MapReduce Program - Weather Data Analysis For Analyzing Hot And Cold Days

// Required imports for Hadoop MapReduce
import java.io.IOException;
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 org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.conf.Configuration;

// Main class
public class MyMaxMin {

    // Mapper class: Extracts max and min temperature from each line
    public static class MaxTemperatureMapper extends Mapper<LongWritable, Text, Text, Text> {

        // Sentinel value used in dataset to represent missing temperature
        public static final int MISSING = 9999;

        // Map method called for each line in the input file
        @Override
        public void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {

            String line = value.toString(); // Convert line to string

            if (line.length() != 0) {  // Skip empty lines
                // Extract date from line (characters 6 to 14)
                String date = line.substring(6, 14);

                // Extract and trim max and min temperatures
                float temp_Max = Float.parseFloat(line.substring(39, 45).trim());
                float temp_Min = Float.parseFloat(line.substring(47, 53).trim());

                // If max temperature is valid and > 30°C, consider it a hot day
                if (temp_Max != MISSING && temp_Max > 30.0) {
                    context.write(new Text("Hot Day: " + date), new Text(String.valueOf(temp_Max)));
                }

                // If min temperature is valid and < 15°C, consider it a cold day
                if (temp_Min != MISSING && temp_Min < 15.0) {
                    context.write(new Text("Cold Day: " + date), new Text(String.valueOf(temp_Min)));
                }
            }
        }
    }

    // Reducer class: Simply passes through the (key, value) pairs from mapper
    public static class MaxTemperatureReducer extends Reducer<Text, Text, Text, Text> {
        @Override
        public void reduce(Text key, Iterable<Text> values, Context context)
                throws IOException, InterruptedException {
            // Write each value to the output (usually only one value per key in this case)
            for (Text val : values) {
                context.write(key, val);
            }
        }
    }

    // Driver method: Configures and starts the MapReduce job
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();  // Create Hadoop job configuration
        Job job = Job.getInstance(conf, "Weather Analysis");  // Initialize job with name

        job.setJarByClass(MyMaxMin.class);  // Set main class
        job.setMapperClass(MaxTemperatureMapper.class);  // Set mapper class
        job.setReducerClass(MaxTemperatureReducer.class);  // Set reducer class

        // Set output types for mapper
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);

        // Set input/output formats
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

        // Set input and output file paths from command-line arguments
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // Submit job and exit based on completion status
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}