MOVIE RATING:
DRIVER:
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
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 avgrating
{
public static void main(String args[]) throws Exception
{
Configuration conf=new Configuration();
Job job=Job.getInstance(conf,"abc");
job.setJarByClass(avgrating.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(Text.class);
job.setReducerClass(ratingreducer.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
MultipleInputs.addInputPath(job,new
Path(args[0]),TextInputFormat.class,ratingmapper1.class);
MultipleInputs.addInputPath(job,new
Path(args[1]),TextInputFormat.class,ratingmapper2.class);
FileOutputFormat.setOutputPath(job,new Path(args[2]));
job.waitForCompletion(true);
}
}
MAPPER1:
import java.io.IOException;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.Mapper;
public class ratingmapper1 extends
Mapper<LongWritable,Text,IntWritable,Text>
{
public void map(LongWritable key,Text value,Context
context) throws IOException,InterruptedException
{
String s[]=value.toString().split("::");
int p=Integer.parseInt(s[0]);
context.write(new IntWritable(p),new Text(s[1]));
}
}
MAPPER2:
import java.io.IOException;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.Mapper;
public class ratingmapper2 extends
Mapper<LongWritable,Text,IntWritable,Text>
{
public void map(LongWritable key,Text value,Context
context) throws IOException,InterruptedException
{
String s[]=value.toString().split("::");
int p=Integer.parseInt(s[0]);
//float t=Float.parseFloat(s[2]);
context.write(new IntWritable(p),new Text(s[2]));
}
}
REDUCER:
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.Reducer;
public class ratingreducer extends
Reducer<IntWritable,Text,Text,FloatWritable>
{
public void reduce(IntWritable key,Iterable<Text>
vals,Context context) throws IOException,InterruptedException
{
float avg,sum=0,p;
int c=0;
//String n=" ";
Text m=new Text();
Iterator<Text> x=vals.iterator();
while(x.hasNext())
{
String s=x.next().toString();
if(s.length()>2)
{
m=new Text(s);
}
else
{
p=Float.parseFloat(s.toString());
sum=sum+p;
c++;
}
}
avg=sum/c;
context.write(m,new FloatWritable(avg));
}
}
INPUT:
FILE 1:
1::Toy Story (1995)::Animation|Children's|Comedy
2::Jumanji (1995)::Adventure|Children's|Fantasy
3::Grumpier Old Men (1995)::Comedy|Romance
4::Waiting to Exhale (1995)::Comedy|Drama
5::Father of the Bride Part II (1995)::Comedy
6::Heat (1995)::Action|Crime|Thriller
7::Sabrina (1995)::Comedy|Romance
8::Tom and Huck (1995)::Adventure|Children's
9::Sudden Death (1995)::Action
10::GoldenEye (1995)::Action|Adventure|Thriller
11::American President, The (1995)::Comedy|Drama|Romance
12::Dracula: Dead and Loving It (1995)::Comedy|Horror
13::Balto (1995)::Animation|Children's
14::Nixon (1995)::Drama
15::Cutthroat Island (1995)::Action|Adventure|Romance
16::Casino (1995)::Drama|Thriller
FILE 2:
1::1193::5::978300760
1::661::3::978302109
1::914::3::978301968
1::3408::4::978300275
1::2355::5::978824291
1::1197::3::978302268
1::1287::5::978302039
1::2804::5::978300719
1::594::4::978302268
1::919::4::978301368
1::595::5::978824268
1::938::4::978301752
1::2398::4::978302281
1::2918::4::978302124
1::1035::5::978301753
1::2791::4::978302188
1::2687::3::978824268
1::2018::4::978301777
1::3105::5::978301713
1::2797::4::978302039
Output:
