Example of calculating the average object size from apache like log file.

KeyCountDriver_with_Combiner.java

import java.io.IOException;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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.Reducer.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

class KeyMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
  @Override
  protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
    String line = value.toString();
    String[] records = line.split(" ");
    context.write(new Text(records[0]), new IntWritable(Integer.parseInt(records[3])));
  }
}

class KeyReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
  @Override
  protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
    int count = 0;
    int sum   = 0;
    int result = 0;
    for(IntWritable value : values){
      sum += value.get();
      count += 1;
    }
    result = sum / count;
    context.write(key, new IntWritable(result));
  }
}


class Combine extends Reducer<Text, IntWritable, Text, IntWritable>{
  @Override
  protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException{
    int count = 0;
    int sum = 0;
    int inter_result = 0;
    for (IntWritable value : values){
      sum += value.get();
      count += 1;
    }
    inter_result = sum / count;
    context.write(key, new IntWritable(inter_result));
  }
}


public class KeyCountDriver extends Configured implements Tool {
  @Override
  public int run(String[] args) throws Exception{
    if(args.length != 2){
      System.out.printf("Usage: %s [generic options] <indir> <outdir>\n", getClass().getSimpleName());
      return -1;
    }
    Job job = new Job(getConf(), "KeyCount");
    job.setJarByClass(KeyCountDriver.class);
    job.setJarByClass(KeyMapper.class);
    job.setJarByClass(KeyReducer.class);

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

    job.setMapperClass(KeyMapper.class);
    job.setReducerClass(KeyReducer.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

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

    return job.waitForCompletion(true) ? 0 : -1;
  }

  public static void main(String[] args) throws Exception {
    System.exit(ToolRunner.run(new KeyCountDriver(), args));
  }
}