MOVIE DATA ANALYTICS BASED ON RATING

FIRST u CREATE A MOVIE DATA IN A  TEXT FILE:



$cat > moviedata.txt

aa dangal 5
bb laggan 4
aa laggan 4
cc dangal 5
bb dangal 4
pq khidi 3
cc khidi 5
cc dangall 5
za khidi 5
cd laggan 5



Load this data in to HDFS


$hadoop fs -put  moviedata.txt    /movie/moviedata1.txt






write Mapper and Partitioner code as shown below:

Partitioner::

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapred.JobConf;

import org.apache.hadoop.mapred.Partitioner;

public class Mpartitioner implements Partitioner<Text,IntWritable>

{

            @Override

            public void configure(JobConf arg0) {

                        // TODO Auto-generated method stub

                       

            }

            @Override

            public int  getPartition(Text key,IntWritable values,int setNumReducers)

            {

                                                                       

                                    int p=values.get();

                                    if(p==0)

                                    {

                                                return 0;

                                    }

                                    else if(p==1)

                                    {

                                                return 1;

                                    }

                                    else if(p==2)

                                    {

                                                return 2;

                                    }

                                    else if(p==3)

                                    {

                                                return 3;

                                    }

                                    else if(p==4)

                                    {

                                                return 4;

                                    }

                                    else if(p==5)

                                    {

                                                return 5;

                                    }

                                    return p;

                                   

            }}

                       

-------------------------------------------------------------

import org.apache.hadoop.mapred.OutputCollector;

import org.apache.hadoop.mapred.MapReduceBase;

import org.apache.hadoop.mapred.Reducer;

import org.apache.hadoop.mapred.Reporter;

            //public class Mreducer1 extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {

           

            public class Mreducer1 extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {

                        @Override

                        public void reduce(Text key, Iterator<IntWritable> values,

                              OutputCollector<Text, IntWritable> output, Reporter reporter)

                              throws IOException {

            //int p=5;

            int c1=0;

            int c2=0;

            int c3=0;

            int c4=0;

            int c5=0;

            int c6=0;

            while (values.hasNext()) {

           

                        int v=values.next().get();

                        if(v==0)

                        {

                  c1++;

                       

                        output.collect(key, new IntWritable(c1));

                        }

                       

                        if(v==1)

                        {

                  c2++;

                       

                        output.collect(key, new IntWritable(c2));

                        }

                       

                        if(v==2)

                        {

                  c3++;

                       

                        output.collect(key, new IntWritable(c3));

                        }

                        if(v==3)

                        {

                  c4++;

                       

                        output.collect(key, new IntWritable(c4));

                        }

                        if(v==4)

                        {

                  c5++;

                       

                        output.collect(key, new IntWritable(c5));

                        }

                        if(v==5)

                        {

                  c6++;

                       

                        output.collect(key, new IntWritable(c6));

                        }

                       

            }

            //output.collect(key, new IntWritable(c));

            }

            }

u make a jar file  and move to local file system

$hadoop jar movie.jar moviedriver movie/movie1.txt  movie/op

it will generates final output after map reduce program as shown below

your data:   

aa dangal 5

bb laggan 4
aa laggan 4
cc dangal 5
bb dangal 4
pq khidi 3
cc khidi 5
cc dangall 5
za khidi 5
cd laggan 5

op director contains


part-00000
part-00001
part-00002
part-00003
part-00004
part-00005


if u open each op directory partition u can find out rating wise information for each movie