Scribd
Upload
8 views2 pages

12 LogFileMapReduce

The document contains Java code for a Hadoop MapReduce program that calculates sales per country. It includes three classes: SalesCountryDriver, SalesCountryReducer, and SalesMapper, which handle job configuration, data reduction, and data mapping respectively. The program processes input data from HDFS and outputs the total sales frequency for each country.

Uploaded by

shashank
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
8 views2 pages

12 LogFileMapReduce

The document contains Java code for a Hadoop MapReduce program that calculates sales per country. It includes three classes: SalesCountryDriver, SalesCountryReducer, and SalesMapper, which handle job configuration, data reduction, and data mapping respectively. The program processes input data from HDFS and outputs the total sales frequency for each country.

Uploaded by

shashank
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

//SalesCountry.

java

package SalesCountry;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;

public class SalesCountryDriver


{
public static void main(String[] args)
{
JobClient my_client = new JobClient();
// Create a configuration object for the job
JobConf job_conf = new JobConf(SalesCountryDriver.class);
// Set a name of the Job
job_conf.setJobName("SalePerCountry");
// Specify data type of output key and value
job_conf.setOutputKeyClass(Text.class);
job_conf.setOutputValueClass(IntWritable.class);
// Specify names of Mapper and Reducer Class
job_conf.setMapperClass(SalesCountry.SalesMapper.class);
job_conf.setReducerClass(SalesCountry.SalesCountryReducer.class);
// Specify formats of the data type of Input and output
job_conf.setInputFormat(TextInputFormat.class);
job_conf.setOutputFormat(TextOutputFormat.class);
// Set input and output directories using command line arguments,
//arg[0] = name of input directory on HDFS, and arg[1] = name of output
//directory to be created to store the output file.
FileInputFormat.setInputPaths(job_conf, new Path(args[0]));
FileOutputFormat.setOutputPath(job_conf, new Path(args[1]));
my_client.setConf(job_conf);
try {
// Run the job
JobClient.runJob(job_conf);
}
catch (Exception e) { e.printStackTrace(); }
}
}

//SalesCountryReducer.java

package SalesCountry;
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.*;
public class SalesCountryReducer extends MapReduceBase implements
Reducer<Text, IntWritable, Text, IntWritable>
{
public void reduce(Text t_key, Iterator<IntWritable> values, r<Text,IntWritable>
output, Reporter reporter) throws IOException
{
Text key = t_key;
int frequencyForCountry = 0;
while (values.hasNext())
{
// replace type of value with the actual type of our value
IntWritable value = (IntWritable) values.next();
frequencyForCountry += value.get();
}
output.collect(key, new IntWritable(frequencyForCountry));
}
}

//SalesMapper.java

package SalesCountry;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.*;

public class SalesMapper extends MapReduceBase implements


Mapper<LongWritable, Text, Text, IntWritable>
{
private final static IntWritable one = new IntWritable(1);
public void map(LongWritable key, Text value, OutputCollector<Text,
IntWritable> output, Reporter reporter) throws IOException
{
String valueString = value.toString();
String[] SingleCountryData = valueString.split(",");
output.collect(new Text(SingleCountryData[7]),one);
}
}

You might also like