Example usage for weka.core Instances Instances

List of usage examples for weka.core Instances Instances

  1. HOME
  2. Java
  3. weka
  4. weka.core.*
  5. Instances
  6. Instances

Introduction

In this page you can find the example usage for weka.core Instances Instances.

Prototype

public Instances(String name, ArrayList<Attribute> attInfo, int capacity)

Source Link

Document

Creates an empty set of instances.

Usage

From source file:de.upb.timok.utils.DatasetTransformationUtils.java

License:Open Source License

public static Instances testSetToInstances(List<double[]> testSet) {
    if (testSet.size() == 0) {
        logger.warn("TestSet has size 0");
    }//from   ww w .  j a va2 s .c o m
    final double[] sample = testSet.get(0);
    final ArrayList<Attribute> fvWekaAttributes = new ArrayList<>(sample.length);
    for (int i = 0; i < sample.length; i++) {
        fvWekaAttributes.add(new Attribute(Integer.toString(i)));
    }
    final ArrayList<String> classStrings = new ArrayList<>();
    classStrings.add("normal");
    final Attribute ClassAttribute = new Attribute("class", classStrings);
    fvWekaAttributes.add(ClassAttribute);

    // Declare the feature vector
    final Instances result = new Instances("testSet", fvWekaAttributes, testSet.size());
    result.setClassIndex(fvWekaAttributes.size() - 1);
    for (final double[] instance : testSet) {
        final Instance wekaInstance = new DenseInstance(1, instance);
        wekaInstance.setDataset(result);
        result.add(wekaInstance);
    }
    return result;
}

From source file:detplagiasi.TextDirectoryToArff.java

License:Open Source License

public Instances createDataset(String directoryPath) throws Exception {

    FastVector atts = new FastVector(2);
    atts.addElement(new Attribute("filename", (FastVector) null));
    atts.addElement(new Attribute("contents", (FastVector) null));

    /*/*  w  w  w. j av a  2  s  .c  o  m*/
    ArrayList atts = new ArrayList(2);
    atts.addElement(new Attribute("filename", (ArrayList) null));
    atts.addElement(new Attribute("contents", (ArrayList) null));
     */
    Instances data = new Instances("text_files_in_" + directoryPath, atts, 0);
    File dir = new File(directoryPath);
    String[] files = dir.list();
    //create file a untuk menampung name file dari instance yang terkait
    //FileWriter fstream = new FileWriter(directoryPath+"\\cluster detail.txt");
    BufferedWriter out = null;
    out = new BufferedWriter(new FileWriter(directoryPath + "\\cluster detail.txt"));

    for (int i = 0; i < files.length; i++) {
        if (files[i].endsWith(".txt")) {
            out.write("file ke " + (i + 1) + ": " + files[i]);
            System.out.println("processed files:" + files[i]);
            fileName[i] = files[i];
            out.write("file ke " + (i + 1) + ": " + files[i]);
            try {
                double[] newInst = new double[2];
                newInst[0] = (double) data.attribute(0).addStringValue(files[i]);
                File txt = new File(directoryPath + File.separator + files[i]);

                System.out.println("TDTARFF: " + txt.getCanonicalPath());

                InputStreamReader is;
                is = new InputStreamReader(new FileInputStream(txt));
                StringBuffer txtStr = new StringBuffer();
                int c;
                while ((c = is.read()) != -1) {
                    txtStr.append((char) c);
                }
                newInst[1] = (double) data.attribute(1).addStringValue(txtStr.toString());
                try {
                    out.write("file ke " + (i + 1) + ": " + files[i]);
                    System.out.println("success");
                } catch (Exception d) {
                    System.err.println(d.getLocalizedMessage());
                }
                //input pada file a nama file dari instance
                //data.add(new Instance(1.0, newInst));
                data.add(new Instance(1.0, newInst));
                //data.renameAttributeValue(data.attribute("att_name_in_data2"),"att_value_in_data2","att_value_in_data1");
            } catch (Exception e) {
                System.err.println("failed to convert file: " + directoryPath + File.separator + files[i]);
            }
        }
    }
    return data;
}

From source file:DiversifyQuery.DivTopK.java

/**
 * Sets the format of the filtered instances that are output. I.e. will
 * include k attributes each shapelet distance and a class value
 *
 * @param inputFormat the format of the input data
 * @return a new Instances object in the desired output format
 * @throws Exception if all required parameters of the filter are not
 * initialised correctly/*ww  w  .j  a va  2 s.  c o m*/
 */
protected Instances determineOutputFormat(Instances inputFormat, ArrayList<LegacyShapelet> shapelets)
        throws Exception {

    //Set up instances size and format.
    //int length = this.numShapelets;
    int length = shapelets.size();
    FastVector atts = new FastVector();
    String name;
    for (int i = 0; i < length; i++) {
        name = "Shapelet_" + i;
        atts.addElement(new Attribute(name));
    }

    if (inputFormat.classIndex() >= 0) { //Classification set, set class
        //Get the class values as a fast vector
        Attribute target = inputFormat.attribute(inputFormat.classIndex());

        FastVector vals = new FastVector(target.numValues());
        for (int i = 0; i < target.numValues(); i++) {
            vals.addElement(target.value(i));
        }
        atts.addElement(new Attribute(inputFormat.attribute(inputFormat.classIndex()).name(), vals));
    }
    Instances result = new Instances("Shapelets" + inputFormat.relationName(), atts,
            inputFormat.numInstances());
    if (inputFormat.classIndex() >= 0) {
        result.setClassIndex(result.numAttributes() - 1);
    }
    return result;
}

From source file:DiversifyTopKShaepelet.DiversifyTopKShaepelet.java

/**
 * Sets the format of the filtered instances that are output. I.e. will
 * include k attributes each shapelet distance and a class value
 *
 * @param inputFormat the format of the input data
 * @return a new Instances object in the desired output format
 * @throws Exception if all required parameters of the filter are not
 * initialised correctly//  ww w.j  a  va2  s.  c  o  m
 */
@Override
protected Instances determineOutputFormat(Instances inputFormat) throws Exception {

    if (this.numShapelets < 1) {
        throw new Exception(
                "ShapeletFilter not initialised correctly - please specify a value of k that is greater than or equal to 1");
    }

    //Set up instances size and format.
    //int length = this.numShapelets;
    int length = this.shapelets.size();
    FastVector atts = new FastVector();
    String name;
    for (int i = 0; i < length; i++) {
        name = "Shapelet_" + i;
        atts.addElement(new Attribute(name));
    }

    if (inputFormat.classIndex() >= 0) { //Classification set, set class
        //Get the class values as a fast vector
        Attribute target = inputFormat.attribute(inputFormat.classIndex());

        FastVector vals = new FastVector(target.numValues());
        for (int i = 0; i < target.numValues(); i++) {
            vals.addElement(target.value(i));
        }
        atts.addElement(new Attribute(inputFormat.attribute(inputFormat.classIndex()).name(), vals));
    }
    Instances result = new Instances("Shapelets" + inputFormat.relationName(), atts,
            inputFormat.numInstances());
    if (inputFormat.classIndex() >= 0) {
        result.setClassIndex(result.numAttributes() - 1);
    }
    return result;
}

From source file:edu.cmu.cs.in.hoop.hoops.analyze.HoopWekaML.java

License:Open Source License

/**
 *
 *//*from  ww  w . j a  v a 2s.c o m*/
public HoopWekaML() {
    setClassName("HoopWekaML");
    debug("HoopWekaML ()");

    removeOutPort("KV");

    setHoopDescription("Run Weka Machine Learning");

    String[] options = new String[1];
    options[0] = "-U"; // unpruned tree
    J48 tree = new J48(); // new instance of tree

    try {
        tree.setOptions(options);
    } catch (Exception e1) {
        // TODO Auto-generated catch block
        e1.printStackTrace();
    }

    // Declare a nominal attribute along with its values
    FastVector fvNominalVal = new FastVector(3);
    fvNominalVal.addElement("blue");
    fvNominalVal.addElement("gray");
    fvNominalVal.addElement("black");

    // Declare the class attribute along with its values
    FastVector fvClassVal = new FastVector(2);
    fvClassVal.addElement("positive");
    fvClassVal.addElement("negative");
    Attribute ClassAttribute = new Attribute("theClass", fvClassVal);

    // Declare two numeric attributes
    Attribute Attribute1 = new Attribute("firstNumeric");
    Attribute Attribute2 = new Attribute("secondNumeric");
    Attribute Attribute3 = new Attribute("aNominal", fvNominalVal);

    // Declare the feature vector
    FastVector fvWekaAttributes = new FastVector(4);
    fvWekaAttributes.addElement(Attribute1);
    fvWekaAttributes.addElement(Attribute2);
    fvWekaAttributes.addElement(Attribute3);
    fvWekaAttributes.addElement(ClassAttribute);

    // Create an empty training set
    Instances isTrainingSet = new Instances("Rel", fvWekaAttributes, 10);

    // Set class index
    isTrainingSet.setClassIndex(3);

    try {
        tree.buildClassifier(isTrainingSet);
    } catch (Exception e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
}

From source file:edu.cmu.lti.oaqa.baseqa.providers.ml.classifiers.MekaProvider.java

License:Apache License

@Override
public void train(List<Map<String, Double>> X, List<String> Y, boolean crossValidation)
        throws AnalysisEngineProcessException {
    // create attribute (including label) info
    ArrayList<Attribute> attributes = new ArrayList<>();
    List<String> labelNames = ClassifierProvider.labelNames(Y);
    labelNames.stream().map(attr -> new Attribute(attr, Arrays.asList("y", "n")))
            .forEachOrdered(attributes::add);
    List<String> featureNames = ClassifierProvider.featureNames(X);
    featureNames.stream().map(Attribute::new).forEachOrdered(attributes::add);
    String name = Files.getNameWithoutExtension(modelFile.getName());
    datasetSchema = new Instances(name, attributes, 0);
    datasetSchema.setClassIndex(labelNames.size());
    // add instances
    // due to the limitation of the interface definition, X, Y should be reorganized
    SetMultimap<Map<String, Double>, String> XY = HashMultimap.create();
    IntStream.range(0, X.size()).forEach(i -> XY.put(X.get(i), Y.get(i)));
    Instances trainingInstances = new Instances(datasetSchema, XY.size());
    for (Map.Entry<Map<String, Double>, Collection<String>> entry : XY.asMap().entrySet()) {
        Set<String> y = ImmutableSet.copyOf(entry.getValue());
        Map<String, Double> x = entry.getKey();
        SparseInstance instance = new SparseInstance(labelNames.size() + x.size());
        for (String labelName : labelNames) {
            instance.setValue(datasetSchema.attribute(labelName), y.contains(labelName) ? "y" : "n");
        }/*from ww  w. j  a  v  a  2s  . co  m*/
        for (Map.Entry<String, Double> e : x.entrySet()) {
            instance.setValue(datasetSchema.attribute(e.getKey()), e.getValue());
        }
        trainingInstances.add(instance);
    }
    // training
    try {
        classifier = (MultiLabelClassifier) AbstractClassifier.forName(classifierName, options);
        classifier.buildClassifier(trainingInstances);
    } catch (Exception e) {
        throw new AnalysisEngineProcessException(e);
    }
    try {
        SerializationHelper.write(modelFile.getAbsolutePath(), classifier);
        SerializationHelper.write(datasetSchemaFile.getAbsolutePath(), datasetSchema);
    } catch (Exception e) {
        throw new AnalysisEngineProcessException(e);
    }
    if (crossValidation) {
        try {
            Evaluation eval = new Evaluation(trainingInstances);
            Random rand = new Random();
            eval.crossValidateModel(classifier, trainingInstances, 10, rand);
            LOG.debug(eval.toSummaryString());
        } catch (Exception e) {
            throw new AnalysisEngineProcessException(e);
        }
    }
}

From source file:edu.cmu.lti.oaqa.baseqa.providers.ml.classifiers.WekaProvider.java

License:Apache License

@Override
public void train(List<Map<String, Double>> X, List<String> Y, boolean crossValidation)
        throws AnalysisEngineProcessException {
    // create attribute (including label) info
    ArrayList<Attribute> attributes = new ArrayList<>();
    ClassifierProvider.featureNames(X).stream().map(Attribute::new).forEachOrdered(attributes::add);
    Attribute label = new Attribute("__label__", ClassifierProvider.labelNames(Y));
    attributes.add(label);//from w ww . j av a2  s  . com
    String name = Files.getNameWithoutExtension(modelFile.getName());
    datasetSchema = new Instances(name, attributes, X.size());
    datasetSchema.setClass(label);
    // add instances
    Instances trainingInstances = new Instances(datasetSchema, X.size());
    if (balanceWeight) {
        Multiset<String> labelCounts = HashMultiset.create(Y);
        double maxCount = labelCounts.entrySet().stream().mapToInt(Multiset.Entry::getCount).max()
                .orElseThrow(AnalysisEngineProcessException::new);
        for (int i = 0; i < X.size(); i++) {
            String y = Y.get(i);
            double weight = maxCount / labelCounts.count(y);
            trainingInstances.add(newInstance(X.get(i), y, weight, trainingInstances));
        }
    } else {
        for (int i = 0; i < X.size(); i++) {
            trainingInstances.add(newInstance(X.get(i), Y.get(i), 1.0, trainingInstances));
        }
    }
    // training
    try {
        classifier = AbstractClassifier.forName(classifierName, options);
        classifier.buildClassifier(trainingInstances);
    } catch (Exception e) {
        throw new AnalysisEngineProcessException(e);
    }
    // write model and dataset schema
    try {
        SerializationHelper.write(modelFile.getAbsolutePath(), classifier);
        SerializationHelper.write(datasetSchemaFile.getAbsolutePath(), datasetSchema);
    } catch (Exception e) {
        throw new AnalysisEngineProcessException(e);
    }
    // backup training dataset as arff file
    if (datasetExportFile != null) {
        try {
            ArffSaver saver = new ArffSaver();
            saver.setInstances(trainingInstances);
            saver.setFile(datasetExportFile);
            saver.writeBatch();
        } catch (IOException e) {
            throw new AnalysisEngineProcessException(e);
        }
    }
    if (crossValidation) {
        try {
            Evaluation eval = new Evaluation(trainingInstances);
            Random rand = new Random();
            eval.crossValidateModel(classifier, trainingInstances, 10, rand);
            LOG.debug(eval.toSummaryString());
        } catch (Exception e) {
            throw new AnalysisEngineProcessException(e);
        }
    }
}

From source file:edu.cuny.qc.speech.AuToBI.util.ClassifierUtils.java

License:Open Source License

/**
 * Converts a feature set object to a weka Instances object
 * <p/>/*from w w  w.  ja v  a  2s. c o  m*/
 * The class is set to the last attribute.
 *
 * @param feature_set the feature set to convert
 * @return a weka instances object
 * @throws Exception If the arff file can't be written or read.
 */
public static Instances convertFeatureSetToWekaInstances(FeatureSet feature_set) throws Exception {
    ArrayList<Attribute> attributes = generateWekaAttributes(feature_set.getFeatures());
    Instances instances = new Instances("AuToBI_feature_set", attributes, feature_set.getDataPoints().size());
    for (Word w : feature_set.getDataPoints()) {
        Instance inst = ClassifierUtils.assignWekaAttributes(instances, w);
        instances.add(inst);
    }

    ClassifierUtils.setWekaClassAttribute(instances, feature_set.getClassAttribute());
    return instances;
}

From source file:edu.cuny.qc.speech.AuToBI.util.ClassifierUtils.java

License:Open Source License

/**
 * Converts a feature set object to a weka Instances object.
 * <p/>/*from w w  w .j  a  v a 2  s.c o  m*/
 * Use wekas instance weighting capability to assign weights for each data point.
 *
 * @param feature_set the feature set to convert
 * @param fn          a weight function
 * @return a weka instances object
 */
public static Instances convertFeatureSetToWeightedWekaInstances(FeatureSet feature_set, WeightFunction fn) {
    ArrayList<Attribute> attributes = generateWekaAttributes(feature_set.getFeatures());
    Instances instances = new Instances("AuToBI_feature_set", attributes, feature_set.getDataPoints().size());
    for (Word w : feature_set.getDataPoints()) {
        Instance inst = ClassifierUtils.assignWekaAttributes(instances, w);
        inst.setWeight(fn.weight(w));
        instances.add(inst);
    }

    ClassifierUtils.setWekaClassAttribute(instances, feature_set.getClassAttribute());
    return instances;
}

From source file:edu.cuny.qc.speech.AuToBI.util.ClassifierUtils.java

License:Open Source License

/**
 * Constructs a data point to a weka instance given a FastVector of weka attribute and a class attribute.
 *
 * @param attributes      a FastVector of weka attributes
 * @param data_point      the data point to convert
 * @param class_attribute the class attribute
 * @return a weka instance./*from   www.ja v  a2  s.  c om*/
 */
protected static Instance constructWekaInstance(ArrayList<Attribute> attributes, Word data_point,
        String class_attribute) {
    Instances instances = new Instances("single_instance_set", attributes, 0);

    setWekaClassAttribute(instances, class_attribute);
    return assignWekaAttributes(instances, data_point);
}