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(Instances dataset)

Source Link

Document

Constructor copying all instances and references to the header information from the given set of instances.

Usage

From source file:controller.DecisionTreeServlet.java

@Override
protected void doPost(HttpServletRequest request, HttpServletResponse response)
        throws ServletException, IOException {
    request.setCharacterEncoding("UTF-8");
    String dir = "/data/";
    String path = getServletContext().getRealPath(dir);

    String action = request.getParameter("action");

    switch (action) {
    case "create": {
        String fileName = request.getParameter("file");

        String aux = fileName.substring(0, fileName.indexOf("."));
        String pathInput = path + "/" + request.getParameter("file");
        String pathTrainingOutput = path + "/" + aux + "-training-arff.txt";
        String pathTestOutput = path + "/" + aux + "-test-arff.txt";
        String pathDecisionTree = path + "/" + aux + "-decisionTree.txt";

        String name = request.getParameter("name");
        int range = Integer.parseInt(request.getParameter("range"));

        int size = Integer.parseInt(request.getParameter("counter"));
        String[] columns = new String[size];
        String[] types = new String[size];
        int[] positions = new int[size];
        int counter = 0;
        for (int i = 0; i < size; i++) {
            if (request.getParameter("column-" + (i + 1)) != null) {
                columns[counter] = request.getParameter("column-" + (i + 1));
                types[counter] = request.getParameter("type-" + (i + 1));
                positions[counter] = Integer.parseInt(request.getParameter("position-" + (i + 1)));
                counter++;/*  w w w  .jav a  2s .  c  o  m*/
            }
        }

        FormatFiles.convertTxtToArff(pathInput, pathTrainingOutput, pathTestOutput, name, columns, types,
                positions, counter, range);
        try {
            J48 j48 = new J48();

            BufferedReader readerTraining = new BufferedReader(new FileReader(pathTrainingOutput));
            Instances instancesTraining = new Instances(readerTraining);
            instancesTraining.setClassIndex(instancesTraining.numAttributes() - 1);

            j48.buildClassifier(instancesTraining);

            BufferedReader readerTest = new BufferedReader(new FileReader(pathTestOutput));
            //BufferedReader readerTest = new BufferedReader(new FileReader(pathTrainingOutput));
            Instances instancesTest = new Instances(readerTest);
            instancesTest.setClassIndex(instancesTest.numAttributes() - 1);

            int corrects = 0;
            int truePositive = 0;
            int trueNegative = 0;
            int falsePositive = 0;
            int falseNegative = 0;

            for (int i = 0; i < instancesTest.size(); i++) {
                Instance instance = instancesTest.get(i);
                double correctValue = instance.value(instance.attribute(instancesTest.numAttributes() - 1));
                double classification = j48.classifyInstance(instance);

                if (correctValue == classification) {
                    corrects++;
                }
                if (correctValue == 1 && classification == 1) {
                    truePositive++;
                }
                if (correctValue == 1 && classification == 0) {
                    falseNegative++;
                }
                if (correctValue == 0 && classification == 1) {
                    falsePositive++;
                }
                if (correctValue == 0 && classification == 0) {
                    trueNegative++;
                }
            }

            Evaluation eval = new Evaluation(instancesTraining);
            eval.evaluateModel(j48, instancesTest);

            PrintWriter writer = new PrintWriter(new BufferedWriter(new FileWriter(pathDecisionTree, false)));

            writer.println(j48.toString());

            writer.println("");
            writer.println("");
            writer.println("Results");
            writer.println(eval.toSummaryString());

            writer.close();

            response.sendRedirect("DecisionTree?action=view&corrects=" + corrects + "&totalTest="
                    + instancesTest.size() + "&totalTrainig=" + instancesTraining.size() + "&truePositive="
                    + truePositive + "&trueNegative=" + trueNegative + "&falsePositive=" + falsePositive
                    + "&falseNegative=" + falseNegative + "&fileName=" + aux + "-decisionTree.txt");
        } catch (Exception e) {
            System.out.println(e.getMessage());
            response.sendRedirect("Navigation?action=decisionTree");
        }

        break;
    }
    default:
        response.sendError(404);
    }
}

From source file:controller.KMeansBean.java

public void handleFileUpload(FileUploadEvent event) {
    FacesMessage message = new FacesMessage("Succesful", event.getFile().getFileName() + " is uploaded.");
    FacesContext.getCurrentInstance().addMessage(null, message);

    try {/*from   w  ww.ja  v a 2 s. c  o m*/
        if (event.getFile().getFileName().endsWith(".arff")) {
            inst = new Instances(new InputStreamReader(event.getFile().getInputstream()));
        } else {
            CSVLoader scv = new CSVLoader();
            scv.setSource(event.getFile().getInputstream());
            inst = scv.getDataSet();
        }
        spalten = new ArrayList<>();
        for (int i = 0; i < inst.firstInstance().numAttributes(); i++) {
            spalten.add(inst.firstInstance().attribute(i).name());
        }
        this.description = this.inst.toSummaryString();
        calculate();
    } catch (IOException ex) {
        System.out.println("Fehler: " + ex);
    }
}

From source file:controller.MineroControler.java

public String regresionLineal() {
    BufferedReader breader = null;
    Instances datos = null;/* w w w  .  j  a va 2s .  c om*/
    breader = new BufferedReader(fuente_arff);
    try {
        datos = new Instances(breader);
        datos.setClassIndex(datos.numAttributes() - 1); // clase principal, ltima en atributos
    } catch (IOException ex) {
        System.err.println("Problemas al intentar cargar los datos");
    }

    LinearRegression regresionL = new LinearRegression();
    try {

        regresionL.buildClassifier(datos);

        Instance nuevaCal = datos.lastInstance();
        double calif = regresionL.classifyInstance(nuevaCal);

        setValorCalculado(new Double(calif));

    } catch (Exception ex) {
        System.err.println("Problemas al clasificar instancia");
    }

    return regresionL.toString();
}

From source file:controller.MineroControler.java

public String clasificarSimpleKmeans(int numClusters) {
    BufferedReader breader = null;
    Instances datos = null;/* ww w .  java2  s .  c  om*/
    breader = new BufferedReader(fuente_arff);
    try {
        datos = new Instances(breader);
    } catch (IOException ex) {
        System.err.println("Problemas al intentar cargar los datos");
    }

    SimpleKMeans skmeans = new SimpleKMeans();

    try {
        skmeans.setSeed(10);
        skmeans.setPreserveInstancesOrder(true);
        skmeans.setNumClusters(numClusters);
        skmeans.buildClusterer(datos);
    } catch (Exception ex) {
        System.err.println("Problemas al ejecutar algorimo de clasificacion");
    }
    return skmeans.toString();
}

From source file:controller.MineroControler.java

public String clasificardorArbolAleat(String atributo) {
    BufferedReader breader = null;
    Instances datos = null;/*w w  w . j  a  v  a2  s .  c o  m*/
    breader = new BufferedReader(fuente_arff);
    try {
        datos = new Instances(breader);
        Attribute atr = datos.attribute(atributo);
        datos.setClass(atr);
        //datos.setClassIndex(0);
    } catch (IOException ex) {
        System.err.println("Problemas al intentar cargar los datos");
        return null;
    }

    RandomTree arbol = new RandomTree(); // Class for constructing a tree that considers K randomly chosen attributes at each node. 

    try {

        arbol.setNumFolds(100);
        arbol.setKValue(0);
        arbol.setMinNum(1);
        arbol.setMaxDepth(0);
        arbol.setSeed(1);
        arbol.buildClassifier(datos);

    } catch (Exception ex) {
        System.err.println("Problemas al ejecutar algorimo de clasificacion" + ex.getLocalizedMessage());
    }
    return arbol.toString();
}

From source file:controller.NaiveBayesBean.java

public void handleFileUpload(FileUploadEvent event) throws FileNotFoundException, IOException, Exception {
    System.out.println("File uploaded!");
    System.out.println(event.getFile().getContentType());
    //this.data = new Instances(new FileReader("web/resources/data/weather.nominal.arff"));

    //Daten als Instanzen aufbereiten
    //CSV Converter
    if (event.getFile().getFileName().endsWith(".csv")) {
        CSVLoader csv = new CSVLoader();

        BufferedReader br = new BufferedReader(new InputStreamReader(event.getFile().getInputstream()));
        String s;//from  w  w w .java2 s.  co  m
        StringBuilder sb = new StringBuilder();
        while ((s = br.readLine()) != null) {
            sb.append(s.replace(";", ","));
            //sb.append(s.replace("\"", ""));
            sb.append("\n");
            System.out.println(sb.toString());
        }
        csv.setSource(new ByteArrayInputStream(sb.toString().getBytes()));
        this.data = csv.getDataSet();
    } else {
        this.data = new Instances(new InputStreamReader(event.getFile().getInputstream()));
    }

    this.attributes.clear();
    //Attribute auslesen und in Bean bereitstellen
    for (int i = 0; i < this.data.numAttributes(); i++) {
        this.attributes.add(data.attribute(i));
    }
    //Meta-Daten der hochgeladenen Daten bereitstellen
    this.description = this.data.toSummaryString();
    //Klasse als letzte Spalte annehmen
    this.data.setClassIndex(this.data.numAttributes() - 1);
    this.index = this.data.classAttribute().index();

    //Daten analysieren
    this.classifier.buildClassifier(this.data);
    //Text im Interface setzen
    this.modeloutput = "Model fr Klasse " + this.data.classAttribute().name();
    this.model = this.classifier.toString();
}

From source file:controller.NaiveBayesServlet.java

@Override
protected void doPost(HttpServletRequest request, HttpServletResponse response)
        throws ServletException, IOException {
    request.setCharacterEncoding("UTF-8");
    String dir = "/data/";
    String path = getServletContext().getRealPath(dir);

    String action = request.getParameter("action");

    switch (action) {
    case "create": {
        String fileName = request.getParameter("file");

        String aux = fileName.substring(0, fileName.indexOf("."));
        String pathInput = path + "/" + request.getParameter("file");
        String pathTrainingOutput = path + "/" + aux + "-training-arff.txt";
        String pathTestOutput = path + "/" + aux + "-test-arff.txt";
        String pathNaivebayes = path + "/" + aux + "-naiveBayes.txt";

        String name = request.getParameter("name");
        int range = Integer.parseInt(request.getParameter("range"));

        int size = Integer.parseInt(request.getParameter("counter"));
        String[] columns = new String[size];
        String[] types = new String[size];
        int[] positions = new int[size];
        int counter = 0;

        for (int i = 0; i < size; i++) {
            if (request.getParameter("column-" + (i + 1)) != null) {
                columns[counter] = request.getParameter("column-" + (i + 1));
                types[counter] = request.getParameter("type-" + (i + 1));
                positions[counter] = Integer.parseInt(request.getParameter("position-" + (i + 1)));
                counter++;/*from   w  w  w.ja  va 2s.c  o  m*/
            }
        }

        FormatFiles.convertTxtToArff(pathInput, pathTrainingOutput, pathTestOutput, name, columns, types,
                positions, counter, range);

        try {
            NaiveBayes naiveBayes = new NaiveBayes();

            BufferedReader readerTraining = new BufferedReader(new FileReader(pathTrainingOutput));
            Instances instancesTraining = new Instances(readerTraining);
            instancesTraining.setClassIndex(instancesTraining.numAttributes() - 1);

            naiveBayes.buildClassifier(instancesTraining);

            BufferedReader readerTest = new BufferedReader(new FileReader(pathTestOutput));
            //BufferedReader readerTest = new BufferedReader(new FileReader(pathTrainingOutput));
            Instances instancesTest = new Instances(readerTest);
            instancesTest.setClassIndex(instancesTest.numAttributes() - 1);

            Evaluation eval = new Evaluation(instancesTraining);
            eval.evaluateModel(naiveBayes, instancesTest);

            int corrects = 0;
            int truePositive = 0;
            int trueNegative = 0;
            int falsePositive = 0;
            int falseNegative = 0;

            for (int i = 0; i < instancesTest.size(); i++) {
                Instance instance = instancesTest.get(i);
                double correctValue = instance.value(instance.attribute(instancesTest.numAttributes() - 1));
                double classification = naiveBayes.classifyInstance(instance);

                if (correctValue == classification) {
                    corrects++;
                }
                if (correctValue == 1 && classification == 1) {
                    truePositive++;
                }
                if (correctValue == 1 && classification == 0) {
                    falseNegative++;
                }
                if (correctValue == 0 && classification == 1) {
                    falsePositive++;
                }
                if (correctValue == 0 && classification == 0) {
                    trueNegative++;
                }
            }

            PrintWriter writer = new PrintWriter(new BufferedWriter(new FileWriter(pathNaivebayes, false)));

            writer.println(naiveBayes.toString());

            writer.println("");
            writer.println("");
            writer.println("Results");
            writer.println(eval.toSummaryString());

            writer.close();

            response.sendRedirect(
                    "NaiveBayes?action=view&corrects=" + corrects + "&totalTest=" + instancesTest.size()
                            + "&totalTrainig=" + instancesTraining.size() + "&range=" + range + "&truePositive="
                            + truePositive + "&trueNegative=" + trueNegative + "&falsePositive=" + falsePositive
                            + "&falseNegative=" + falseNegative + "&fileName=" + aux + "-naiveBayes.txt");

        } catch (Exception e) {
            System.out.println(e.getMessage());
            response.sendRedirect("Navigation?action=naiveBayes");
        }

        break;
    }
    default:
        response.sendError(404);
    }

}

From source file:controller.OneRBean.java

public void handleFileUpload(FileUploadEvent event) {
    FacesMessage message = new FacesMessage("Succesful", event.getFile().getFileName() + " is uploaded.");
    FacesContext.getCurrentInstance().addMessage(null, message);

    try {//from w  ww . j  av a2s . com
        if (event.getFile().getFileName().endsWith(".arff")) {
            inst = new Instances(new InputStreamReader(event.getFile().getInputstream()));
        } else {
            CSVLoader scv = new CSVLoader();
            scv.setSource(event.getFile().getInputstream());
            inst = scv.getDataSet();
        }
        columns = new ArrayList<>();
        for (int i = 0; i < inst.firstInstance().numAttributes(); i++) {
            columns.add(inst.firstInstance().attribute(i).name());
        }
        System.out.println(columns);
    } catch (IOException ex) {
        System.out.println("Fehler: " + ex);
    }
    this.description = this.inst.toSummaryString();
    this.calculate();
}

From source file:core.classifier.MyFirstClassifier.java

License:Open Source License

/**
 * Method for building the classifier. Implements a one-against-one
 * wrapper for multi-class problems./*from   w w w .  j a v  a  2  s .com*/
 *
 * @param insts the set of training instances
 * @throws Exception if the classifier can't be built successfully
 */
public void buildClassifier(Instances insts) throws Exception {

    if (!m_checksTurnedOff) {
        // can classifier handle the data?
        getCapabilities().testWithFail(insts);

        // remove instances with missing class
        insts = new Instances(insts);
        insts.deleteWithMissingClass();

        /* Removes all the instances with weight equal to 0.
         MUST be done since condition (8) of Keerthi's paper
         is made with the assertion Ci > 0 (See equation (3a). */
        Instances data = new Instances(insts, insts.numInstances());
        for (int i = 0; i < insts.numInstances(); i++) {
            if (insts.instance(i).weight() > 0)
                data.add(insts.instance(i));
        }
        if (data.numInstances() == 0) {
            throw new Exception("No training instances left after removing " + "instances with weight 0!");
        }
        insts = data;
    }

    if (!m_checksTurnedOff) {
        m_Missing = new ReplaceMissingValues();
        m_Missing.setInputFormat(insts);
        insts = Filter.useFilter(insts, m_Missing);
    } else {
        m_Missing = null;
    }

    if (getCapabilities().handles(Capability.NUMERIC_ATTRIBUTES)) {
        boolean onlyNumeric = true;
        if (!m_checksTurnedOff) {
            for (int i = 0; i < insts.numAttributes(); i++) {
                if (i != insts.classIndex()) {
                    if (!insts.attribute(i).isNumeric()) {
                        onlyNumeric = false;
                        break;
                    }
                }
            }
        }

        if (!onlyNumeric) {
            m_NominalToBinary = new NominalToBinary();
            m_NominalToBinary.setInputFormat(insts);
            insts = Filter.useFilter(insts, m_NominalToBinary);
        } else {
            m_NominalToBinary = null;
        }
    } else {
        m_NominalToBinary = null;
    }

    if (m_filterType == FILTER_STANDARDIZE) {
        m_Filter = new Standardize();
        m_Filter.setInputFormat(insts);
        insts = Filter.useFilter(insts, m_Filter);
    } else if (m_filterType == FILTER_NORMALIZE) {
        m_Filter = new Normalize();
        m_Filter.setInputFormat(insts);
        insts = Filter.useFilter(insts, m_Filter);
    } else {
        m_Filter = null;
    }

    m_classIndex = insts.classIndex();
    m_classAttribute = insts.classAttribute();
    m_KernelIsLinear = (m_kernel instanceof PolyKernel) && (((PolyKernel) m_kernel).getExponent() == 1.0);

    // Generate subsets representing each class
    Instances[] subsets = new Instances[insts.numClasses()];
    for (int i = 0; i < insts.numClasses(); i++) {
        subsets[i] = new Instances(insts, insts.numInstances());
    }
    for (int j = 0; j < insts.numInstances(); j++) {
        Instance inst = insts.instance(j);
        subsets[(int) inst.classValue()].add(inst);
    }
    for (int i = 0; i < insts.numClasses(); i++) {
        subsets[i].compactify();
    }

    // Build the binary classifiers
    Random rand = new Random(m_randomSeed);
    m_classifiers = new BinarySMO[insts.numClasses()][insts.numClasses()];
    for (int i = 0; i < insts.numClasses(); i++) {
        for (int j = i + 1; j < insts.numClasses(); j++) {
            m_classifiers[i][j] = new BinarySMO();
            m_classifiers[i][j].setKernel(Kernel.makeCopy(getKernel()));
            Instances data = new Instances(insts, insts.numInstances());
            for (int k = 0; k < subsets[i].numInstances(); k++) {
                data.add(subsets[i].instance(k));
            }
            for (int k = 0; k < subsets[j].numInstances(); k++) {
                data.add(subsets[j].instance(k));
            }
            data.compactify();
            data.randomize(rand);
            m_classifiers[i][j].buildClassifier(data, i, j, m_fitLogisticModels, m_numFolds, m_randomSeed);
        }
    }
}

From source file:core.ClusterEvaluationEX.java

License:Open Source License

/**
 * Perform a cross-validation for DensityBasedClusterer on a set of instances.
 *
 * @param clusterer the clusterer to use
 * @param data the training data//from   w ww.jav a  2s .  co  m
 * @param numFolds number of folds of cross validation to perform
 * @param random random number seed for cross-validation
 * @return the cross-validated log-likelihood
 * @throws Exception if an error occurs
 */
public static double crossValidateModel(DensityBasedClusterer clusterer, Instances data, int numFolds,
        Random random) throws Exception {
    Instances train, test;
    double foldAv = 0;
    ;
    data = new Instances(data);
    data.randomize(random);
    //    double sumOW = 0;
    for (int i = 0; i < numFolds; i++) {
        // Build and test clusterer
        train = data.trainCV(numFolds, i, random);

        clusterer.buildClusterer(train);

        test = data.testCV(numFolds, i);

        for (int j = 0; j < test.numInstances(); j++) {
            try {
                foldAv += ((DensityBasedClusterer) clusterer).logDensityForInstance(test.instance(j));
                //     sumOW += test.instance(j).weight();
                //   double temp = Utils.sum(tempDist);
            } catch (Exception ex) {
                // unclustered instances
            }
        }
    }

    //    return foldAv / sumOW;
    return foldAv / data.numInstances();
}