Example usage for weka.attributeSelection Ranker Ranker

Introduction

In this page you can find the example usage for weka.attributeSelection Ranker Ranker.

Prototype

public Ranker() 

Source Link

Document

Constructor

Usage

From source file:FeatureSelectionClass.java

public AttributeSelection withGainRatio(String path) throws Exception {
    int N;/*from   w  w w.  j a v a  2  s. c  o m*/
    PreparingSteps pr = new PreparingSteps();
    N = pr.getReadFileData(path).numAttributes();
    Instances data = pr.getReadFileData(path);

    AttributeSelection selector = new AttributeSelection();
    InfoGainAttributeEval evaluator = new InfoGainAttributeEval();
    Ranker ranker = new Ranker();
    ranker.setNumToSelect(Math.min(500, N - 1));
    selector.setEvaluator(evaluator);
    selector.setSearch(ranker);
    selector.SelectAttributes(data);
    return selector;

}

---

From source file:FeatureSelectionClass.java

public AttributeSelection withInfoGain(String path) throws Exception {
    int N;//from   w  w  w  .  ja v a  2  s .  c o m
    PreparingSteps pr = new PreparingSteps();
    N = pr.getReadFileData(path).numAttributes();
    Instances data = pr.getReadFileData(path);

    AttributeSelection selector = new AttributeSelection();
    GainRatioAttributeEval evaluator = new GainRatioAttributeEval();
    Ranker ranker = new Ranker();
    ranker.setNumToSelect(Math.min(500, N - 1));
    selector.setEvaluator(evaluator);
    selector.setSearch(ranker);
    selector.SelectAttributes(data);
    return selector;
}

---

From source file:FeatureSelectionClass.java

public AttributeSelection withChiSquare(String path) throws Exception {
    int N;//  ww  w. j a va  2  s.co m
    PreparingSteps pr = new PreparingSteps();
    N = pr.getReadFileData(path).numAttributes();
    Instances data = pr.getReadFileData(path);

    AttributeSelection selector = new AttributeSelection();
    ChiSquaredAttributeEval evaluator = new ChiSquaredAttributeEval();
    Ranker ranker = new Ranker();
    ranker.setNumToSelect(Math.min(500, N - 1));
    selector.setEvaluator(evaluator);
    selector.setSearch(ranker);
    selector.SelectAttributes(data);
    return selector;

}

---

From source file:PCADetector.java

License:Apache License

public boolean runPCA(ArrayList<Double> newData, int slidewdSz, double cAlpha, int nAttrs) {
    try {/*w w  w  .ja va 2  s  . c  o  m*/
        if (m_nDims == 0) {
            m_nDims = nAttrs;
            for (int i = 0; i < this.m_nDims; i++) {
                m_oriDataMatrix.add(new ArrayList<Double>()); // one list for each attribute
            }
        }
        verifyData(newData);
        this.c_alpha = cAlpha;
        if (false == prepareData(newData, slidewdSz))
            return false;
        Instances oriDataInsts = getInstances();
        if (oriDataInsts != null) {
            // standardization + PCA covariance matrix
            m_scaledInstances = new Instances(oriDataInsts);
            Standardize filter = new Standardize();

            filter.setInputFormat(m_scaledInstances);
            m_scaledInstances = Standardize.useFilter(m_scaledInstances, filter); // standardization

            PrincipalComponents PCA = new PrincipalComponents();
            PCA.setVarianceCovered(1.0); // means 100%
            PCA.setMaximumAttributeNames(-1);
            PCA.setCenterData(true);
            Ranker ranker = new Ranker();
            AttributeSelection selector = new AttributeSelection();
            selector.setSearch(ranker);
            selector.setEvaluator(PCA);
            selector.SelectAttributes(m_scaledInstances);
            //                Instances transformedData = selector.reduceDimensionality(m_scaledInstances);

            // get sorted eigens
            double[] eigenValues = PCA.getEigenValues();
            // eigenVectors[i][j]  i: rows; j: cols
            double[][] eigenVectors = PCA.getUnsortedEigenVectors();
            Sort(eigenValues, eigenVectors);
            setEigens(eigenValues);

            // get residual start dimension
            int residualStartDimension = -1;
            double sum = 0;
            double major = 0;
            for (int ss = 0; ss < eigenValues.length; ss++) {
                sum += eigenValues[ss];
            }
            for (int ss = 0; ss < eigenValues.length; ss++) {
                major += eigenValues[ss];
                if ((residualStartDimension < 0) && (major / sum > 0.95)) {
                    residualStartDimension = ss + 1;
                    break;
                }
            }
            //            System.out.println("residualStartDim: "+residualStartDimension);
            m_threshold = computeThreshold(eigenValues, residualStartDimension);

            // check new data abnormal or not
            boolean bAbnormal = checkSPE(eigenVectors, residualStartDimension, newData);
            computeProjPCs(eigenVectors, residualStartDimension, newData); // only for demo

            if (bAbnormal) { // anomaly, now to diagnosis
                // check original space using all the lists
                diagnosis(eigenVectors, residualStartDimension, newData);
            }

        }

    } catch (Exception exc) {
    }
    return true;
}

---

From source file:ca.uottawa.balie.WekaAttributeSelection.java

License:Open Source License

/**
 * Select the top attributes/*from   www .  j  a v a  2s.  c o m*/
 */
public void Select(boolean pi_Debug) {
    Instances insts = m_DummyLearner.GetTrainInstances();

    try {
        ASEvaluation eval = null;
        ASSearch search = null;

        if (m_Evaluator == WEKA_CHI_SQUARE) {
            eval = new ChiSquaredAttributeEval();
            search = new Ranker();
            ((Ranker) search).setNumToSelect(m_NumAttributes);
        } else if (m_Evaluator == WEKA_INFO_GAIN) {
            eval = new InfoGainAttributeEval();
            search = new Ranker();
            ((Ranker) search).setNumToSelect(m_NumAttributes);
        } else if (m_Evaluator == WEKA_WRAPPER) {
            eval = new ClassifierSubsetEval();
            ((ClassifierSubsetEval) eval).setClassifier(new NaiveBayes());
            search = new Ranker(); // TODO: use something else than ranker
            ((Ranker) search).setNumToSelect(m_NumAttributes);
        } else if (m_Evaluator == WEKA_SYM_UNCERT) {
            eval = new SymmetricalUncertAttributeEval();
            search = new Ranker();
            ((Ranker) search).setNumToSelect(m_NumAttributes);
        } else if (m_Evaluator == WEKA_SVM) {
            eval = new SVMAttributeEval();
            search = new Ranker();
            ((Ranker) search).setNumToSelect(m_NumAttributes);
        } else if (m_Evaluator == WEKA_RELIEF) {
            eval = new ReliefFAttributeEval();
            search = new Ranker();
            ((Ranker) search).setNumToSelect(m_NumAttributes);
        } else if (m_Evaluator == WEKA_ONER) {
            eval = new OneRAttributeEval();
            search = new Ranker();
            ((Ranker) search).setNumToSelect(m_NumAttributes);
        }

        m_AttributeSelection = new AttributeSelection();
        m_AttributeSelection.setEvaluator(eval);
        m_AttributeSelection.setSearch(search);

        m_AttributeSelection.SelectAttributes(insts);
        if (pi_Debug)
            System.out.println(m_AttributeSelection.toResultsString());

    } catch (Exception e) {
        System.err.println(e.getMessage());
    }

}

---

From source file:com.ivanrf.smsspam.SpamClassifier.java

License:Apache License

private static FilteredClassifier initFilterClassifier(int wordsToKeep, String tokenizerOp,
        boolean useAttributeSelection, String classifierOp, boolean boosting) throws Exception {
    StringToWordVector filter = new StringToWordVector();
    filter.setDoNotOperateOnPerClassBasis(true);
    filter.setLowerCaseTokens(true);//from  ww w.  ja  v a 2 s .  com
    filter.setWordsToKeep(wordsToKeep);

    if (!tokenizerOp.equals(TOKENIZER_DEFAULT)) {
        //Make a tokenizer
        WordTokenizer wt = new WordTokenizer();
        if (tokenizerOp.equals(TOKENIZER_COMPLETE))
            wt.setDelimiters(" \r\n\t.,;:\'\"()?!-+*&#$%/=<>[]_`@\\^{}");
        else //TOKENIZER_COMPLETE_NUMBERS)
            wt.setDelimiters(" \r\n\t.,;:\'\"()?!-+*&#$%/=<>[]_`@\\^{}|~0123456789");
        filter.setTokenizer(wt);
    }

    FilteredClassifier classifier = new FilteredClassifier();
    classifier.setFilter(filter);

    if (useAttributeSelection) {
        AttributeSelection as = new AttributeSelection();
        as.setEvaluator(new InfoGainAttributeEval());
        Ranker r = new Ranker();
        r.setThreshold(0);
        as.setSearch(r);

        MultiFilter mf = new MultiFilter();
        mf.setFilters(new Filter[] { filter, as });

        classifier.setFilter(mf);
    }

    if (classifierOp.equals(CLASSIFIER_SMO))
        classifier.setClassifier(new SMO());
    else if (classifierOp.equals(CLASSIFIER_NB))
        classifier.setClassifier(new NaiveBayes());
    else if (classifierOp.equals(CLASSIFIER_IB1))
        classifier.setClassifier(new IBk(1));
    else if (classifierOp.equals(CLASSIFIER_IB3))
        classifier.setClassifier(new IBk(3));
    else if (classifierOp.equals(CLASSIFIER_IB5))
        classifier.setClassifier(new IBk(5));
    else if (classifierOp.equals(CLASSIFIER_PART))
        classifier.setClassifier(new PART()); //Tarda mucho

    if (boosting) {
        AdaBoostM1 boost = new AdaBoostM1();
        boost.setClassifier(classifier.getClassifier());
        classifier.setClassifier(boost); //Con NB tarda mucho
    }

    return classifier;
}

---

From source file:es.uvigo.ei.sing.gc.model.entities.GeneSelectionMetaData.java

License:Open Source License

public FeatureSelector createFeatureSelection() throws Exception {
    final Ranker ranker = new Ranker();
    ranker.setNumToSelect(this.numGenes);

    return new WekaFeatureSelector(this.getASEvaluationBuilder().buildEvaluator(), ranker);
}

---

From source file:etc.aloe.oilspill2010.FeatureGenerationImpl.java

License:Open Source License

protected Filter getFeatureSelectionFilter(ExampleSet examples) throws Exception {

    AttributeSelection filter = new AttributeSelection(); // package weka.filters.supervised.attribute!
    //CfsSubsetEval eval = new CfsSubsetEval();

    //CorrelationAttributeEval eval = new CorrelationAttributeEval();
    //InfoGainAttributeEval eval = new InfoGainAttributeEval();

    ReliefFAttributeEval eval = new ReliefFAttributeEval();

    //GreedyStepwise search = new GreedyStepwise();
    //search.setNumToSelect(980);
    //search.setSearchBackwards(true);

    Ranker search = new Ranker();
    search.setNumToSelect(980);//from w w  w  . ja  va  2s.  c  o m

    filter.setEvaluator(eval);
    filter.setSearch(search);

    filter.setInputFormat(examples.getInstances());
    Instances filtered = Filter.useFilter(examples.getInstances(), filter);
    examples.setInstances(filtered);

    return filter;
}

---

From source file:Helper.CustomFilter.java

public Instances removeAttribute(Instances structure) throws Exception {
    //NORMALIZE AND REMOVE USELESS ATTRIBUTES
    Normalize norm = new Normalize();
    norm.setInputFormat(structure);/*from w  ww. j  a v  a2s  .c om*/
    structure = Filter.useFilter(structure, norm);

    RemoveUseless ru = new RemoveUseless();
    ru.setInputFormat(structure);
    structure = Filter.useFilter(structure, ru);

    Ranker rank = new Ranker();
    InfoGainAttributeEval eval = new InfoGainAttributeEval();
    eval.buildEvaluator(structure);
    //END OF NORMALIZATION

    return structure;
}

---

From source file:ia02classificacao.IA02Classificacao.java

/**
 * @param args the command line arguments
 *//*w  w  w .  ja  va2  s  .co  m*/
public static void main(String[] args) throws Exception {

    // abre o banco de dados arff e mostra a quantidade de instancias (linhas)
    DataSource arquivo = new DataSource("data/zoo.arff");
    Instances dados = arquivo.getDataSet();
    System.out.println("Instancias lidas: " + dados.numInstances());

    // FILTER: remove o atributo nome do animal da classificao
    String[] parametros = new String[] { "-R", "1" };
    Remove filtro = new Remove();
    filtro.setOptions(parametros);
    filtro.setInputFormat(dados);
    dados = Filter.useFilter(dados, filtro);

    AttributeSelection selAtributo = new AttributeSelection();
    InfoGainAttributeEval avaliador = new InfoGainAttributeEval();
    Ranker busca = new Ranker();
    selAtributo.setEvaluator(avaliador);
    selAtributo.setSearch(busca);
    selAtributo.SelectAttributes(dados);
    int[] indices = selAtributo.selectedAttributes();
    System.out.println("Selected attributes: " + Utils.arrayToString(indices));

    // Usa o algoritimo J48 e mostra a classificao dos dados em forma textual
    String[] opcoes = new String[1];
    opcoes[0] = "-U";
    J48 arvore = new J48();
    arvore.setOptions(opcoes);
    arvore.buildClassifier(dados);
    System.out.println(arvore);

    // Usa o algoritimo J48 e mostra a classificao de dados em forma grafica
    /*
    TreeVisualizer tv = new TreeVisualizer(null, arvore.graph(), new PlaceNode2());
    JFrame frame = new javax.swing.JFrame("?rvore de Conhecimento");
    frame.setSize(800,500);
    frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
    frame.getContentPane().add(tv);
    frame.setVisible(true);
    tv.fitToScreen();
    */

    /*
    * Classificao de novos dados
    */

    System.out.println("\n\nCLASSIFICAO DE NOVOS DADOS");
    // criar atributos
    double[] vals = new double[dados.numAttributes()];
    vals[0] = 1.0; // hair
    vals[1] = 0.0; // feathers
    vals[2] = 0.0; // eggs
    vals[3] = 1.0; // milk
    vals[4] = 1.0; // airborne
    vals[5] = 0.0; // aquatic
    vals[6] = 0.0; // predator
    vals[7] = 1.0; // toothed
    vals[8] = 1.0; // backbone
    vals[9] = 1.0; // breathes
    vals[10] = 0.0; // venomous
    vals[11] = 0.0; // fins
    vals[12] = 4.0; // legs
    vals[13] = 1.0; // tail
    vals[14] = 1.0; // domestic
    vals[15] = 1.0; // catsize

    // Criar uma instncia baseada nestes atributos
    Instance meuUnicornio = new DenseInstance(1.0, vals);

    // Adicionar a instncia nos dados
    meuUnicornio.setDataset(dados);

    // Classificar esta nova instncia
    double label = arvore.classifyInstance(meuUnicornio);

    // Imprimir o resultado da classificao
    System.out.println("Novo Animal: Unicrnio");
    System.out.println("classificacao: " + dados.classAttribute().value((int) label));

    /*
    * Avaliao e predio de erros de mtrica
    */
    System.out.println("\n\nAVALIAO E PREDIO DE ERROS DE MTRICA");
    Classifier cl = new J48();
    Evaluation eval_roc = new Evaluation(dados);
    eval_roc.crossValidateModel(cl, dados, 10, new Random(1), new Object[] {});
    System.out.println(eval_roc.toSummaryString());

    /*
    * Matriz de confuso
    */
    System.out.println("\n\nMATRIZ DE CONFUSO");
    double[][] confusionMatrix = eval_roc.confusionMatrix();
    System.out.println(eval_roc.toMatrixString());

}

---

• «
• 1
• 2
• 3
• »