hadoop06--自定義數據類型,自定義分區,排序

自定義數據類型(序列化)

自定義數據類型

Java類型 Hadoop類型
boolean BooleanWritable
byte ByteWriteable
int IntWritable
float FloatWritable
long LongWritable
double DoubleWritable
String Text
map MapWritable
array ArrayWritable

對於以上的數據類型, hadoop都提供了相應的實現, 能滿足基本開發需求, 但是有一些需求不能滿足

自定義數據類型規則
  1. 必須實現** writable **接口
  2. 必須提供無參的構造方法, 因爲反射的時候 , 默認調用無參的構造方法
  3. 分爲 key 和 **value ** , 如果自定義數據類型爲key , 則必須實現writableComparable接口

實例1

一張數據表如下格式:

13726230503	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com	24	27

想要得到的格式:

手機號   				上行流量  		下行流量  		總流量
13726230503     	2481  			 	24681   			53456
使用hadoop提供的數據類型實現如上格式輸出
  • 分析: 自定義一個數據類型, 把上行流量, 下行流量進行保存
自定義數據類型 FlowWritable
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

import org.apache.hadoop.io.Writable;

public class FlowWritable implements Writable{

	private long upFlow; //上行總流量 
	private long downFlow; //下行總流量
	
	/**
	 * 數據序列化方法
	 */
	@Override
	public void write(DataOutput out) throws IOException {
		// TODO Auto-generated method stub
		out.writeLong(upFlow);
		out.writeLong(downFlow);
	}

	/**
	 * 反序列化方法
	 */
	@Override
	public void readFields(DataInput in) throws IOException {
		// TODO Auto-generated method stub
		this.upFlow=in.readLong();
		this.downFlow=in.readLong();
	}
}
實現map方法
import java.io.IOException;

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

public class FlowMap extends Mapper<LongWritable, Text, Text, FlowWritable>{

	private Text outputKey=new Text();
	
	private FlowWritable outputValue=new FlowWritable();
	
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		
//		13726230503	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com	24	27	2481	24681	200
		//1 獲取數據
		String line =value.toString();
		
		//2 開始切割 
		
		String[] fileds=line.split("\t");
		
		// 3 獲得手機號 
		
		String phoneNumber=fileds[0];
		
		//4 上行總流量 和下行總流量 
		
		long upFlowValue=Long.valueOf(fileds[fileds.length-3]);
		long downFlowValue=Long.valueOf(fileds[fileds.length-2]);
		
		// 設置 手機號, 上行流量  下行流量 到序列化類型中
		outputKey.set(phoneNumber);
		outputValue.set(upFlowValue, downFlowValue);
		
		context.write(outputKey, outputValue);
	}
	
}
實現reduce方法
import java.io.IOException;

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

public class FlowReduce extends Reducer<Text, FlowWritable, Text, FlowWritable>{

	private FlowWritable outputValue=new FlowWritable();
	
	@Override
	protected void reduce(Text key, Iterable<FlowWritable> values,
			Context context) throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		
		long totalUpFlow=0;
		
		long totalDownFlow=0;
		
		//相同的手機號,上行流量 和下行流量的和進行累加
		
		for(FlowWritable value:values) {
			
			totalUpFlow+=value.getUpFlow();
			
			totalDownFlow+=value.getDownFlow();
		}
		
		outputValue.set(totalUpFlow, totalDownFlow);
		context.write(key, outputValue);
	}

}
主函數 Driver
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
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 org.qianfeng.wordcount.WordCountMap;
import org.qianfeng.wordcount.WordCountReduce;

public class Driver {

	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		
		
		//1 獲得配置信息 
		
		Configuration config=new Configuration();
		// 實例化 job類 並且把配置信息傳給job
		Job job=Job.getInstance(config);
		
		// 通過反射機制 加載主類的位置
		job.setJarByClass(Driver.class);
		
		//設置map和reduce類
		job.setMapperClass(FlowMap.class);
		job.setReducerClass(FlowReduce.class);
		
		
		//設置map的輸出 
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(FlowWritable.class);
		
		
		
		//設置redue的輸出
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(FlowWritable.class);
		
		//設置文件的輸入 輸出路徑
		
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		//提交任務 
		
		boolean result=job.waitForCompletion(true);
		
		System.exit(result?0:1);
		
	}
}

  • 注意: 序列化的順序和反序列化的順序一致
Map的分片
  1. Map的執行數量是由分片決定的
  2. 每一個分片 對應一個MapTask任務
  3. 默認情況下 , 切片的大小等於 blocksize 塊的大小, 可以進行修改

自定義分區

實例2

  • 要求:對這個文件實現自定義分區,並且是按照省份ID進行分區的
默認分區的源碼
 /** Use {@link Object#hashCode()} to partition. */
  public int getPartition(K key, V value,
                          int numReduceTasks) {
    return (key.hashCode() & Integer.MAX_VALUE) % numReduceTasks;
  }

Key.hashCode % numberReduceTask = 0 或者 1

integer.MAX_VALUE = 01111111 11111111 11111111 11111111 11111111 11111111 11111111 11111111
假設key.hashcode = 10101011 10101010 11011011 11101000 00110101 11011011 11101000 00110101
做 & 運算

01111111 11111111 11111111 11111111 11111111 11111111 11111111 11111111 
10101011 10101010 11011011 11101000 00110101 11011011 11101000 00110101

00101011 10101010 11011011 11101000 00110101 11011011 11101000 00110101  

注意:

  1. 這裏所做的&運算主要就是爲了防止key.hashcode爲負數, 對2取餘出現其他分區
  2. 默認的分區規則: key.hashCode%reduce 的數量
上一層源碼
@InterfaceAudience.Public
@InterfaceStability.Stable
public class HashPartitioner<K, V> extends Partitioner<K, V> {

  /** Use {@link Object#hashCode()} to partition. */
  public int getPartition(K key, V value,
                          int numReduceTasks) {
    return (key.hashCode() & Integer.MAX_VALUE) % numReduceTasks;
  }

}

從上面的源碼可以發現,一個類繼承了Partitoner就可以實現一個分區規則

過程分析
  1. 拿到手機號
  2. 獲得手機號前三位
  3. 存在一個數據塊, 存儲對應的省份ID, 可以通過手機號查詢到對應的省份
  4. 去數據庫查詢對應的省份, 獲得省份ID
繼承Partitioner類
import java.util.HashMap;

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

public class ProvincePartitioner extends Partitioner<Text, FlowWritable>{

	static HashMap<String, Integer> provinveID=new HashMap<>();
	
	static {
		
		provinveID.put("136", 0);
		provinveID.put("137", 1);
		provinveID.put("138", 2);
		provinveID.put("139", 3);
	}
	
	@Override
	public int getPartition(Text key, FlowWritable value, int numPartitions) {
		// TODO Auto-generated method stub
		
		//1 獲得手機號碼的字符串
		
		String phoneNumber=key.toString();
		
		//2 獲得手機號碼的前三位
		String prefix=phoneNumber.substring(0, 3);
		
		
		Integer proviceId=provinveID.get(prefix);
		
		return proviceId ==null? 4:proviceId;
	}

}
修改主函數Driver
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
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 org.qianfeng.wordcount.WordCountMap;
import org.qianfeng.wordcount.WordCountReduce;

public class Driver {

	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		
		//1 獲得配置信息 
		Configuration config=new Configuration();
		// 實例化 job類 並且把配置信息傳給job
		Job job=Job.getInstance(config);
		
		// 通過反射機制 加載主類的位置
		job.setJarByClass(Driver.class);
		
		//設置map和reduce類
		job.setMapperClass(CountSortMap.class);
		job.setReducerClass(CountSortReduce.class);
		
		//設置map的輸出 
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(FlowWritable.class);
		
		//設置reduce數量
		job.setNumReduceTasks(5);
		
		// 設置自定義分區類
		job.setPartitionerClass(ProvincePartitioner.class);
		
		//設置redue的輸出
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(FlowWritable.class);
		
		//設置文件的輸入 輸出路徑
		
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		//提交任務 
		
		boolean result=job.waitForCompletion(true);
		
		System.exit(result?0:1);
		
	}
}

排序

實例3

對實例1的結果中的總流量進行降序排列
分析

修改FlowWritable 實現 WritableComparable 接口
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;

public class FlowWritable implements WritableComparable<FlowWritable>{

	private long upFlow; //上行總流量 
	
	private long downFlow; //下行總流量
	
	private long totalFlow; //總流量
	
	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 void set(long upFlow,long downFlow) {
		
		this.upFlow=upFlow;
		
		this.downFlow=downFlow;
		
		this.totalFlow=this.upFlow+this.downFlow;
	}

	/**
	 * 數據序列化方法
	 */
	@Override
	public void write(DataOutput out) throws IOException {
		// TODO Auto-generated method stub
		out.writeLong(upFlow);
		out.writeLong(downFlow);
	}

	/**
	 * 反序列化方法
	 */
	@Override
	public void readFields(DataInput in) throws IOException {
		// TODO Auto-generated method stub
		this.upFlow=in.readLong();
		this.downFlow=in.readLong();
	}

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

	@Override
	public int compareTo(FlowWritable o) {
		// TODO Auto-generated method stub
		return this.totalFlow>o.totalFlow?-1:1;
	}
}
實現map函數

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


// values 13480253104   key 180	180	360
public class CountSortMap extends Mapper<LongWritable, Text, FlowWritable, Text>{

	FlowWritable outputKey=new FlowWritable();
	
	Text outputValue=new Text();
	
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		
		// 1 獲取一行的數據文本
		String line=value.toString();
		
		//2 截取想要的內容
		
		String[] fileds=line.split("\t");
		//3 手機號
		String phoneNumber=fileds[0];
		//4 上行流量
		long upFlow=Long.valueOf(fileds[1]);
		//5 下行流量
		
		long downFlow=Long.valueOf(fileds[2]);
		
		outputKey.set(upFlow, downFlow);
		
		outputValue.set(phoneNumber);
		
		//6 輸出到 reduce 
		context.write(outputKey, outputValue);
		
	}
}
實現reduce函數
import java.io.IOException;

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

public class CountSortReduce extends Reducer<FlowWritable, Text, Text, FlowWritable>{
	@Override
	protected void reduce(FlowWritable key, Iterable<Text> values,
			Context context) throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		
		for(Text text:values) {
			System.out.println(key.getUpFlow());
			context.write(text, key);
		}
	}
}
實現主函數Driver
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
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 org.qianfeng.wordcount.WordCountMap;
import org.qianfeng.wordcount.WordCountReduce;

public class Driver {

	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		
		
		//1 獲得配置信息 
		
		Configuration config=new Configuration();
		// 實例化 job類 並且把配置信息傳給job
		Job job=Job.getInstance(config);
		
		// 通過反射機制 加載主類的位置
		job.setJarByClass(Driver.class);
		
		//設置map和reduce類
		job.setMapperClass(CountSortMap.class);
		job.setReducerClass(CountSortReduce.class);
		
		
		//設置map的輸出 
		job.setMapOutputKeyClass(FlowWritable.class);
		job.setMapOutputValueClass(Text.class);

		//設置redue的輸出
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(FlowWritable.class);
		
		//設置文件的輸入 輸出路徑
		
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		//提交任務 
		
		boolean result=job.waitForCompletion(true);
		
		System.exit(result?0:1);
		
	}
}
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章