《hadoop权威指南》第二章的例子（修改已可用）

额，我看了一下1990年气象数据的格式，已经和书上有很大出入了，新的数据已经格式化了，后面附件里有，我用的时候把第一行的名称都删掉了。而且也不是int的了，我用的是double

 

MaxTemperatureMapper

 

 

package com.eryk.hadoop.weather;

import java.io.IOException;

import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;

public class MaxTemperatureMapper extends MapReduceBase implements
		Mapper<LongWritable, Text, Text, DoubleWritable> {
	private static final double MISSING = 99.9;
	public void map(LongWritable key, Text value,
			OutputCollector<Text, DoubleWritable> output, Reporter reporter)
			throws IOException {
		String line = value.toString();
		String year = line.substring(14,18);
		double airTemperature;
			airTemperature = Double.parseDouble(line.substring(104,108));
		if(airTemperature != MISSING){
			output.collect(new Text(year), new DoubleWritable(airTemperature));
		}
	}

}

 

MaxTemperatureReducer

 

package com.eryk.hadoop.weather;

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;

public class MaxTemperatureReducer extends MapReduceBase implements
		Reducer<Text, DoubleWritable, Text, DoubleWritable> {

	public void reduce(Text key, Iterator<DoubleWritable> values,
			OutputCollector<Text, DoubleWritable> output, Reporter reporter)
			throws IOException {
		double maxValue = Double.MIN_VALUE;
		while(values.hasNext()){
			maxValue = Math.max(maxValue, values.next().get());
		}
		output.collect(key, new DoubleWritable(maxValue));
	}

}

 

MaxTemperature

 

package com.eryk.hadoop.weather;

import java.io.IOException;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;

public class MaxTemperature {
	public static void main(String[] args) throws IOException {
		if(args.length !=2){
			System.err.println("参数错误");
			System.exit(-1);
		}
		JobConf conf = new JobConf(MaxTemperature.class);
		conf.setJobName("eryk Max temperature");
		
		FileInputFormat.addInputPath(conf, new Path(args[0]));
		FileOutputFormat.setOutputPath(conf, new Path(args[1]));
		
		conf.setMapperClass(MaxTemperatureMapper.class);
		conf.setReducerClass(MaxTemperatureReducer.class);

		conf.setOutputKeyClass(Text.class);
		conf.setOutputValueClass(DoubleWritable.class);
		
		JobClient.runJob(conf);
	}
}