Run Word Count Java Mapreduce Program in Hadoop

How to create Jar file for Wordcount using eclipse IDE for Java.

1:- Create a Java project in Eclipse with name “WordCount”

2:- Create a class file named “WordCount.java” in src folder.

3:- Download hadoop-core.jar and hadoop-commons.jar.

4:-Right click on “WordCount” project -> Click on properties ->; Click on “;Java Build Path”-> Click on tab – “Libraries” -> Add External jars

6:- Add "Mapper", "Reducer" and "Driver" code to WordCount.java

import java.io.IOException;

import java.io.InvalidObjectException;

import java.util.StringTokenizer;

import java.util.Iterator;

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;

public class WordCountDemo

{

public static class TokenizerMapper




extends Mapper<Object, Text, Text, IntWritable>

{




private final static IntWritable one = new IntWritable(1); private Text word = new Text();




public void map(Object key, Text value, Context context) throws IOException, InterruptedException

  {

     StringTokenizer itr = new StringTokenizer(value.toString());

     while (itr.hasMoreTokens())

      {

      word.set(itr.nextToken());

      context.write(word, one);

      }

  }

}

public static class IntSumReducer




extends Reducer<Text,IntWritable,Text,IntWritable>

{

     private IntWritable result = new IntWritable();

    public void reduce(Text 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);

    }

}

public static void main(String[] args) throws Exception

{

Configuration conf = new Configuration(); conf job = new conf();

//Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCountDemo.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.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);

}

}

7:-Compile the project.

8:- Right click on project -> Export -> Jar -> Add location and name of jar.

 

11:- run command to word count of the file

   hadoop jar wordCount.jar wordCount 

12 :- after the program get executed the output will show like this