手机流量统计项目

一、任务需求

统计每个手机号上行流量和、下行流量和、总流量和（上行流量和+下行流量和），并且：将统计结果按照手机号的前缀
进行区分，并输出到不同的输出文件中去。如：
13* ==> ..
15* ==> ..
other ==> ..
其中，access.log数据文件
第二个字段：手机号
倒数第三个字段：上行流量
倒数第二个字段：下行流量

部分数据文件：

二、项目思路

（1）自定义Access类
包括属性：手机号、上行流量、下行流量、总流量
 
（2）自定义Map任务类（Map Task）
对每一行日志内容进行拆分，Map输出数据为：
phone==>Access(手机号,该行手机号的上行流量,该行手机号的
下行流量)
 
（3）编写Reduce任务类（Reduce Task）
对每个手机号的流量进行汇总，Map输出数据为：
phone==>Access(手机号,上行流量和,下行流量和)
也可以优化为：
phone==>Access(NullWritable对象,上行流量和,下行流量和)
 
（4）编写分区处理类
继承org.apache.hadoop.mapreduce.Partitioner
类，"13"开头的手机号交给第一个ReduceTask任务处理，最终
输出到0号分区，"15"开头的手机号交给第二个ReduceTask任
务处理，最终输出到1号分区，其余手机号交给第三个
ReduceTask任务处理，最终输出到2号分区。

三、代码实现

1.Access类

​
package org.mapreduce;

import org.apache.hadoop.io.Writable;

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

//1实现writable方法
public class Access implements Writable{

    private long upflow;
    private long downflow;
    private long sumflow;

    //必须要有空参构造，为了以后反射用
    public Access() {
        super();
    }


    public Access(long upflow, long downflow) {
        super();
        this.upflow = upflow;
        this.downflow = downflow;
        this.sumflow = upflow+downflow;
    }

    public void set(long upflow, long downflow) {
        this.upflow = upflow;
        this.downflow = downflow;
        this.sumflow = upflow+downflow;
    }
    //序列化的方法
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upflow);
        out.writeLong(downflow);
        out.writeLong(sumflow);

        //反序列化方法
        //注意序列化方法和反序列化方法顺序必须保持一致
    }
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upflow=in.readLong();
        this.downflow=in.readLong();
        this.sumflow=in.readLong();
    }


    @Override
    public String toString() {
        return  upflow + "\t" + downflow + "\t" + sumflow;
    }



    public void setUpflow(long upflow) {
        this.upflow = upflow;
    }

    public long getUpflow() {
        return 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;
    }


}

​

2.FlowMapper类

package org.mapreduce;

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

import java.io.IOException;


public class FlowMapper extends Mapper<LongWritable, Text, Text, Access>{
    Text k=new Text();
    Access v=new Access();
    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String line=value.toString();
        String[] fields=line.split("\t");
        String phNum=fields[1];
        long upFlow=Long.parseLong(fields[fields.length-3]);
        long downFlow=Long.parseLong(fields[fields.length-2]);

        k.set(phNum);
        v.set(upFlow,downFlow);
        context.write(k, v);
    }
}

3.FlowReducer类

package org.mapreduce;

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

import java.io.IOException;


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

    @Override
    protected void reduce(Text key, Iterable<Access> values, Context context)
            throws IOException, InterruptedException {
        long sumUpFlow=0;
        long sumDownFlow=0;
        System.out.println(values);
        for (Access access : values) {
            sumUpFlow+= access.getUpflow();
            sumDownFlow+= access.getDownflow();
        }
        Access v=new Access(sumUpFlow,sumDownFlow);
        context.write(key, v);
    }
}

4.FlowDriver类

package org.mapreduce;

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 FlowDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        if (args.length < 2) {
            System.err.println("Usage: FlowDriver <inputPath> <outputPath>");
            System.exit(1);
        }

        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration, "Flow Calculation");

        job.setJarByClass(FlowDriver.class);

        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Access.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Access.class);

        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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

5.FlowHDFSApp类

package org.mapreduce;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.net.URI;

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

        System.setProperty("HADOOP_USER_NAME", "root");

        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://hadoop102:8020");


        // 创建一个Job
        Job job = Job.getInstance(configuration);

        // 设置Job对应的参数: 主类
        job.setJarByClass(FlowHDFSApp.class);

        // 设置Job对应的参数: 设置自定义的Mapper和Reducer处理类
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        // 添加Combiner的设置即可
        job.setCombinerClass(FlowReducer.class);

        // 设置Job对应的参数: Mapper输出key和value的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 设置Job对应的参数: Reduce输出key和value的类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 如果输出目录已经存在，则先删除
        FileSystem fileSystem = FileSystem.get(new URI("hdfs://hadoop102:8020"),configuration, "root");
        Path outputPath = new Path("/user/output");
        if(fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath,true);
        }

        // 设置Job对应的参数: Mapper输出key和value的类型：作业输入和输出的路径
        FileInputFormat.setInputPaths(job, new Path("hdfs://hadoop102:8020/user/input.txt"));
        FileOutputFormat.setOutputPath(job, outputPath);

        // 提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : -1);

    }
}

6.PhonePartitioner类

package org.mapreduce;

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

public class PhonePartitioner extends Partitioner<Text, Access> {
    @Override
    public int getPartition(Text key, Access value, int numPartitions) {
        String phonePrefix = key.toString().substring(0, 2);
        switch (phonePrefix) {
            case "13":
                return 0;
            case "15":
                return 1;
            default:
                return 2;
        }
    }
}

四、结果展示

在本次实验中，要注意数据文件上传HDFS文件系统的方法，以及idea的maven环境配置；输出文件的路径要正确。