如何使用MapReduce实现TopN

版权声明：Please make the source marked https://blog.csdn.net/qq_31807385/article/details/84555034

输出流量使用量在前10的用户信息：数据源：

13470253144	180	180	360
13509468723	7335	110349	117684
13560439638	918	4938	5856
13568436656	3597	25635	29232
13590439668	1116	954	2070
13630577991	6960	690	7650
13682846555	1938	2910	4848
13729199489	240	0	240
13736230513	2481	24681	27162
13768778790	120	120	240
13846544121	264	0	264
13956435636	132	1512	1644
13966251146	240	0	240
13975057813	11058	48243	59301
13992314666	3008	3720	6728
15043685818	3659	3538	7197
15910133277	3156	2936	6092
15959002129	1938	180	2118
18271575951	1527	2106	3633
18390173782	9531	2412	11943
84188413	4116	1432	5548

代码实现：

package com.isea.topN;

import org.apache.hadoop.io.WritableComparable;

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

public class FlowBean implements WritableComparable<FlowBean> {
    private long upFlow;
    private long downFlow;
    private long sumFlow;

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

    public FlowBean() {
    }

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

    public long getSumFlow() {
        return sumFlow;
    }

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

    public void set(long upFlow,long downFlow){
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        sumFlow = upFlow + downFlow;
    }

    @Override
    public int compareTo(FlowBean o) {
        if (this.sumFlow > o.getSumFlow()){
            return -1;
        }else if (this.sumFlow < o.getSumFlow()){
            return 1;
        }else {
            return 0;
        }
    }

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

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

package com.isea.topN;

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

import java.io.IOException;
import java.util.Iterator;
import java.util.TreeMap;

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

    TreeMap<FlowBean,Text> kBeans = new TreeMap<>();
    FlowBean flowBean ;
    Text v ;


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

        flowBean = new FlowBean();
        v = new Text();
        String line = value.toString();

        String[] fields = line.split("\t");
        flowBean.set(Long.parseLong(fields[1]),Long.parseLong(fields[2]));
        v.set(fields[0]);
        kBeans.put(flowBean,v);
        if (kBeans.size() > 10){
            kBeans.remove(kBeans.lastKey());
        }
    }

    @Override
    protected void cleanup(Context context) throws IOException, InterruptedException {
        Iterator<FlowBean> it = kBeans.keySet().iterator();
        while(it.hasNext()){
            FlowBean bean = it.next();
            context.write(bean,kBeans.get(bean));
        }
    }
}

package com.isea.topN;

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

import java.io.IOException;
import java.util.Iterator;
import java.util.TreeMap;

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

    TreeMap<FlowBean,Text> flowBeanTextTreeMap = new TreeMap<>();

    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        FlowBean flowBean = new FlowBean();
        for (Text value : values) {
            flowBean.set(key.getUpFlow(),key.getDownFlow());
            flowBeanTextTreeMap.put(flowBean,value);
        }
        if (flowBeanTextTreeMap.size() > 10){
            flowBeanTextTreeMap.remove(flowBeanTextTreeMap.lastKey());
        }
    }

    @Override
    protected void cleanup(Context context) throws IOException, InterruptedException {
        Iterator<FlowBean> iterator = flowBeanTextTreeMap.keySet().iterator();
        while (iterator.hasNext()){
            FlowBean flowBean = iterator.next();
            context.write(new Text(flowBeanTextTreeMap.get(flowBean)),flowBean);
        }
    }
}

package com.isea.topN;

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 TopNDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args  = new String[]{"g:/input/topN","g:/output3"};

        // 1 获取配置信息，或者job对象实例
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        // 6 指定本程序的jar包所在的本地路径
        job.setJarByClass(TopNDriver.class);

        // 2 指定本业务job要使用的mapper/Reducer业务类
        job.setMapperClass(TopNMapper.class);
        job.setReducerClass(TopNReducer.class);

        // 3 指定mapper输出数据的kv类型
        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(Text.class);

        // 4 指定最终输出的数据的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        // 5 指定job的输入原始文件所在目录
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 7 将job中配置的相关参数，以及job所用的java类所在的jar包， 提交给yarn去运行
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);

    }
}

输出结果：

13560439638	7335	110349	117684
13560439638	11058	48243	59301
13560439638	3597	25635	29232
13560439638	2481	24681	27162
13560439638	9531	2412	11943
13560439638	6960	690	7650
13560439638	3659	3538	7197
13560439638	3008	3720	6728
13560439638	3156	2936	6092
13560439638	918	4938	5856