import java.io.IOException; import org.apache.hadoop.fs.Path; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.io.*; import org.apache.hadoop.mapreduce.*; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class MaxTemperature { public static class TempMapper extends Mapper { private final static int MISSING = 9999; public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line = value.toString(); String[] fields = line.split(","); String year = fields[0].trim(); String station = fields[1].trim(); String tempStr = fields[2].trim(); if (!tempStr.equals("Max Temperature")) { int temperature = Integer.parseInt(tempStr.substring(0, tempStr.indexOf("°F")).trim()); context.write(new Text(year), new IntWritable(temperature)); } } } public static class TempReducer extends Reducer { public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException { int maxTemp = Integer.MIN_VALUE; for (IntWritable value : values) { int temp = value.get(); if (temp > maxTemp) { maxTemp = temp; } } context.write(key, new IntWritable(maxTemp)); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "max temperature"); job.setJarByClass(MaxTemperature.class); job.setMapperClass(TempMapper.class); job.setReducerClass(TempReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }