Example usage for weka.attributeSelection SignificanceAttributeEval SignificanceAttributeEval

List of usage examples for weka.attributeSelection SignificanceAttributeEval SignificanceAttributeEval

Introduction

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

Prototype

public SignificanceAttributeEval() 

Source Link

Document

Constructor

Usage

From source file:org.uclab.mm.kcl.ddkat.dataselector.FeatureEvaluator.java

License:Apache License

/**
 * Constructor to instantiate a new FeatureEvaluator object.
 *
 * @param json the data string/*from   w  ww .  ja  v  a 2 s .  c o m*/
 * @param data the data set
 * @throws Exception the exception
 */

public FeatureEvaluator(String json, Instances data) throws Exception {
    //   public FeatureEvaluator(String json, Instances data, String filePath) throws Exception {

    this.featureTitles = new ArrayList<String>();
    this.featureScores = new ArrayList<Double>();
    this.featureWeights = new ArrayList<Double>();
    this.featurePriorities = new ArrayList<Double>();

    OrderedJSONObject jsonObject = new OrderedJSONObject(json.toString());
    JSONArray jsontokenArray = jsonObject.getJSONArray("unprocessed_data");
    String csvString = "";
    String str;
    for (int i = 0; i < jsontokenArray.length(); i++) {
        str = jsontokenArray.get(i).toString();
        str = str.substring(1, str.length() - 1);
        csvString += str + "\n";
    }

    String filePath = BASE_DIR + "FeaturesEvaluationDataSet.csv";
    File file = new File(filePath);
    // if file does not exists, then create it
    if (!file.exists())
        file.createNewFile();

    FileUtils.writeStringToFile(file, csvString);

    CSVLoader loader = new CSVLoader();
    loader.setSource(new File(filePath));
    data = loader.getDataSet();

    if (data.classIndex() == -1)
        data.setClassIndex(data.numAttributes() - 1);

    int numUnlabeledAttributes = data.numAttributes() - 1;
    double[] minmaxValues = new double[2];
    double min, max;

    String[] options = new String[1];
    options[0] = "-T -1.7976931348623157E308 -N -1"; // confidenceFactor = 0.25, minNumObject = 2
    Ranker atrank = new Ranker();
    atrank.setOptions(options);

    weka.attributeSelection.AttributeSelection atsel = new weka.attributeSelection.AttributeSelection();

    //  Information Gain Attribute Evaluator
    InfoGainAttributeEval infoGainAttrEval = new InfoGainAttributeEval();
    atsel.setEvaluator(infoGainAttrEval);
    atsel.setSearch(atrank);
    atsel.SelectAttributes(data);
    double[] infoGainRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        infoGainRanks[i] = Math.round(10000 * infoGainAttrEval.evaluateAttribute(i)) / 10000d;
    }
    minmaxValues = computerMinMaxValues(infoGainRanks);
    min = minmaxValues[0];
    max = minmaxValues[1];
    double[] scaledInfoGainRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        scaledInfoGainRanks[i] = Math.round(10000 * ((infoGainRanks[i] - min) / (max - min))) / 10000d;
    }

    //  Gain Ratio Attribute Evaluator
    GainRatioAttributeEval gainRatioAttrEval = new GainRatioAttributeEval();
    atsel.setEvaluator(gainRatioAttrEval);
    atsel.setSearch(atrank);
    atsel.SelectAttributes(data);
    double[] gainRatioRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        gainRatioRanks[i] = Math.round(10000 * gainRatioAttrEval.evaluateAttribute(i)) / 10000d;
    }
    minmaxValues = computerMinMaxValues(gainRatioRanks);
    min = minmaxValues[0];
    max = minmaxValues[1];
    double[] scaledGainRatioRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        scaledGainRatioRanks[i] = Math.round(10000 * ((gainRatioRanks[i] - min) / (max - min))) / 10000d;
    }

    //  Chi Squared Attribute Evaluator
    ChiSquaredAttributeEval chiSquaredAttrEval = new ChiSquaredAttributeEval();
    atsel.setEvaluator(chiSquaredAttrEval);
    atsel.setSearch(atrank);
    atsel.SelectAttributes(data);
    double[] chiSquaredRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        chiSquaredRanks[i] = Math.round(10000 * chiSquaredAttrEval.evaluateAttribute(i)) / 10000d;
    }
    minmaxValues = computerMinMaxValues(chiSquaredRanks);
    min = minmaxValues[0];
    max = minmaxValues[1];
    double[] scaledChiSquaredRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        scaledChiSquaredRanks[i] = Math.round(10000 * ((chiSquaredRanks[i] - min) / (max - min))) / 10000d;
    }

    //  Symmetrical Uncert Attribute Evaluator
    SymmetricalUncertAttributeEval symmetricalUncertAttrEval = new SymmetricalUncertAttributeEval();
    atsel.setEvaluator(symmetricalUncertAttrEval);
    atsel.setSearch(atrank);
    atsel.SelectAttributes(data);
    double[] symmetricalUncertRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        symmetricalUncertRanks[i] = Math.round(10000 * symmetricalUncertAttrEval.evaluateAttribute(i)) / 10000d;
    }
    minmaxValues = computerMinMaxValues(symmetricalUncertRanks);
    min = minmaxValues[0];
    max = minmaxValues[1];
    double[] scaledSymmetricalUncertRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        scaledSymmetricalUncertRanks[i] = Math.round(10000 * ((symmetricalUncertRanks[i] - min) / (max - min)))
                / 10000d;
    }

    //  Significance Attribute Evaluator
    SignificanceAttributeEval significanceAttrEval = new SignificanceAttributeEval();
    atsel.setEvaluator(significanceAttrEval);
    atsel.setSearch(atrank);
    atsel.SelectAttributes(data);
    double[] significanceRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        significanceRanks[i] = Math.round(10000 * significanceAttrEval.evaluateAttribute(i)) / 10000d;
    }
    minmaxValues = computerMinMaxValues(significanceRanks);
    min = minmaxValues[0];
    max = minmaxValues[1];
    double[] scaledSignificanceRanks = new double[numUnlabeledAttributes];
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        scaledSignificanceRanks[i] = Math.round(10000 * ((significanceRanks[i] - min) / (max - min))) / 10000d;
    }

    double attributeSum;

    double[] combinedRanks = new double[numUnlabeledAttributes];
    double combinedranksSum = 0;

    for (int i = 0; i < numUnlabeledAttributes; i++) {
        attributeSum = scaledInfoGainRanks[i] + scaledGainRatioRanks[i] + scaledChiSquaredRanks[i]
                + scaledSymmetricalUncertRanks[i] + scaledSignificanceRanks[i];
        combinedRanks[i] = Math.round(10000 * attributeSum) / 10000d;
        combinedranksSum = combinedranksSum + combinedRanks[i];
    }

    double[][] tempArray = new double[numUnlabeledAttributes][2];
    String[] attributesTitles = new String[numUnlabeledAttributes];
    double[] attributesScores = new double[numUnlabeledAttributes];
    double[] attributesWeights = new double[numUnlabeledAttributes];
    double[] attributesPriorities = new double[numUnlabeledAttributes];

    for (int j = 0; j < numUnlabeledAttributes; j++) {
        tempArray[j][0] = j;
        tempArray[j][1] = combinedRanks[j];
    }

    double temp;
    for (int i = 0; i < numUnlabeledAttributes; i++) {
        for (int j = 1; j < (numUnlabeledAttributes - i); j++) {
            if (combinedRanks[j - 1] < combinedRanks[j]) {
                //swap the elements!
                temp = combinedRanks[j - 1];
                combinedRanks[j - 1] = combinedRanks[j];
                combinedRanks[j] = temp;
            }
        }
    }

    for (int j = 0; j < numUnlabeledAttributes; j++) {
        for (int k = 0; k < numUnlabeledAttributes; k++) {
            if (combinedRanks[j] == tempArray[k][1]) {
                attributesTitles[j] = data.attribute((int) tempArray[k][0]).toString();
                String res[] = attributesTitles[j].split("\\s+");
                attributesTitles[j] = res[1];

                this.featureTitles.add(attributesTitles[j]);
                break;
            }
        }
        attributesScores[j] = Math.round(10000 * (combinedRanks[j] / 9)) / 100d;
        attributesWeights[j] = Math.round(10000 * (combinedRanks[j] / combinedranksSum)) / 100d;
        attributesPriorities[j] = Math.round(attributesScores[j] * attributesWeights[j]) / 100d;
        this.featureScores.add(attributesScores[j]);
        this.featureWeights.add(attributesWeights[j]);
        this.featurePriorities.add(attributesPriorities[j]);

        System.out.println(attributesTitles[j] + " is " + attributesScores[j] + " % Important");
    }

}