘贴进去

vi flow.data 数据集如下

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

保存成功后移入input 文件夹中

hadoop fs -put flow.data /flowsum/input

将打包成功的jar 包移动到集群中，并运行

hadoop jar hadoop.jar /flowsum/input /flowsum/output

在这里说明一下由于idea 打jar的时候已经将main方法打入jar包，所以已经指定了main方法在这里就不用添加类名的指向路径

上面的执行成功后

统计完成：统计结果如下：

3分钟秒懂大数据

关注

0
点赞
踩
9

收藏

觉得还不错? 一键收藏
打赏
2
评论
MapReduce实践—流量统计(大数据学习12)

FlowCount示例编写需求：在一堆给定的文本文件中统计出每个用户的上行流量和下行流量使用IDEA编写代码：定义三个类分别为：FlowCount，FlowCountMapper，FlowCountReducerpackage com.lyz.bigdata.mr.flowsun;import org.apache.hadoop.conf.Configuration;...
复制链接

扫一扫