hadoop之MapReduce上网流量统计（3）

最新推荐文章于 2020-03-05 18:05:21 发布
winnertakeall
最新推荐文章于 2020-03-05 18:05:21 发布
阅读量258
点赞数 1
CC 4.0 BY-SA版权
本文链接：https://blog.youkuaiyun.com/winnertakeall/article/details/98515463
本文介绍了一种使用Hadoop进行手机号码流量分析的方法，包括自定义FlowBean类以存储流量数据，通过FlowMapper解析输入数据，使用PhonePartition按手机号前缀分区，以及FlowReducer汇总流量信息。
摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >
需求三：手机号码分区

FlowBean:
import org.apache.hadoop.io.Writable;

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

/**
 * 这里暂时不需要做排序，所以直接实现writable接口就可以了
 */
public class FlowBean implements Writable {

    //上行流量
    private Integer  upFlow;
    //下行流量
    private Integer  downFlow;
    //上行总流量
    private Integer  upCountFlow;
    //下行总流量
    private Integer  downCountFlow;

    @Override
    public String toString() {
        return upFlow+"\t"+downFlow+"\t"+upCountFlow+"\t"+downCountFlow;
    }

    public Integer getUpFlow() {
        return upFlow;
    }

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

    public Integer getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(Integer downFlow) {
        this.downFlow = downFlow;
    }

    public Integer getUpCountFlow() {
        return upCountFlow;
    }

    public void setUpCountFlow(Integer upCountFlow) {
        this.upCountFlow = upCountFlow;
    }

    public Integer getDownCountFlow() {
        return downCountFlow;
    }

    public void setDownCountFlow(Integer downCountFlow) {
        this.downCountFlow = downCountFlow;
    }

    /**
     * 序列化方法
     * @param out
     * @throws IOException
     */
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(upFlow);
        out.writeInt(downFlow);
        out.writeInt(upCountFlow);
        out.writeInt(downCountFlow);

    }

    /**
     * 反序列化的方法
     * @param in
     * @throws IOException
     */
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readInt();
        this.downFlow = in.readInt();
        this.upCountFlow = in.readInt();
        this.downCountFlow = in.readInt();
    }
}






FlowMapper:
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,FlowBean> {

//1363157985066	13726230503	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com	游戏娱乐	24	27	2481	24681	200
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] split = value.toString().split("\t");
        String phoneNum = split[1];
        String upFlow = split[6];
        String downFlow = split[7];
        String upCountFlow = split[8];
        String downCountFlow = split[9];
        FlowBean flowBean = new FlowBean();
        flowBean.setUpFlow(Integer.parseInt(upFlow));
        flowBean.setDownFlow(Integer.parseInt(downFlow));
        flowBean.setUpCountFlow(Integer.parseInt(upCountFlow));
        flowBean.setDownCountFlow(Integer.parseInt(downCountFlow));

        //往下一阶段写出我们的数据，key2  是手机号  value2  我们自己封装定义的javaBean
        context.write(new Text(phoneNum),flowBean);
    }
}





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

public class PhonePartition extends Partitioner<Text,FlowBean> {

    /**
     * 判断我们的手机号以什么数字开头
     *
     * @param text
     * @param flowBean
     * @param i
     * @return
     */
    @Override
    public int getPartition(Text text, FlowBean flowBean, int i) {
        String phone = text.toString();
        if (phone.startsWith("135")){
            return 0;
        }else if(phone.startsWith("136")){
            return 1;
        }else if (phone.startsWith("137")){
            return 2;
        }else if(phone.startsWith("138")){
            return 3;
        }else if(phone.startsWith("139")){
            return 4;
        }else{
            return 5;
        }

    }
}






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

import java.io.IOException;

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

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

        int  upFlow = 0;
        int downFlow = 0;
        int upCountFlow = 0;
        int downCountFlow = 0;

        for (FlowBean value : values) {
            upFlow += value.getUpFlow();
            downFlow  += value.getDownFlow();
            upCountFlow += value.getUpCountFlow();
            downCountFlow += value.getDownCountFlow();
        }

        //写出去我们的手机号
        FlowBean flowBean = new FlowBean();
        flowBean.setUpFlow(upFlow);
        flowBean.setUpCountFlow(upCountFlow);
        flowBean.setDownFlow(downFlow);
        flowBean.setDownCountFlow(downCountFlow);
        context.write(key,flowBean);
    }
}



FlowMain:
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.SnappyCodec;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class FlowMain extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
        //组装我们的程序运行
        Job job = Job.getInstance(super.getConf(), "flowCount");

        //打包运行的时候，设置我们 的main方法在哪里java文件里面
        job.setJarByClass(FlowMain.class);
        //第一步：读取文件，解析成key,value对
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path(args[0]));

        //第二步：自定义map逻辑
        job.setMapperClass(FlowMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);


        //第三到六步全部省略
        job.setPartitionerClass(PhonePartition.class);




        //第七步：自定义reduce逻辑
        job.setReducerClass(FlowReducer.class);
        //设置reduce的个数为6个，每个reduce刚好处理一个分区里面的数据
        job.setNumReduceTasks(6);

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

        //第八步：输出数据
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path(args[1]));
        boolean b = job.waitForCompletion(true);
        return b?0:1;
    }

    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();
        //开启我们map阶段的数据压缩
        configuration.set("mapreduce.map.output.compress","true");
        configuration.set("mapreduce.map.output.compress.codec", "org.apache.hadoop.io.compress.SnappyCodec");

        //开启我们reduce阶段的数据压缩
        configuration.set("mapreduce.output.fileoutputformat.compress","true");
        configuration.set("mapreduce.output.fileoutputformat.compress.type","RECORD");
        configuration.set("mapreduce.output.fileoutputformat.compress.codec","org.apache.hadoop.io.compress.SnappyCodec");

        int run = ToolRunner.run(configuration, new FlowMain(), args);
        System.exit(run);
    }

}
输出结果：