MapReduce code for addition of numbers per line

/*
* To change this license header, choose License Headers in Project Properties.
* To change this template file, choose Tools | Templates
* and open the template in the editor.
*/
package com.github.milind;
import java.io.IOException;
import java.util.StringTokenizer;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
*
* @author milind
*/
public class NumberAdditionPerLine {
public static class NumberAdditionPerLineMapper
extends Mapper < Object, Text, Text, IntWritable > {
public void map(Object key, Text value, Mapper.Context context) throws IOException,
InterruptedException {
int sum = 0;
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
String str = itr.nextToken();
sum = sum + Integer.parseInt(str);
}
context.write(new Text("Addition of numbers :" + value.toString() + " =>"), new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "Addition of Numbers Per Line");
job.setJarByClass(NumberAdditionPerLine.class);
job.setMapperClass(NumberAdditionPerLineMapper.class);
job.setNumReduceTasks(0);
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);
}
}

Published by milindjagre

I founded my blog www.milindjagre.co four years ago and am currently working as a Data Scientist Analyst at the Ford Motor Company. I graduated from the University of Connecticut pursuing Master of Science in Business Analytics and Project Management. I am working hard and learning a lot of new things in the field of Data Science. I am a strong believer of constant and directional efforts keeping the teamwork at the highest priority. Please reach out to me at milindjagre@gmail.com for further information. Cheers!

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: