下载气象数据集部分数据,写一个Map-Reduce做业,求每一年的最低温度

环境:CentOS6.6    Hadoop1.2.1

1.设置 HADOOP_PREFIX 环境变量
[grid@hadoop1 ~]$ cat .bash_profile 
HADOOP_PREFIX=/home/grid/hadoop-1.2.1
PATH=$PATH:$HOME/bin:$HADOOP_PREFIX/bin
export HADOOP_PREFIX PATH

2.准备天气数据
java

3.解压合并


4.上传到HDFS


5.编写JAVA文件
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class MinTemperatureMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private static final int MISSING = -9999;
    @Override
    public void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String line = value.toString();
        String year = line.substring(0, 4);
        int airTemperature = Integer.parseInt(line.substring(13, 19).trim());
        if (airTemperature != MISSING) {
            context.write(new Text(year), new IntWritable(airTemperature));
        }
    }
}

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class MinTemperatureReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    @Override
    public void reduce(Text key, Iterable<IntWritable> values, Context context)
            throws IOException, InterruptedException {
        int minValue = Integer.MAX_VALUE;
        for (IntWritable value : values) {
            minValue = Math.min(minValue, value.get());
        }
        context.write(key, new IntWritable(minValue));
    }
}

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
public class MinTemperature {
    public static void main(String[] args) throws Exception {
        if (args.length != 2) {
            System.err.println("Usage: MinTemperature <input path> <output path>");
            System.exit(-1);
        }
        Job job = new Job();
        job.setJarByClass(MinTemperature.class);
        job.setJobName("Min temperature");
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.setMapperClass(MinTemperatureMapper.class);
        job.setCombinerClass(MinTemperatureReducer.class);
        job.setReducerClass(MinTemperatureReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

6.编译并打成JAR包,删除编译后的class文件 shell

7.执行