MapReduce经典案例 -------- 统计最高温度

版权声明：个人原创，转载请标注！ https://blog.csdn.net/Z_Date/article/details/83858999

需求：求给定日期的最高温度

待处理数据内容：

​ 201701082.6

​ 201701066

​ 2017020810

​ 2017030816.33

​ 2017060833.0

每一行的前8位是日期，从第8位往后是温度

代码

import java.io.IOException;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
 * 求最高温度
 * @author lyd
 * 
 * 数据：
 * 
 * 201701082.6
 * 201701066
 * 2017020810
 * 2017030816.33
 * 2017060833.0
 * 2017050126.6
 * 2017050320.9
 *
 */
public class HighTem {
	public static class MyMapper extends Mapper<Object, Text, Text,Text>{
		@Override
		protected void map(Object key, Text value,Context context)
				throws IOException, InterruptedException {
			String line = value.toString();
			String tmp = line.substring(8, line.length());
			context.write(new Text(""), new Text(tmp));
			/**
			"" 201701082.6
			"" 201701066
			"" 2017020810
			"" 2017030816.33
			"" 2017060833.0
			"" 2017050126.6
			"" 2017050320.9
			 */
		}
	}
	
	/**
	 * 自定义reducer类
	 * @author lyd
	 *
	 */
	public static class MyReducer extends Reducer<Text, Text, Text, Text>{
		@Override
		protected void reduce(Text key, Iterable<Text> value,Context context)
				throws IOException, InterruptedException {
			/**
			 * "" list(2.6,6,10)
			 */
			double max = Double.MIN_VALUE;
			//获取最大值
			for (Text t : value) {
				if(max < Double.parseDouble(t.toString())){
					max = Double.parseDouble(t.toString());
				}
			}
			context.write(new Text(max+""), new Text(""));
			
		}
	}
	
	
	public static void main(String[] args) {
		try {
			//获取配置对象
			Configuration conf = new Configuration();
			//创建job
			Job job = new Job(conf, "HighTemp");
			//为job设置运行主类
			job.setJarByClass(HighTem.class);
			
			//设置map阶段的属性
			job.setMapperClass(MyMapper.class);
			FileInputFormat.addInputPath(job, new Path(args[0]));
			
			
			//设置reduce阶段的属性
			job.setReducerClass(MyReducer.class);
			job.setOutputKeyClass(Text.class);
			job.setOutputValueClass(Text.class);
			FileOutputFormat.setOutputPath(job, new Path(args[1]));
			
			//提交运行作业job 并打印信息
			int isok = job.waitForCompletion(true)?0:1;
			//退出job
			System.exit(isok);
			
		} catch (IOException | ClassNotFoundException | InterruptedException e) {
			e.printStackTrace();
		}
	}
}