Example usage for weka.core.converters ArffSaver resetOptions

Introduction

In this page you can find the example usage for weka.core.converters ArffSaver resetOptions.

Prototype

@Override
public void resetOptions() 

Source Link

Document

Resets the Saver

Usage

From source file:es.upm.dit.gsi.barmas.dataset.utils.DatasetSplitter.java

License:Open Source License

/**
 * @param folds/*from  w  ww. j a v a 2s .c  o m*/
 * @param minAgents
 * @param maxAgents
 * @param originalDatasetPath
 * @param outputDir
 * @param scenario
 * @param logger
 */
public void splitDataset(int folds, int minAgents, int maxAgents, String originalDatasetPath, String outputDir,
        String scenario, Logger logger) {

    int ratioint = (int) ((1 / (double) folds) * 100);
    double roundedratio = ((double) ratioint) / 100;

    // Look for essentials
    List<String[]> essentials = this.getEssentials(originalDatasetPath, logger);

    for (int fold = 0; fold < folds; fold++) {
        String outputDirWithRatio = outputDir + "/" + roundedratio + "testRatio/iteration-" + fold;
        File dir = new File(outputDirWithRatio);
        if (!dir.exists() || !dir.isDirectory()) {
            dir.mkdirs();
        }

        logger.finer("--> splitDataset()");
        logger.fine("Creating experiment.info...");

        try {

            Instances originalData = this.getDataFromCSV(originalDatasetPath);

            originalData.randomize(new Random());
            originalData.stratify(folds);

            // TestDataSet
            Instances testData = originalData.testCV(folds, fold);
            CSVSaver saver = new CSVSaver();
            ArffSaver arffsaver = new ArffSaver();
            File file = new File(outputDirWithRatio + File.separator + "test-dataset.csv");
            if (!file.exists()) {
                saver.resetOptions();
                saver.setInstances(testData);
                saver.setFile(file);
                saver.writeBatch();
            }

            file = new File(outputDirWithRatio + File.separator + "test-dataset.arff");
            if (!file.exists()) {
                arffsaver.resetOptions();
                arffsaver.setInstances(testData);
                arffsaver.setFile(file);
                arffsaver.writeBatch();
            }

            // BayesCentralDataset
            Instances trainData = originalData.trainCV(folds, fold);
            file = new File(outputDirWithRatio + File.separator + "bayes-central-dataset.csv");
            if (!file.exists()) {
                saver.resetOptions();
                saver.setInstances(trainData);
                saver.setFile(file);
                saver.writeBatch();
                this.copyFileUsingApacheCommonsIO(file,
                        new File(
                                outputDirWithRatio + File.separator + "bayes-central-dataset-noEssentials.csv"),
                        logger);
                CsvWriter w = new CsvWriter(new FileWriter(file, true), ',');
                for (String[] essential : essentials) {
                    w.writeRecord(essential);
                }
                w.close();
            }
            file = new File(outputDirWithRatio + File.separator + "bayes-central-dataset.arff");
            if (!file.exists()) {
                arffsaver.resetOptions();
                arffsaver.setInstances(trainData);
                arffsaver.setFile(file);
                arffsaver.writeBatch();
                this.copyFileUsingApacheCommonsIO(file, new File(
                        outputDirWithRatio + File.separator + "bayes-central-dataset-noEssentials.arff"),
                        logger);
                CsvWriter w = new CsvWriter(new FileWriter(file, true), ',');
                for (String[] essential : essentials) {
                    w.writeRecord(essential);
                }
                w.close();
            }

            // Agent datasets
            CsvReader csvreader = new CsvReader(new FileReader(new File(originalDatasetPath)));
            csvreader.readHeaders();
            String[] headers = csvreader.getHeaders();
            csvreader.close();

            for (int agents = minAgents; agents <= maxAgents; agents++) {
                this.createExperimentInfoFile(folds, agents, originalDatasetPath, outputDirWithRatio, scenario,
                        logger);
                HashMap<String, CsvWriter> writers = new HashMap<String, CsvWriter>();
                String agentsDatasetsDir = outputDirWithRatio + File.separator + agents + "agents";
                HashMap<String, CsvWriter> arffWriters = new HashMap<String, CsvWriter>();
                File f = new File(agentsDatasetsDir);
                if (!f.isDirectory()) {
                    f.mkdirs();
                }
                Instances copy = new Instances(trainData);
                copy.delete();
                for (int i = 0; i < agents; i++) {
                    String fileName = agentsDatasetsDir + File.separator + "agent-" + i + "-dataset.csv";
                    file = new File(fileName);
                    if (!file.exists()) {
                        CsvWriter writer = new CsvWriter(new FileWriter(fileName), ',');
                        writer.writeRecord(headers);
                        writers.put("AGENT" + i, writer);
                    }
                    fileName = agentsDatasetsDir + File.separator + "agent-" + i + "-dataset.arff";
                    file = new File(fileName);
                    if (!file.exists()) {
                        arffsaver.resetOptions();
                        arffsaver.setInstances(copy);
                        arffsaver.setFile(new File(fileName));
                        arffsaver.writeBatch();
                        CsvWriter arffwriter = new CsvWriter(new FileWriter(fileName, true), ',');
                        arffWriters.put("AGENT" + i, arffwriter);
                    }

                    logger.fine("AGENT" + i + " dataset created in csv and arff formats.");
                }
                // Append essentials to all
                for (String[] essential : essentials) {
                    for (CsvWriter wr : writers.values()) {
                        wr.writeRecord(essential);
                    }
                    for (CsvWriter arffwr : arffWriters.values()) {
                        arffwr.writeRecord(essential);
                    }
                }

                int agentCounter = 0;
                for (int j = 0; j < trainData.numInstances(); j++) {
                    Instance instance = trainData.instance(j);
                    CsvWriter writer = writers.get("AGENT" + agentCounter);
                    CsvWriter arffwriter = arffWriters.get("AGENT" + agentCounter);
                    String[] row = new String[instance.numAttributes()];
                    for (int a = 0; a < instance.numAttributes(); a++) {
                        row[a] = instance.stringValue(a);
                    }
                    if (writer != null) {
                        writer.writeRecord(row);
                    }
                    if (arffwriter != null) {
                        arffwriter.writeRecord(row);
                    }
                    agentCounter++;
                    if (agentCounter == agents) {
                        agentCounter = 0;
                    }
                }

                for (CsvWriter wr : writers.values()) {
                    wr.close();
                }
                for (CsvWriter arffwr : arffWriters.values()) {
                    arffwr.close();
                }
            }

        } catch (Exception e) {
            logger.severe("Exception while splitting dataset. ->");
            logger.severe(e.getMessage());
            System.exit(1);
        }

        logger.finest("Dataset for fold " + fold + " created.");
    }

    logger.finer("<-- splitDataset()");

}

---