Example6:(Average salary of the organization)
Example 6 : Emp6.java
_____________________________________________________________________________________________________
[training@localhost ~]$ hadoop fs -cat mr/emp
101,ravi,10000,hyd,m,11
102,rani,12000,pune,f,12
103,ravina,13000,hyd,f,13
104,rana,14000,hyd,m,11
105,roopa,15000,pune,f,12
106,razeena,16000,pune,f,12
107,susma,14000,hyd,f,12
108,sampurnesh,20000,delhi,m,13
109,samantha,18000,pune,f,12
110,kamal,19000,delhi,m,11
111,krupa,21000,delhi,m,11
112,kapoor,16000,pune,m,12
schema : ecode, name, sal, city, sex, dno
Task: Average salary of the organization
Sql : select avg(sal) from emp;
____________
Emp6.java
____________
package bharath.sreeram.big.halitcs;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class Emp6
{
public static class MyMap extends Mapper<LongWritable,Text,Text,IntWritable>
{
public void map(LongWritable k,Text v, Context con)
throws IOException, InterruptedException
{
String line = v.toString();
String[] w=line.split(",");
int sal=Integer.parseInt(w[2]);
con.write(new Text("BigHalitics"), new IntWritable(sal));
}
}
public static class MyRed extends Reducer<Text,IntWritable,IntWritable,Text>
{
public void reduce(Text k, Iterable<IntWritable> vlist, Context con)
throws IOException , InterruptedException
{
int tot =0;
int cnt=0;
for(IntWritable v:vlist)
{
tot+=v.get();
cnt++;
}
int avg=tot/cnt;
con.write(new IntWritable(avg), new Text());
}
}
public static void main(String[] args) throws Exception
{
Configuration c = new Configuration();
Job j= new Job(c,"Test");
j.setJarByClass(Emp6.class);
j.setMapperClass(MyMap.class);
j.setReducerClass(MyRed.class);
j.setOutputKeyClass(Text.class);
j.setOutputValueClass(IntWritable.class);
Path p1 = new Path(args[0]);
Path p2 = new Path(args[1]);
FileInputFormat.addInputPath(j,p1);
FileOutputFormat.setOutputPath(j,p2);
System.exit(j.waitForCompletion(true) ? 0:1);
}
}
Submitting Hadoop Job:
$ hadoop jar Desktop/mr.jar bharath.sreeram.big.halitcs.Emp6 mr/emp Result6
Output Of the Job:
$ hadoop fs -cat Result6/part-r-00000
15666
_____________________________________________________________________________________________________
[training@localhost ~]$ hadoop fs -cat mr/emp
101,ravi,10000,hyd,m,11
102,rani,12000,pune,f,12
103,ravina,13000,hyd,f,13
104,rana,14000,hyd,m,11
105,roopa,15000,pune,f,12
106,razeena,16000,pune,f,12
107,susma,14000,hyd,f,12
108,sampurnesh,20000,delhi,m,13
109,samantha,18000,pune,f,12
110,kamal,19000,delhi,m,11
111,krupa,21000,delhi,m,11
112,kapoor,16000,pune,m,12
schema : ecode, name, sal, city, sex, dno
Task: Average salary of the organization
Sql : select avg(sal) from emp;
____________
Emp6.java
____________
package bharath.sreeram.big.halitcs;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class Emp6
{
public static class MyMap extends Mapper<LongWritable,Text,Text,IntWritable>
{
public void map(LongWritable k,Text v, Context con)
throws IOException, InterruptedException
{
String line = v.toString();
String[] w=line.split(",");
int sal=Integer.parseInt(w[2]);
con.write(new Text("BigHalitics"), new IntWritable(sal));
}
}
public static class MyRed extends Reducer<Text,IntWritable,IntWritable,Text>
{
public void reduce(Text k, Iterable<IntWritable> vlist, Context con)
throws IOException , InterruptedException
{
int tot =0;
int cnt=0;
for(IntWritable v:vlist)
{
tot+=v.get();
cnt++;
}
int avg=tot/cnt;
con.write(new IntWritable(avg), new Text());
}
}
public static void main(String[] args) throws Exception
{
Configuration c = new Configuration();
Job j= new Job(c,"Test");
j.setJarByClass(Emp6.class);
j.setMapperClass(MyMap.class);
j.setReducerClass(MyRed.class);
j.setOutputKeyClass(Text.class);
j.setOutputValueClass(IntWritable.class);
Path p1 = new Path(args[0]);
Path p2 = new Path(args[1]);
FileInputFormat.addInputPath(j,p1);
FileOutputFormat.setOutputPath(j,p2);
System.exit(j.waitForCompletion(true) ? 0:1);
}
}
Submitting Hadoop Job:
$ hadoop jar Desktop/mr.jar bharath.sreeram.big.halitcs.Emp6 mr/emp Result6
Output Of the Job:
$ hadoop fs -cat Result6/part-r-00000
15666
0 comments: