Sunday, March 3, 2013

MapReduce : writting a Simple wordcount program.

Below is the simple program to understand workingof MapReduce.

package com.hadoop.mapreduce;

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class WordCount {
    // Mapper inner class
    public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            //Proccessing each line from input file
            String line = value.toString();
           //separating each word and putting into the map. 
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                //key as a word and value as a count
                context.write(word, one);
            }
        }
    }
   // Reducer inner class
    public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {

        public void reduce(Text key, Iterable<IntWritable> values, Context context)
        throws IOException, InterruptedException {
            int sum = 0;
            //summation of same words and counting their occurances 
            for (IntWritable val : values) {
                sum += val.get();
            }
            //writing output into the context
            context.write(key, new IntWritable(sum));
        }
    }

   //main class takes input file as a command line args
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();

        Job job = new Job(conf, "wordcount");

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);

        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        job.waitForCompletion(true);
    }

}
Read more: http://thinkjava.boards.net/index.cgi?action=display&board=hadoop&thread=7&page=1#12#ixzz2MTlBvOwR

Followers