Example usage for weka.classifiers.evaluation.output.prediction AbstractOutput setHeader

Introduction

In this page you can find the example usage for weka.classifiers.evaluation.output.prediction AbstractOutput setHeader.

Prototype

public void setHeader(Instances value) 

Source Link

Document

Sets the header of the dataset.

Usage

From source file:dkpro.similarity.experiments.rte.util.Evaluator.java

License:Open Source License

public static void runClassifier(WekaClassifier wekaClassifier, Dataset trainDataset, Dataset testDataset)
        throws Exception {
    Classifier baseClassifier = ClassifierSimilarityMeasure.getClassifier(wekaClassifier);

    // Set up the random number generator
    long seed = new Date().getTime();
    Random random = new Random(seed);

    // Add IDs to the train instances and get the instances
    AddID.main(new String[] { "-i", MODELS_DIR + "/" + trainDataset.toString() + ".arff", "-o",
            MODELS_DIR + "/" + trainDataset.toString() + "-plusIDs.arff" });
    Instances train = DataSource.read(MODELS_DIR + "/" + trainDataset.toString() + "-plusIDs.arff");
    train.setClassIndex(train.numAttributes() - 1);

    // Add IDs to the test instances and get the instances
    AddID.main(new String[] { "-i", MODELS_DIR + "/" + testDataset.toString() + ".arff", "-o",
            MODELS_DIR + "/" + testDataset.toString() + "-plusIDs.arff" });
    Instances test = DataSource.read(MODELS_DIR + "/" + testDataset.toString() + "-plusIDs.arff");
    test.setClassIndex(test.numAttributes() - 1);

    // Instantiate the Remove filter
    Remove removeIDFilter = new Remove();
    removeIDFilter.setAttributeIndices("first");

    // Randomize the data
    test.randomize(random);/*  w  ww . j av  a 2s .co m*/

    // Apply log filter
    //       Filter logFilter = new LogFilter();
    //       logFilter.setInputFormat(train);
    //       train = Filter.useFilter(train, logFilter);        
    //       logFilter.setInputFormat(test);
    //       test = Filter.useFilter(test, logFilter);

    // Copy the classifier
    Classifier classifier = AbstractClassifier.makeCopy(baseClassifier);

    // Instantiate the FilteredClassifier
    FilteredClassifier filteredClassifier = new FilteredClassifier();
    filteredClassifier.setFilter(removeIDFilter);
    filteredClassifier.setClassifier(classifier);

    // Build the classifier
    filteredClassifier.buildClassifier(train);

    // Prepare the output buffer 
    AbstractOutput output = new PlainText();
    output.setBuffer(new StringBuffer());
    output.setHeader(test);
    output.setAttributes("first");

    Evaluation eval = new Evaluation(train);
    eval.evaluateModel(filteredClassifier, test, output);

    // Convert predictions to CSV
    // Format: inst#, actual, predicted, error, probability, (ID)
    String[] scores = new String[new Double(eval.numInstances()).intValue()];
    double[] probabilities = new double[new Double(eval.numInstances()).intValue()];
    for (String line : output.getBuffer().toString().split("\n")) {
        String[] linesplit = line.split("\\s+");

        // If there's been an error, the length of linesplit is 6, otherwise 5,
        // due to the error flag "+"

        int id;
        String expectedValue, classification;
        double probability;

        if (line.contains("+")) {
            id = Integer.parseInt(linesplit[6].substring(1, linesplit[6].length() - 1));
            expectedValue = linesplit[2].substring(2);
            classification = linesplit[3].substring(2);
            probability = Double.parseDouble(linesplit[5]);
        } else {
            id = Integer.parseInt(linesplit[5].substring(1, linesplit[5].length() - 1));
            expectedValue = linesplit[2].substring(2);
            classification = linesplit[3].substring(2);
            probability = Double.parseDouble(linesplit[4]);
        }

        scores[id - 1] = classification;
        probabilities[id - 1] = probability;
    }

    System.out.println(eval.toSummaryString());
    System.out.println(eval.toMatrixString());

    // Output classifications
    StringBuilder sb = new StringBuilder();
    for (String score : scores)
        sb.append(score.toString() + LF);

    FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + testDataset.toString() + "/"
            + wekaClassifier.toString() + "/" + testDataset.toString() + ".csv"), sb.toString());

    // Output probabilities
    sb = new StringBuilder();
    for (Double probability : probabilities)
        sb.append(probability.toString() + LF);

    FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + testDataset.toString() + "/"
            + wekaClassifier.toString() + "/" + testDataset.toString() + ".probabilities.csv"), sb.toString());

    // Output predictions
    FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + testDataset.toString() + "/"
            + wekaClassifier.toString() + "/" + testDataset.toString() + ".predictions.txt"),
            output.getBuffer().toString());

    // Output meta information
    sb = new StringBuilder();
    sb.append(classifier.toString() + LF);
    sb.append(eval.toSummaryString() + LF);
    sb.append(eval.toMatrixString() + LF);

    FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + testDataset.toString() + "/"
            + wekaClassifier.toString() + "/" + testDataset.toString() + ".meta.txt"), sb.toString());
}

---