Install Apache Mahout in Eclipse

Posted by on
Apache Mahout is an open source project that is primarily used in producing scalable machine learning algorithms. This tutorial will show you how to install Apache Mahout in Eclipse.

Requirement:
Eclipse IDE
Maven - http://download.eclipse.org/technology/m2e/releases/

Apache Mahout

Steps for installing Eclipse:

1. Installing Maven in Eclipse:
  1. Open Eclipse -> Help -> Install new software
  2. In text box paste this URL - http://download.eclipse.org/technology/m2e/releases/
  3. Click add -> type the name [Example: m2eclipse] -> OK
  4. Click on check box of Maven Integration for Eclipse -> Next -> Agree the Licenses -> Finish
  5. Restart the Eclipse
2. Maven Setup for Mahout
  1. File -> New -> Project -> Select Maven -> Maven Project -> Next -> Next
  2. In Group ID -> com.predictionmarketing [Any name]
  3. Artifact ID -> Name of your project [RecommenderApp]
  4. Finish 
 If you are Getting build path problem in Problem Tab
  1. Right Click on Project 
  2. Properties
  3. Java Build Path -> Libraries -> Add Library 
  4. Select JRE System Library -> Next -> Workspace Default Library -> Finish
  5. Delete JRE System Library [J2SE 1.5] 
  6. OK
3. Now lets edit pom.xml file
  1. Click project and you will see pom.xml -> Open it
  2. Beside Overview tab there will be pom.xml -> click it
  3. Add the Dependency inside <dependencies>  </dependencies>
    <dependency>
    <groupId>org.apache.mahout</groupId>
    <artifactId>mahout-math</artifactId>
    <version>${mahout.version}</version>
</dependency>
  4. Change ${mahout.version} with your mahout version [Example: 0.13.0]
  5. Save and close the file
Done!!!

Recommendation Java Code

Creating Dataset for project
  1. Copy the Dataset from https://mahout.apache.org/users/recommender/userbased-5-minutes.html
  2. Project -> Right Click -> New -> Folder -> Folder Name "data" -> Finish
  3. Right click on "data" Folder -> New -> File 
  4. File name as "dataset.csv" -> paste the Dataset you have copied from the above website and save
Add JAR files 
  1. Extract the Apache Mahout Files -> Inside Mahout Folder -> Copy All Jar files
  2. Right Click on Project -> And paste all jar files
  3. One by one  right click jar file -> Build Path -> Add to Build Path
In src/main/PackageName/App 


package com.predictionmarketing.RecommenderApp;

import java.io.File;
import java.io.IOException;
import java.util.List;

import org.apache.log4j.PropertyConfigurator;
import org.apache.mahout.cf.taste.impl.model.file.FileDataModel;
import org.apache.mahout.cf.taste.impl.neighborhood.ThresholdUserNeighborhood;
import org.apache.mahout.cf.taste.impl.recommender.GenericUserBasedRecommender;
import org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity;
import org.apache.mahout.cf.taste.model.DataModel;
import org.apache.mahout.cf.taste.neighborhood.UserNeighborhood;
import org.apache.mahout.cf.taste.recommender.RecommendedItem;
import org.apache.mahout.cf.taste.recommender.UserBasedRecommender;
import org.apache.mahout.cf.taste.similarity.UserSimilarity;

/**
 * Hello world!
 *
 */
public class App 
{
    public static void main( String[] args ) throws Exception
    {
     String log4jConfPath = "LOG4J/log4j.properties";
     PropertyConfigurator.configure(log4jConfPath);
     
     DataModel model = new FileDataModel(new File("data/dataset.csv"));
     UserSimilarity similarity = new PearsonCorrelationSimilarity(model);
     UserNeighborhood neighborhood = new ThresholdUserNeighborhood(0.1, similarity, model);
     UserBasedRecommender recommender = new GenericUserBasedRecommender(model, neighborhood, similarity);
     
     List<RecommendedItem> recommendations = recommender.recommend(2, 3);
     for (RecommendedItem recommendation : recommendations) {
       System.out.println(recommendation);
     }
     
    }
}

Run the project

IF you getting warn for log4j then 
  1. Create a folder in project as LOG4J
  2. Create a file in folder LOG4J as "log4j.properties" and paste the code 
    log4j.rootLogger=INFO, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.Target=System.out
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
  3. And add the below code 
    String log4jConfPath = "/path/to/log4j.properties";
PropertyConfigurator.configure(log4jConfPath);
    4.  
You might ask yourself, how to make sure that your recommender returns good results.

EvaluationRecommender.java 

package com.predictionmarketing.RecommenderApp;

import java.io.File;
import java.io.IOException;

import org.apache.mahout.cf.taste.common.TasteException;
import org.apache.mahout.cf.taste.eval.RecommenderBuilder;
import org.apache.mahout.cf.taste.eval.RecommenderEvaluator;
import org.apache.mahout.cf.taste.impl.eval.AverageAbsoluteDifferenceRecommenderEvaluator;
import org.apache.mahout.cf.taste.impl.model.file.FileDataModel;
import org.apache.mahout.cf.taste.impl.neighborhood.ThresholdUserNeighborhood;
import org.apache.mahout.cf.taste.impl.recommender.GenericUserBasedRecommender;
import org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity;
import org.apache.mahout.cf.taste.model.DataModel;
import org.apache.mahout.cf.taste.neighborhood.UserNeighborhood;
import org.apache.mahout.cf.taste.recommender.Recommender;
import org.apache.mahout.cf.taste.similarity.UserSimilarity;

public class EvaluateRecommender {

 public static void main(String[] args) throws Exception {
  
  DataModel model = new FileDataModel(new File("data/dataset.csv"));
  RecommenderEvaluator evaluator = new AverageAbsoluteDifferenceRecommenderEvaluator();
  RecommenderBuilder builder = new MyRecommenderBuilder();
  double result = evaluator.evaluate(builder, null, model, 0.9, 1.0);
  System.out.println(result);

 }

}

class MyRecommenderBuilder implements RecommenderBuilder {
 
 public Recommender buildRecommender(DataModel dataModel) throws TasteException{
  UserSimilarity similarity = new PearsonCorrelationSimilarity(dataModel);
  UserNeighborhood neighborhood = new ThresholdUserNeighborhood(0.1, similarity, dataModel);
  return new GenericUserBasedRecommender(dataModel, neighborhood, similarity);
  
 }
 
}

References: https://mahout.apache.org/users/recommender/userbased-5-minutes.html
https://www.youtube.com/watch?v=63k560Livmg

Comments

Post a Comment