基于MapReduce的手机流量统计

Zxmmy_77

已于 2024-06-20 22:07:50 修改

阅读量232

点赞数 9

文章标签： mapreduce 大数据

于 2024-06-20 22:03:41 首次发布

本文链接：https://blog.csdn.net/Zxmmy_77/article/details/139843385

版权

Mapreduce案例之—统计手机号耗费的总上行流量、下行流量、总流量。需求是统计每一个手机号耗费的总上行流量、下行流量、总流量。

基本思路：

Map阶段：

读取一行数据，转换为字符串类型
切分字段
抽取手机号、上行流量、下行流量
以手机号为key，bean对象（上行流量、下行流量、总流量）为value 进行封装
文件写出，即context.write(手机号,bean)

Reduce阶段

遍历集合上行流量和下行流量总和得到总流量
实现自定义的bean来封装流量信息，并将bean作为map输出的key来传输
MR程序在处理数据的过程中会对数据排序(map输出的kv对传输到reduce之前，会排序)，排序的依据是map输出的key

1.数据集access.log

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
1363157985066 	13726238888	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	10000	20000	200

2.FlowBean.java

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;

// bean对象要实例化
public class FlowBean implements Writable {

    private long upFlow;
    private long downFlow;
    private long sumFlow;

    // 反序列化时，需要反射调用空参构造函数，所以必须有
    public FlowBean() {
        super();
    }

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

    public long getSumFlow() {
        return sumFlow;
    }

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

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



    @Override
    public void readFields(DataInput in) throws IOException {
        upFlow = in.readLong();
        downFlow = in.readLong();
        sumFlow = in.readLong();
    }

    @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;
    }
}

3.FlowDriver.java

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;


public class FlowDriver {

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

        //1.获取配置信息
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //2.获取jar包信息
        job.setJarByClass(FlowDriver.class);

        //3.配置mapper、reducer类
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //4.配置mapper输出key、value值
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //5.配置输出key、value值
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

//		//设置分区
//		job.setPartitionerClass(FlowPartitioner.class);
//
//		//设置Reducenum,依据是看flowpartitioner里分了几个区
//		job.setNumReduceTasks(5);

        //6.配置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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

4.FlowMapper.java


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

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

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

    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {

        //1.获取一行数据（）
        String line = value.toString();

        //2.截取字段（1、2可归结为一大步：对输入数据的处理）
        String[] fields = line.split("\t");

        //3.封装bean对象，获取电话号码（第二大步：具体的业务逻辑）
        String phoneNum = fields[1];
        long upFlow = Long.parseLong(fields[fields.length - 3]);
        long downFlow = Long.parseLong(fields[fields.length - 2]);
        bean.set(upFlow, downFlow);
        k.set(phoneNum);

        context.write(k, bean);
    }
}

5.FlowReducer.java


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

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

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context)
            throws IOException, InterruptedException {
        //1.计算总的流量
        long sum_upFlow = 0;
        long sum_downFlow = 0;
        for(FlowBean bean : values){
            sum_upFlow += bean.getUpFlow();
            sum_downFlow += bean.getDownFlow();
        }

        //2.输出
        context.write(key, new FlowBean(sum_upFlow,sum_downFlow));
    }
}