Project2

package org.apache.hadoop.ramapo;
import java.io.IOException;
import java.util.StringTokenizer;
import java.util.Map;
import java.util.TreeMap;
import java.util.Arrays;
import java.util.ArrayList;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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 Project2{

  public static class MyMapper
        extends Mapper<LongWritable, Text, IntWritable, IntWritable>{
            public void map (LongWritable key, Text value, Context context) throws IOException, InterruptedException{
                String[] line = value.toString().split("\t");
                //String[] line = value.toString().split(",");
                Integer user = Integer.parseInt(line[0]);
                Integer movie = Integer.parseInt(line[1]);
                context.write(new IntWritable(user), new IntWritable(movie));

            }
    }


  public static class MyReducer
        extends Reducer<IntWritable, IntWritable, IntWritable, Text> {

            // first TM is for UserID : movies; the second is UserID : friendList
            private TreeMap<Integer, ArrayList<Integer>> TM1 = new TreeMap<Integer, ArrayList<Integer>>();
            public TreeMap<Integer, ArrayList<Integer>> TM2 = new TreeMap<Integer, ArrayList<Integer>>();
            // will be used for the context (output will be the list of a user's liked movies)
            String outputString = "";
            public void reduce (IntWritable key, Iterable<IntWritable> value, Context context) throws IOException, InterruptedException{

                // create a treemap where key is UserID and value is a
                // list of UserID's watched movies
                for(IntWritable x: value){
                      Integer movieVal = x.get();
                      ArrayList<Integer> valList = TM1.get(key.get());
                      // if not in list, add new list to TM, else
                      // append to TM's value list
                      if (valList == null) {
                      valList = new ArrayList<Integer>();
                      valList.add(movieVal);
                      TM1.put(key.get(), valList);
                      } else {
                        valList.add(movieVal);
                      }
                }

                // populate the second TM; this one will contain UserID: Friend List



                for(ArrayList<Integer>  x: TM1.values()){
                  outputString = Integer.toString(x.get(0));
                  for (int i = 1; i < x.size(); i++)
                  {
                      outputString = outputString + "," + Integer.toString(x.get(i)) ;
                  }
                  outputString = outputString + "\n";
                }

                context.write(new IntWritable(key.get()), new Text(outputString));


            }
    }

  public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Project2");
        job.setJarByClass(Project2.class);
        job.setMapperClass(MyMapper.class);
        //job.setCombinerClass(MyReducer.class);
        job.setReducerClass(MyReducer.class);
        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(Text.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}