hadoop学习：mapreduce入门案例四：partitioner 和 combiner

news2024/10/6 8:27:13

先简单介绍一下partitioner 和 combiner

Partitioner类

用于在Map端对key进行分区
- 默认使用的是HashPartitioner
  - 获取key的哈希值
  - 使用key的哈希值对Reduce任务数求模
- 决定每条记录应该送到哪个Reducer处理
自定义Partitioner
- 继承抽象类Partitioner，重写getPartition方法
- job.setPartitionerClass(MyPartitioner.class)

Combiner类

Combiner相当于本地化的Reduce操作
- 在shuffle之前进行本地聚合
- 用于性能优化，可选项
- 输入和输出类型一致
Reducer可以被用作Combiner的条件
- 符合交换律和结合律
实现Combiner
- job.setCombinerClass(WCReducer.class)

我们进入案例来看这两个知识点

一案例需求

一个存放电话号码的文本，我们需要136 137，138 139和其它开头的号码分开存放统计其每个数字开头的号码个数

二 PhoneMapper 类

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

import java.io.IOException;

public class PhoneMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String phone = value.toString();
        Text text = new Text(phone);
        IntWritable intWritable = new IntWritable(1);
        context.write(text,intWritable);
    }
}

三 PhoneReducer 类

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

import java.io.IOException;

public class PhoneReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count = 0;
        for (IntWritable intWritable : values){
            count += intWritable.get();
        }
        context.write(key, new IntWritable(count));
    }
}

四 PhonePartitioner 类

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

public class PhonePartitioner extends Partitioner<Text, IntWritable> {
    @Override
    public int getPartition(Text text, IntWritable intWritable, int i) {
        //136,137   138,139     其它号码放一起
        if("136".equals(text.toString().substring(0,3)) || "137".equals(text.toString().substring(0,3))){
            return 0;
        }else if ("138".equals(text.toString().substring(0,3)) || "139".equals(text.toString().substring(0,3))){
            return 1;
        }else {
            return 2;
        }

    }
}

五 PhoneCombiner 类

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

import java.io.IOException;

public class PhoneCombiner extends Reducer<Text, IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count = 0;
        for(IntWritable intWritable : values){
            count += intWritable.get();
        }
        context.write(new Text(key.toString().substring(0,3)), new IntWritable(count));
    }
}

六 PhoneDriver 类

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.io.IOException;

public class PhoneDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(PhoneDriver.class);

        job.setMapperClass(PhoneMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setCombinerClass(PhoneCombiner.class);

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

        job.setReducerClass(PhoneReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        Path inPath = new Path("in/demo4/phone.csv");
        FileInputFormat.setInputPaths(job, inPath);

        Path outPath = new Path("out/out6");
        FileSystem fs = FileSystem.get(outPath.toUri(),conf);
        if (fs.exists(outPath)){
            fs.delete(outPath, true);
        }
        FileOutputFormat.setOutputPath(job, outPath);

        job.waitForCompletion(true);

    }
}