hadoop 自定义数据类型

根据需要构造自己的数据类型

FlowBean.java

package flow;

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

import org.apache.hadoop.io.Writable;

/**
 * 使用对象构造自己的数据结构,这个对象要实现Writable的接口
 * 1、该类一定要保留空参构造函数
 * 2、write方法中输出字段二进制数据的顺序  要与  readFields方法读取数据的顺序一致
 */
public class FlowBean implements Writable {

	private int upFlow;
	private int dFlow;
	private int amountFlow;

	public FlowBean(){}
	
	public FlowBean(int upFlow, int dFlow) {
		this.upFlow = upFlow;//上行流量
		this.dFlow = dFlow;//下行流量
		this.amountFlow = upFlow + dFlow;//总流量
	}

	public int getUpFlow() {
		return upFlow;
	}

	public void setUpFlow(int upFlow) {
		this.upFlow = upFlow;
	}

	public int getdFlow() {
		return dFlow;
	}

	public void setdFlow(int dFlow) {
		this.dFlow = dFlow;
	}

	public int getAmountFlow() {
		return amountFlow;
	}

	public void setAmountFlow(int amountFlow) {
		this.amountFlow = amountFlow;
	}
	@Override
	public void write(DataOutput out) throws IOException {//该方法必须重写序列化,让hadoop集群来调用

		out.writeInt(upFlow);
		out.writeUTF(phone);
		out.writeInt(dFlow);
		out.writeInt(amountFlow);

	}

	@Override
	public void readFields(DataInput in) throws IOException {//该方法必须重写反序列化,让hadoop集群调用
		this.upFlow = in.readInt();
		this.phone = in.readUTF();
		this.dFlow = in.readInt();
		this.amountFlow = in.readInt();
	}

	@Override
	public String toString() {//返回最终的结果
		return this.phone + ","+this.upFlow +","+ this.dFlow +"," + this.amountFlow;
	}
	
}

partitioner

package flow;

import java.util.HashMap;

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

/**
 * MapTask通过这个类的getPartition方法，根据partitioner方法决定maper的结果如何分配给reducer
 */
public class ProvincePartitioner extends Partitioner<Text, FlowBean>{
	static HashMap<String,Integer> codeMap = new HashMap<>();
	static{
		
		codeMap.put("135", 0);
		codeMap.put("136", 1);
		codeMap.put("137", 2);
		codeMap.put("138", 3);
		codeMap.put("139", 4);
		
	}
	
	
	
	@Override//默认是根据key的haskcode的值%reducernum来分配任务
	public int getPartition(Text key, FlowBean value, int numPartitions) {
		
		Integer code = codeMap.get(key.toString().substring(0, 3));
		return code==null?5:code;
	}

}

mapper

package flow;

import java.io.IOException;

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

public class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean>{
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		
		String line = value.toString();
		String[] fields = line.split("\t");
		
		int upFlow = Integer.parseInt(fields[1]);
		int dFlow = Integer.parseInt(fields[2]);
		
		context.write(new Text(phone), new FlowBean(upFlow, dFlow));
	}
}

reducer

package flow;

import java.io.IOException;

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

public class FlowCountReducer extends Reducer<Text, FlowBean, Text, FlowBean>{
	
	
	
	/**
	 *  key：是某个手机号
	 *  values：是这个手机号所产生的所有访问记录中的流量数据
	 */
	@Override
	protected void reduce(Text key, Iterable<FlowBean> values, Reducer<Text, FlowBean, Text, FlowBean>.Context context)
			throws IOException, InterruptedException {

		int upSum = 0;
		int dSum = 0;
		
		for(FlowBean value:values){
			upSum += value.getUpFlow();
			dSum += value.getdFlow();
		}
		
		
		context.write(key, new FlowBean(key.toString(), upSum, dSum));
		
	}
	

}

JobSubmitter.java

package flow;

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;

public class JobSubmitter {

	public static void main(String[] args) throws Exception {

		Configuration conf = new Configuration();

		Job job = Job.getInstance(conf);

		job.setJarByClass(JobSubmitter.class);

		job.setMapperClass(FlowCountMapper.class);
		job.setReducerClass(FlowCountReducer.class);

		job.setPartitionerClass(ProvincePartitioner.class);//如果不设定默认使用HashPartitioner
		job.setNumReduceTasks(6);

		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(FlowBean.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(FlowBean.class);
		
		
		

		FileInputFormat.setInputPaths(job, new Path("F:\\input"));
		FileOutputFormat.setOutputPath(job, new Path("F:\\province-output"));

		job.waitForCompletion(true);

	}

}