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

package org.greenstone.mars;

/*
import java.io.BufferedInputStream;
import java.io.FileInputStream;

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileReader;
import java.io.FileWriter;

import weka.core.converters.ConverterUtils.DataSource;
import weka.core.Attribute;
import weka.core.Instance;
*/

import weka.core.Instances;
/*
import weka.core.SerializationHelper;

import weka.filters.Filter;
import weka.filters.unsupervised.attribute.Remove;
*/

import weka.classifiers.Classifier;


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

class WekaApplyValenceModel
{
    
    public static void main(String[] args)
    {
    WekaUtil.checkUsageApplyModel(args);
    
    String classifier_input_filename        = args[0];
    String unclassified_data_input_filename = args[1];
    String classified_data_output_filename  = args[2];

    Classifier classifier = WekaUtil.loadClassifierModel(classifier_input_filename);

    Instances unlabeled_instances= WekaUtil.loadInstancesForClassification(unclassified_data_input_filename);

    // It is permissible to run this code and supply it with a data file that includes groundtruth in it.
    // In this situation, the 'unlabeled' instances:
    //  (i) need to be massaged to be in the same form as truly unlabeled data
    // (ii) we also set up 'groundtruth_instances' as an alias (reference) to 'filtered_unlabeled_instanced'
    //      to trigger calculating the error on the predicted vaues

    boolean has_groundtruth_data = WekaUtil.instancesHavePredictAttribute(unlabeled_instances,WekaUtil.VALENCE_ATTRIBUTE_NAME); 

    // The following deals with (i) internally, ensuring that what is returned is suitable for making predictions on
    Instances filtered_unlabeled_instances
        = WekaUtil.filterInstancesForApplying(unlabeled_instances,has_groundtruth_data,
                          WekaUtil.VALENCE_ATTRIBUTE_NAME,"471");

    WekaUtil.checkDatasetInstancesCompatible(filtered_unlabeled_instances,"471");
    
    // The following deals with (ii)
    Instances groundtruth_instances = (has_groundtruth_data) ? filtered_unlabeled_instances : null;

    System.out.println("Predicting valence:");
    Instances labeled_instances = WekaUtil.makePredictions(classifier, filtered_unlabeled_instances, groundtruth_instances);

    /*
    try {
        // Save labeled data
        
        System.out.println("Saving labeled instances: " + classified_data_output_filename);     
        FileWriter fw = new FileWriter(classified_data_output_filename);
        BufferedWriter bw = new BufferedWriter(fw);
        
        bw.write(labeled_instances.toString());
        bw.newLine();
        bw.flush();
        bw.close();
             
    }
    catch (Exception e) {
        e.printStackTrace();
    }
    */
    
    WekaUtil.saveInstancesAsDataSink(labeled_instances,classified_data_output_filename);
    }
}