Scribd
Upload
15 views3 pages

WordCount MapReduce Source Code

The document contains Java source code for a Hadoop MapReduce program that performs word counting. It includes a driver class, a mapper class that tokenizes input text, and a reducer class that sums the occurrences of each word. The program is structured to take input and output directories as arguments and utilizes Hadoop's framework for processing large datasets.

Uploaded by

shravya.pattiri
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
15 views3 pages

WordCount MapReduce Source Code

The document contains Java source code for a Hadoop MapReduce program that performs word counting. It includes a driver class, a mapper class that tokenizes input text, and a reducer class that sums the occurrences of each word. The program is structured to take input and output directories as arguments and utilizes Hadoop's framework for processing large datasets.

Uploaded by

shravya.pattiri
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

//Source Code for Wordcount:

//Driver Code:

package naiduwc;

import [Link];

import [Link];

import [Link];

import [Link];

import [Link];

import [Link];

import [Link];

import [Link];

import [Link];

public class WordCount {

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

Configuration conf = new Configuration();

Job job = [Link](conf, "WordCount");

[Link]([Link]);

// TODO: specify a mapper

[Link]([Link]);

// TODO: specify a reducer

[Link]([Link]);

// TODO: specify output types

[Link]([Link]);

[Link]([Link]);
// TODO: specify input and output DIRECTORIES (not files)

[Link](job, new Path(args[1]));

[Link](job, new Path(args[2]));

if (![Link](true))

return;

//Mapper code:

package naiduwc;

import [Link].*;

import [Link].*;

import [Link];

import [Link];

import [Link];

import [Link];

import [Link];

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>

public void map(LongWritable key, Text value, Context context)

throws IOException, InterruptedException {

Text word=new Text();

String line=[Link]();

StringTokenizer s=new StringTokenizer(line);

while([Link]())

{
[Link]([Link]());

[Link](word,new IntWritable(1));

//Reducer Code:

package naiduwc;

import [Link].*;

import [Link];

import [Link];

import [Link];

import [Link];

public class WordCountReducer extends Reducer<Text, IntWritable ,Text, IntWritable>

public void reduce(Text key, Iterable<IntWritable> value, Context context)

throws IOException, InterruptedException

int sum=0;

for (IntWritable values : value) {

sum=sum+[Link]();

[Link](key, new IntWritable(sum));

You might also like