MapReduce 获取全年的最高气温

气温数据：

1997-07-01	10
1998-04-01	26
1997-05-01	-5
1989-06-01	25
1925-05-01	45

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;

import java.io.IOException;

public class MaxTemp {
    //本地运行需要的方法
    static {
        System.setProperty("hadoop.home.dir", "D:\\soft\\hadoop\\hadoop-2.9.2");
    }
    
    public static class MyMapper extends Mapper<LongWritable, Text, Text, Text > {

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String[] lineArr = line.split("\\s");
            //从日期中获取年
            String year = lineArr[0].substring(0, 4);
            context.write(new Text(year),value);
        }
    }


    public static class MyReducer extends Reducer<Text, Text, Text, Text> {

        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {

            Double maxTemp=Double.MIN_VALUE;
            String day=null;
            for (Text value:values
                 ) {
                String str = value.toString();
                String[] split = str.split("\\s");
                //拆分出气温和对应的日期
                double temp = Double.parseDouble(split[1]);
                if (temp > maxTemp) {
                    //比较获取最高气温
                    maxTemp=temp;
                    //比较获取最高气温对应的日期
                    day=split[0];
                }
            }
            //输出获取到的每年每天最高的气温
            context.write(key,new Text(day +"   "+maxTemp));
        }
    }


    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //0.初始化一个job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "maxTemp");
            /*
                打jar包集群方式运行
                job.setJarByClass(WordCount.class);
             */
        //1.输入文件
        FileInputFormat.addInputPath(job, new Path(args[0]));
        //2.map并行计算
        //如果map的输出key value 的类型个reduce key  value的类型相同可以省略
        job.setMapperClass(MyMapper.class);
//        job.setMapOutputKeyClass(Text.class);
//        job.setMapOutputValueClass(LongWritable.class);
        //3.shuffle流程(内部实现)
        //4.reduce计算
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        //5.输出文件
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        //如果输入目录存在删除
        FileSystem fs = FileSystem.get(conf);
        if (fs.exists(new Path(args[1]))){
            fs.delete(new Path(args[1]),true);
        }
        //6.提交作业（总入口）
        boolean result = job.waitForCompletion(true);
        System.out.println(result ? 1 : 0);
    }
}

结果：

1925	1925-05-01   45.0
1989	1989-06-01   25.0
1997	1997-07-01   10.0
1998	1998-04-01   26.0