MapReduce 基础 （三）分区

概念

在 MapReduce 中, 通过我们指定分区, 会将同一个分区的数据发送到同一个 Reduce 当中进行 处理

例如: 为了数据的统计, 可以把一批类似的数据发送到同一个 Reduce 当中, 在同一个 Reduce 当 中统计相同类型的数据, 就可以实现类似的数据分区和统计等

其实就是相同类型的数据, 有共性的数据, 送到一起去处理

Reduce 当中默认的分区只有一个

image

案例：
将表中的数据分区成两组，一组是中奖结果大于15的分区查询，一组的中奖结果小于15的分区查询。

PartitionReducer

package Partitioner;

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

import java.io.IOException;

public class PartitionReducer extends Reducer<Text, NullWritable, Text,NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        context.write(key,NullWritable.get());
    }
}

PartitionMapper

package Partitioner;

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 PartitionMapper extends Mapper<LongWritable,Text, Text, NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        context.write(value,NullWritable.get());
    }
}

Partition

package Partitioner;

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

public class PartitonerOwn extends Partitioner<Text, NullWritable> {

    @Override
    public int Partition(Text text, NullWritable nullWritable, int i) {
        //1:拆分行文本数据(K2),获取中奖字段的值
        String[] split = text.toString().split("\t");
        String numStr = split[5];

        //2:判断中奖字段的值和15的关系，然后返回对应的分区编号
        if(Integer.parseInt(numStr) > 15){
            return  1;
        }else{
            return  0;
        }
    }
}

main

package Partitioner;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
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;

import java.net.URI;

public class MainJob extends Configured implements Tool {

    @Override
    public int run(String[] strings) throws Exception {

        //1.创建job任务对象
        Job job = Job.getInstance(super.getConf(), "partition_mapreduce");

        //2.对job任务进行配置(八个步骤)

        //1）设置输入类和路径
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("hdfs://node1:8020/input"));
        
        //2) 设置mapper类
        job.setMapperClass(PartitionerMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        
        //3) 指定分区类
        job.setPartitionerClass(PartitonerOwn.class);
        
        //7) 指定Reducer类
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        
        //设置reduceTask个数
        job.setNumReduceTasks(2);

        //8）指定输出类和路径
        Path path = new Path("hdfs://node1:8020/out/partition_out");
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,path);

        FileSystem fileSystem = FileSystem.get(new URI("hdfs://node1:8020/out/partition_out"),new Configuration());
        if (fileSystem.exists(path)){
            fileSystem.delete(path,true);
        }

        //3.等待任务执行
        boolean bl = job.waitForCompletion(true);
        return bl?0:1;
    }

    public static void main(String[] args) throws Exception{
        Configuration configuration = new Configuration();
        
        //启动Job任务
        int run = ToolRunner.run(configuration,new MainJob(),args);

        System.exit(run);
    }
}