source: main/trunk/model-sites-dev/mars/src/java/org/greenstone/mars/WekaTrainArousalModel.java@ 35207

package org.greenstone.mars;
    
import weka.core.Instances;
 
import weka.classifiers.Classifier;
import weka.classifiers.Evaluation;

// Based on:
//   https://waikato.github.io/weka-wiki/use_weka_in_your_java_code/


// Also, for a more direct command-line approach see
//    https://waikato.github.io/weka-wiki/saving_and_loading_models/
//
// You save a trained classifier with the -d option (dumping), e.g.:
//
//   java weka.classifiers.trees.J48 -C 0.25 -M 2 -t /some/where/train.arff -d /other/place/j48.model
//
// And you can load it with -l and use it on a test set, e.g.:
//
//   java weka.classifiers.trees.J48 -l /other/place/j48.model -T /some/where/test.arff

     
class WekaTrainArousalModel
{
    // Scheme:       weka.classifiers.trees.REPTree -M 2 -V 0.001 -N 3 -S 1 -L -1 -I 0.0   -- (i.e., default vals)
    // Relation:     deam-essentia-features-arousal-valence-weka.filters.unsupervised.attribute.Remove-R472-weka.filters.unsupervised.attribute.Remove-R458-466
    // Instances:    1743

    // Note, above missed -R 425 and 427 (ordinal vals)
    
    public static void main(String[] args)
    {   
    WekaUtil.checkUsageTraining(args);
    
    String input_data_filename = args[0];
    String output_model_filename = args[1];

    // knock out 472 (valence) from dataset
    Instances filtered_data_instances = WekaUtil.loadAndFilterDataInstances(input_data_filename, "472");
    Classifier classifier = WekaUtil.trainREPTree(filtered_data_instances);
    System.out.println(classifier);

    Evaluation eval = WekaUtil.evaluateClassifier(classifier,filtered_data_instances);
    System.out.println(eval.toSummaryString());

    try {
        System.out.println("Saving REPTree classifier model as: " + output_model_filename);
        weka.core.SerializationHelper.write(output_model_filename, classifier);
    }
    catch (Exception e) {
        e.printStackTrace();
    }   
    }
}