MapReduce部分排序案例

案例需求：

输入数据：

要求：

计算每行总上行流量，并把手机号前三位相同的数据输出到同一个文件中，并按照总流量从大到小排序

输出结果：

三个文件

 

 

 

导包：

<dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>2.10.0</version>
        </dependency>

    </dependencies>

 FlowBean类：

主要是重写compareTo方法实现排序

这里需要注意的是排序默认的是按照map输出的key来排序，所以一定把要排序的类作为key

实现的是WritableComparable，而不是WritableComparator，别记错了

import org.apache.hadoop.io.WritableComparable;

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

public class FlowBean implements WritableComparable<FlowBean> {
    long phone;
    long upFlow;
    long downFlow;
    long totalFlow;

    public FlowBean() {
        super();
    }


    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(phone);
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(totalFlow);

    }

    public void readFields(DataInput dataInput) throws IOException {
        phone = dataInput.readLong();
        upFlow=dataInput.readLong();
        downFlow=dataInput.readLong();
        totalFlow=dataInput.readLong();
    }

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

    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 getTotalFlow() {
        return totalFlow;
    }

    public void setTotalFlow(long totalFlow) {
        this.totalFlow = totalFlow;
    }

    public long getPhone() {
        return phone;
    }

    public void setPhone(long phone) {
        this.phone = phone;
    }

    public int compareTo(FlowBean o) {
//        return this.getTotalFlow()>o.getTotalFlow()?-1:1;
        if(totalFlow>o.getTotalFlow())
            return -1;
        else if (totalFlow<o.getTotalFlow())
            return 1;
        else
            return 0;
    }
}

MyMapper类：

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

import java.io.IOException;

public class MyMapper extends Mapper<LongWritable,Text, FlowBean,NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line=value.toString();
        String[] s = line.split("\\t");


        FlowBean k = new FlowBean();
        k.setPhone(Long.parseLong(s[0]));

        k.setUpFlow(Long.parseLong(s[1]));

        k.setDownFlow(Long.parseLong(s[2]));

        k.setTotalFlow(k.getDownFlow()+k.getUpFlow());

        context.write(k,NullWritable.get());


    }
}

MyReducer类：

mport org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class MyReducer extends Reducer<FlowBean,NullWritable, FlowBean,NullWritable> {

    @Override
    protected void reduce(FlowBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        context.write(key,NullWritable.get());
    }
}

MyPartitioner类：

Partitioner泛型参数即map输出的看k，v类型

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Partitioner;

public class MyPartitioner extends Partitioner<FlowBean,NullWritable> {


    public int getPartition(FlowBean flowBean, NullWritable nullWritable, int i) {
        int partition=0;
        if(flowBean.getPhone()==186)
            partition=0;
        else if(flowBean.getPhone()==158)
            partition=1;
        else
            partition=2;
        return partition;
    }
}

MyDriver类：

分区主要：

job.setPartitionerClass(MyPartitioner.class);设定分区类

 job.setNumReduceTasks(3);设置分区个数

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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 MyDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(MyDriver.class);

        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);

//        job.setMapOutputKeyClass(LongWritable.class);
//        job.setMapOutputValueClass(FlowBean.class);

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

        job.setPartitionerClass(MyPartitioner.class);
        job.setNumReduceTasks(3);


        FileInputFormat.addInputPath(job,new Path("/home/hadoop/temp/phone_info.txt"));
        FileOutputFormat.setOutputPath(job,new Path("/home/hadoop/temp/phone_info_Partition"));

        FileSystem.get(conf).delete(new Path("/home/hadoop/temp/phone_info_Partition"),true);


        boolean b = job.waitForCompletion(true);

        System.exit(b?0:1);
    }
}