Example4:(For each sex group , Number of employees)
Example4: Emp4.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: for each sex group , Number of employees
Sql : select sex , count(*) from emp group by sex;
___________
Emp4.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 Emp4
{
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(",");
String sex=w[4];
con.write(new Text(sex), new IntWritable(1));
}
}
public static class MyRed extends Reducer<Text,IntWritable,Text,IntWritable>
{
public void reduce(Text k, Iterable<IntWritable> vlist, Context con)
throws IOException , InterruptedException
{
int tot =0;
for(IntWritable v:vlist)
tot+=v.get();
con.write(k,new IntWritable(tot));
}
}
public static void main(String[] args) throws Exception
{
Configuration c = new Configuration();
Job j= new Job(c,"Test");
j.setJarByClass(Emp4.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.Emp4 mr/emp Result4
Output of the Job :
$ hadoop fs -cat Result4/part-r-00000
f 6
m 6
_____________________________________________________________________________________________
[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: for each sex group , Number of employees
Sql : select sex , count(*) from emp group by sex;
___________
Emp4.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 Emp4
{
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(",");
String sex=w[4];
con.write(new Text(sex), new IntWritable(1));
}
}
public static class MyRed extends Reducer<Text,IntWritable,Text,IntWritable>
{
public void reduce(Text k, Iterable<IntWritable> vlist, Context con)
throws IOException , InterruptedException
{
int tot =0;
for(IntWritable v:vlist)
tot+=v.get();
con.write(k,new IntWritable(tot));
}
}
public static void main(String[] args) throws Exception
{
Configuration c = new Configuration();
Job j= new Job(c,"Test");
j.setJarByClass(Emp4.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.Emp4 mr/emp Result4
Output of the Job :
$ hadoop fs -cat Result4/part-r-00000
f 6
m 6
0 comments: