Hadoop Word count: receive the total number of words that start with the letter "c"

Solution 1:

Chris Gerken 's answer is right.

If you are outputing word as your key it will only help you to calculate the count of unique words starting with "c"

Not all total count of "c".

So for that you need to output a unique key from mapper.

 while (itr.hasMoreTokens()) {
            String token = itr.nextToken();
            if(token.startsWith("c")){
                word.set("C_Count");
                output.collect(word, one);
            }

        }

Here is an example using New Api

Driver class

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.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 {

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();

        Job job = new Job(conf, "wordcount");
        FileSystem fs = FileSystem.get(conf);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        if (fs.exists(new Path(args[1])))
            fs.delete(new Path(args[1]), true);
        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.setJarByClass(WordCount.class);     
        job.waitForCompletion(true);
    }

}

Mapper class

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public 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 {
        String line = value.toString();
        StringTokenizer itr = new StringTokenizer(line);
        while (itr.hasMoreTokens()) {
            String token = itr.nextToken();
            if(token.startsWith("c")){
                word.set("C_Count");
                context.write(word, one);
            }

        }
    }
}

Reducer class

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {

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

Solution 2:

Instead of

output.collect(word, one);

in your mapper, try:

output.collect("c-total", one);

Solution 3:

Simpler code for mapper:

public void map(LongWritable key, Text value,OutputCollector<Text,IntWritable> op, Reporter r)throws IOException
{
    String s = value.toString();
      for (String w : s.split("\\W+"))
       {
       if (w.length()>0)
        {
         if(w.startsWith("C")){
         op.collect(new Text("C-Count"), new IntWritable(1));        
         }
       }
  }
}