Using realKD in your Java Project

##Dependency declaration via Maven##

In order to add realKD to a Java project that is managed via Maven you just have to add two snippets into your pom.xml.

First you have to register the realKD release repository to your <repositories> section (create one if your pom does not yet contain one).

    <repository>
        <id>realKD-releases</id>
        <url>https://bitbucket.org/realKD/releases/raw/master/releases</url>
        <releases>
            <enabled>true</enabled>
            <updatePolicy>always</updatePolicy>
            <checksumPolicy>fail</checksumPolicy>
        </releases>
        <snapshots>
            <enabled>true</enabled>
            <updatePolicy>always</updatePolicy>
            <checksumPolicy>warn</checksumPolicy>
        </snapshots>
    </repository>

Moreover, you have to declare the realKD dependency in your <dependencies> secion.

    <dependency>
        <groupId>de.unibonn</groupId>
        <artifactId>realKD</artifactId>
        <version>0.5.1</version>
        <scope>compile</scope>
    </dependency>

##Example Code## When the dependency is declared correctly, you can use realKD. In the following basic example we also assume that the titanic example data file is available in the resource folder.

#!java

/**
 * Runs the exceptional subgroup sampler on the titanic dataset with target
 * attribute "survived" and positive category "1".
 */
public class ExceptionalSubgroupSamplingForTitanic {

    public static void main(String[] args) {

        // Set up workspace with data import for algorithm
        Workspace workspace = workspace();
        DataTable table = xarfImport("src//main//resources//titanic_1.0.0.xarf").get();
        PropositionalLogic propositions = propositionalLogic(table);
        workspace.addAll(table, propositions);

        // Set up algorithm
        Attribute<?> survived = table.attribute(identifier("survived")).get();
        ExceptionalSubgroupSampler sampler = exceptionalSubgroupSampler(workspace);
        sampler.targetAttributes(survived).useSingleEventModel().positiveCategory("1").numberOfResults(5)
                .numberOfSeeds(500);

        // Run and print results
        Collection<Pattern<?>> subgroups = sampler.call();
        System.out.println(subgroups);

    }

}

Note that this example is based on the following Java imports that have to be present in the source file.

#!java

import static de.unibonn.realkd.algorithms.emm.ExceptionalSubgroupSampler.exceptionalSubgroupSampler;
import static de.unibonn.realkd.common.workspace.Identifier.identifier;
import static de.unibonn.realkd.common.workspace.Workspaces.workspace;
import static de.unibonn.realkd.data.propositions.Propositions.propositionalLogic;
import static de.unibonn.realkd.data.table.XarfImport.xarfImport;

import java.util.Collection;

import de.unibonn.realkd.algorithms.emm.ExceptionalSubgroupSampler;
import de.unibonn.realkd.common.workspace.Workspace;
import de.unibonn.realkd.data.propositions.PropositionalLogic;
import de.unibonn.realkd.data.table.DataTable;
import de.unibonn.realkd.data.table.attribute.Attribute;
import de.unibonn.realkd.patterns.Pattern;

Wiki

realKD / using_realkd_in_java_project

Using realKD in your Java Project