Move the file from local to hdfs

hdfs dfs -copyFromLocal "C:\\Users\\labuser\\Desktop\\MCA54\\CountNumberOfSubPatent\\assets\\patent" /mca54

Check whether the file is copied to hdfs

hdfs dfs -ls /mca54

Check hadoop user interface (Namenode Status) and the File we’ve copied just now.

Now create one Java Project using vs code (CountNumberOfSubPatent)

Copy jar file from hadoop (hdfs > common and mapreduce dir) and paste in lib folder of java project

Java file ContNumberOfSubPatents.java (Even assignment (SubPatent by Patent))

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 ContNumberOfSubPatents {

    // Mapper Class
    public static class PatentMapper extends Mapper<Object, Text, IntWritable, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private IntWritable patentId = new IntWritable();
    
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString().trim();
    
            if (line.isEmpty()) return;
    
            String[] parts = line.split("\\\\s+");
    
            if (parts.length == 2) {
                try {
                    int id = Integer.parseInt(parts[0]);  // convert patent ID string to int
                    patentId.set(id);
                    context.write(patentId, one);  // emit (int patent ID, 1)
                } catch (NumberFormatException e) {
                    // Ignore lines where patent ID is not an integer
                }
            }
        }
    }
    

    // Reducer Class
    public static class CountReducer extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {
        private IntWritable result = new IntWritable();
    
        public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

    // Main Method (Driver)
    public static void main(String[] args) throws Exception {

        if (args.length != 2) {
            System.err.println("Usage: ContNumberOfSubPatents <input path> <output path>");
            System.exit(-1);
        }

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Count Number of Sub-Patents");

        job.setJarByClass(ContNumberOfSubPatents.class);
        job.setMapperClass(PatentMapper.class);
        job.setCombinerClass(CountReducer.class);
        job.setReducerClass(CountReducer.class);

        job.setOutputKeyClass(IntWritable.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);
    }
}

Create output folder inside java project

1. command to compile ContNumberOfSubPatents.java file

   javac --release 8 -cp "lib/*" -d output "src/ContNumberOfSubPatents.java"
   

   

2. command to create a jar file for the ContNumberOfSubPatents program

   jar -cvf src/ContNumberOfSubPatents.jar -C output/ .
   

   

command to run hadoop jar

hadoop jar C:\\Users\\labuser\\Desktop\\MCA54\\CountNumberOfSubPatent\\src\\ContNumberOfSubPatents.jar ContNumberOfSubPatents /mca54/patent /mca54/output/ContNumberOfSubPatents

"C:\\Users\\labuser\\Desktop\\MCA54\\CountNumberOfSubPatent\\src\\ContNumberOfSubPatents.jar" is the path of the jar file present in the local system

"/mca54/patent" is the path of the input files present on the hadoop server.

"/mca54/ContNumberOfSubPatents/output" is the path of the output folder where i wish to upload all the output files on the hadoop server.

Java file ContNumberOfMainPatentsBySubPatent.java (Odd assignment (Patent by SubPatent))

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 ContNumberOfMainPatentsBySubPatent {

    // Mapper Class
    public static class SubPatentMapper extends Mapper<Object, Text, IntWritable, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private IntWritable subPatentId = new IntWritable();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString().trim();

            if (line.isEmpty()) return;

            String[] parts = line.split("\\\\s+");

            // Expect two parts: main patent, sub-patent
            if (parts.length == 2) {
                try {
                    int subId = Integer.parseInt(parts[1]);  // sub-patent ID is second part
                    subPatentId.set(subId);
                    context.write(subPatentId, one);  // emit (sub-patent ID, 1)
                } catch (NumberFormatException e) {
                    // Ignore lines where sub-patent ID is not integer
                }
            }
        }
    }

    // Reducer Class
    public static class CountReducer extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

    // Main Method (Driver)
    public static void main(String[] args) throws Exception {

        if (args.length != 2) {
            System.err.println("Usage: ContNumberOfMainPatentsBySubPatent <input path> <output path>");
            System.exit(-1);
        }

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Count Number of Main Patents by Sub-Patent");

        job.setJarByClass(ContNumberOfMainPatentsBySubPatent.class);
        job.setMapperClass(SubPatentMapper.class);
        job.setCombinerClass(CountReducer.class);
        job.setReducerClass(CountReducer.class);

        job.setOutputKeyClass(IntWritable.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);
    }
}

Create output folder inside java project

1. command to compile ContNumberOfMainPatentsBySubPatent.java file

   javac --release 8 -cp "lib/*" -d output/ContNumberOfMainPatentsBySubPatent "src/ContNumberOfMainPatentsBySubPatent.java"
   

   

2. command to create a jar file for the ContNumberOfMainPatentsBySubPatent program

   jar -cvf src/ContNumberOfMainPatentsBySubPatent.jar -C output/ContNumberOfMainPatentsBySubPatent .
   

   

command to run hadoop jar

hadoop jar C:\\Users\\labuser\\Desktop\\MCA54\\CountNumberOfSubPatent\\src\\ContNumberOfMainPatentsBySubPatent.jar ContNumberOfMainPatentsBySubPatent /mca54/patent /mca54/output/ContNumberOfMainPatentsBySubPatent