使用Hadoop计算气象数据讲述.doc

1 下载气象数据集部分数据，写一个Map-Reduce作业，求每年的最低温度，部署并运行之，抓图过程 选取了1971、1972、1973年的部分数据： 程序代码内容如下： MinTemperatureMapper.java import java.io.IOException; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; public class MinTemperatureMapper extends MapperLongWritable, Text, Text, IntWritable { private static final int MISSING = 9999; @Override protected void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper.Context context) throws IOException, InterruptedException { String line = value.toString(); String year = line.substring(15, 19); int airTemperature; if (line.charAt(87) == +) { // parseInt doesnt like leading plus signs airTemperature = Integer.parseInt(line.substring(88, 92)); } else { airTemperature = Integer.parseInt(line.substring(87, 92)); } String quality = line.substring(92, 93); if (airTemperature != MISSING quality.matches([01459])) { context.write(new Text(year), new IntWritable(airTemperature)); } } } MinTemperatureReducer.java import java.io.IOException; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; public class MinTemperatureReducer extends ReducerText, IntWritable, Text, IntWritable { @Override protected void reduce(Text key, IterableIntWritable values, Context context) throws IOException, InterruptedException { int minValue = Integer.MAX_VALUE; for (IntWritable value : values) { minValue = Math.min(value.get(), minValue); }