Example usage for weka.core Instance toString

List of usage examples for weka.core Instance toString

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

Introduction

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

Prototype

public String toString(Attribute att);

Source Link

Document

Returns the description of one value of the instance as a string.

Usage

From source file:bme.mace.logicdomain.Evaluation.java

License:Open Source License

/**
 * store the prediction made by the classifier as a string
 * /*from   www.j  av a  2 s. c  o m*/
 * @param classifier the classifier to use
 * @param inst the instance to generate text from
 * @param instNum the index in the dataset
 * @param attributesToOutput the indices of the attributes to output
 * @param printDistribution prints the complete distribution for nominal
 *          classes, not just the predicted value
 * @return the prediction as a String
 * @throws Exception if something goes wrong
 * @see #printClassifications(Classifier, Instances, String, int, Range,
 *      boolean)
 */
protected static String predictionText(Classifier classifier, Instance inst, int instNum,
        Range attributesToOutput, boolean printDistribution)

        throws Exception {

    StringBuffer result = new StringBuffer();
    int width = 10;
    int prec = 3;

    Instance withMissing = (Instance) inst.copy();
    withMissing.setDataset(inst.dataset());
    withMissing.setMissing(withMissing.classIndex());
    double predValue = classifier.classifyInstance(withMissing);

    // index
    result.append(Utils.padLeft("" + (instNum + 1), 6));

    if (inst.dataset().classAttribute().isNumeric()) {
        // actual
        if (inst.classIsMissing()) {
            result.append(" " + Utils.padLeft("?", width));
        } else {
            result.append(" " + Utils.doubleToString(inst.classValue(), width, prec));
        }
        // predicted
        if (Instance.isMissingValue(predValue)) {
            result.append(" " + Utils.padLeft("?", width));
        } else {
            result.append(" " + Utils.doubleToString(predValue, width, prec));
        }
        // error
        if (Instance.isMissingValue(predValue) || inst.classIsMissing()) {
            result.append(" " + Utils.padLeft("?", width));
        } else {
            result.append(" " + Utils.doubleToString(predValue - inst.classValue(), width, prec));
        }
    } else {
        // actual
        result.append(" "
                + Utils.padLeft(((int) inst.classValue() + 1) + ":" + inst.toString(inst.classIndex()), width));
        // predicted
        if (Instance.isMissingValue(predValue)) {
            result.append(" " + Utils.padLeft("?", width));
        } else {
            result.append(" " + Utils.padLeft(
                    ((int) predValue + 1) + ":" + inst.dataset().classAttribute().value((int) predValue),
                    width));
        }
        // error?
        if (!Instance.isMissingValue(predValue) && !inst.classIsMissing()
                && ((int) predValue + 1 != (int) inst.classValue() + 1)) {
            result.append(" " + "  +  ");
        } else {
            result.append(" " + "     ");
        }
        // prediction/distribution
        if (printDistribution) {
            if (Instance.isMissingValue(predValue)) {
                result.append(" " + "?");
            } else {
                result.append(" ");
                double[] dist = classifier.distributionForInstance(withMissing);
                for (int n = 0; n < dist.length; n++) {
                    if (n > 0) {
                        result.append(",");
                    }
                    if (n == (int) predValue) {
                        result.append("*");
                    }
                    result.append(Utils.doubleToString(dist[n], prec));
                }
            }
        } else {
            if (Instance.isMissingValue(predValue)) {
                result.append(" " + "?");
            } else {
                result.append(" " + Utils.doubleToString(
                        classifier.distributionForInstance(withMissing)[(int) predValue], prec));
            }
        }
    }

    // attributes
    result.append(" " + attributeValuesString(withMissing, attributesToOutput) + "\n");

    return result.toString();
}

From source file:bme.mace.logicdomain.Evaluation.java

License:Open Source License

/**
 * Builds a string listing the attribute values in a specified range of
 * indices, separated by commas and enclosed in brackets.
 * //  w  w w .j a va 2  s.c  o m
 * @param instance the instance to print the values from
 * @param attRange the range of the attributes to list
 * @return a string listing values of the attributes in the range
 */
protected static String attributeValuesString(Instance instance, Range attRange) {
    StringBuffer text = new StringBuffer();
    if (attRange != null) {
        boolean firstOutput = true;
        attRange.setUpper(instance.numAttributes() - 1);
        for (int i = 0; i < instance.numAttributes(); i++) {
            if (attRange.isInRange(i) && i != instance.classIndex()) {
                if (firstOutput) {
                    text.append("(");
                } else {
                    text.append(",");
                }
                text.append(instance.toString(i));
                firstOutput = false;
            }
        }
        if (!firstOutput) {
            text.append(")");
        }
    }
    return text.toString();
}

From source file:com.hack23.cia.service.impl.action.user.wordcount.WordCounterImpl.java

License:Apache License

@Override
public Map<String, Integer> calculateWordCount(final DocumentContentData documentContentData,
        final int maxResult) {

    final String html = documentContentData.getContent();

    final Attribute input = new Attribute("html", (ArrayList<String>) null);

    final ArrayList<Attribute> inputVec = new ArrayList<>();
    inputVec.add(input);//  w  w  w.j  a v a2  s  . c  o m

    final Instances htmlInst = new Instances("html", inputVec, 1);

    htmlInst.add(new DenseInstance(1));
    htmlInst.instance(0).setValue(0, html);

    final StopwordsHandler StopwordsHandler = new StopwordsHandler() {

        @Override
        public boolean isStopword(final String word) {

            return word.length() < 5;
        }
    };

    final NGramTokenizer tokenizer = new NGramTokenizer();
    tokenizer.setNGramMinSize(1);
    tokenizer.setNGramMaxSize(1);
    tokenizer.setDelimiters(" \r\n\t.,;:'\"()?!'");

    final StringToWordVector filter = new StringToWordVector();
    filter.setTokenizer(tokenizer);
    filter.setStopwordsHandler(StopwordsHandler);
    filter.setLowerCaseTokens(true);
    filter.setOutputWordCounts(true);
    filter.setWordsToKeep(maxResult);

    final Map<String, Integer> result = new HashMap<>();

    try {
        filter.setInputFormat(htmlInst);
        final Instances dataFiltered = Filter.useFilter(htmlInst, filter);

        final Instance last = dataFiltered.lastInstance();

        final int numAttributes = last.numAttributes();

        for (int i = 0; i < numAttributes; i++) {
            result.put(last.attribute(i).name(), Integer.valueOf(last.toString(i)));
        }
    } catch (final Exception e) {
        LOGGER.warn("Problem calculating wordcount for : {} , exception:{}", documentContentData.getId(), e);
    }

    return result;
}

From source file:core.ClusterEvaluationEX.java

License:Open Source License

/**
 * Builds a string listing the attribute values in a specified range of indices,
 * separated by commas and enclosed in brackets.
 *
 * @param instance the instance to print the values from
 * @param attRange the range of the attributes to list
 * @return a string listing values of the attributes in the range
 *//*ww  w  .j a v  a  2 s  .  com*/
private static String attributeValuesString(Instance instance, Range attRange) {
    StringBuffer text = new StringBuffer();
    if (attRange != null) {
        boolean firstOutput = true;
        attRange.setUpper(instance.numAttributes() - 1);
        for (int i = 0; i < instance.numAttributes(); i++)
            if (attRange.isInRange(i)) {
                if (firstOutput)
                    text.append("(");
                else
                    text.append(",");
                text.append(instance.toString(i));
                firstOutput = false;
            }
        if (!firstOutput)
            text.append(")");
    }
    return text.toString();
}

From source file:cotraining.copy.Evaluation_D.java

License:Open Source License

/**
 * store the prediction made by the classifier as a string
 * //from www .j a  va  2 s. co  m
 * @param classifier      the classifier to use
 * @param inst      the instance to generate text from
 * @param instNum      the index in the dataset
 * @param attributesToOutput   the indices of the attributes to output
 * @param printDistribution   prints the complete distribution for nominal 
 *             classes, not just the predicted value
 * @return                    the prediction as a String
 * @throws Exception      if something goes wrong
 * @see         #printClassifications(Classifier, Instances, String, int, Range, boolean)
 */
protected static String predictionText(Classifier classifier, Instance inst, int instNum,
        Range attributesToOutput, boolean printDistribution)

        throws Exception {

    StringBuffer result = new StringBuffer();
    int width = 10;
    int prec = 3;

    Instance withMissing = (Instance) inst.copy();
    withMissing.setDataset(inst.dataset());
    withMissing.setMissing(withMissing.classIndex());
    double predValue = classifier.classifyInstance(withMissing);

    // index
    result.append(Utils.padLeft("" + (instNum + 1), 6));

    if (inst.dataset().classAttribute().isNumeric()) {
        // actual
        if (inst.classIsMissing())
            result.append(" " + Utils.padLeft("?", width));
        else
            result.append(" " + Utils.doubleToString(inst.classValue(), width, prec));
        // predicted
        if (Instance.isMissingValue(predValue))
            result.append(" " + Utils.padLeft("?", width));
        else
            result.append(" " + Utils.doubleToString(predValue, width, prec));
        // error
        if (Instance.isMissingValue(predValue) || inst.classIsMissing())
            result.append(" " + Utils.padLeft("?", width));
        else
            result.append(" " + Utils.doubleToString(predValue - inst.classValue(), width, prec));
    } else {
        // actual
        result.append(" "
                + Utils.padLeft(((int) inst.classValue() + 1) + ":" + inst.toString(inst.classIndex()), width));
        // predicted
        if (Instance.isMissingValue(predValue))
            result.append(" " + Utils.padLeft("?", width));
        else
            result.append(" " + Utils.padLeft(
                    ((int) predValue + 1) + ":" + inst.dataset().classAttribute().value((int) predValue),
                    width));
        // error?
        if (!Instance.isMissingValue(predValue) && !inst.classIsMissing()
                && ((int) predValue + 1 != (int) inst.classValue() + 1))
            result.append(" " + "  +  ");
        else
            result.append(" " + "     ");
        // prediction/distribution
        if (printDistribution) {
            if (Instance.isMissingValue(predValue)) {
                result.append(" " + "?");
            } else {
                result.append(" ");
                double[] dist = classifier.distributionForInstance(withMissing);
                for (int n = 0; n < dist.length; n++) {
                    if (n > 0)
                        result.append(",");
                    if (n == (int) predValue)
                        result.append("*");
                    result.append(Utils.doubleToString(dist[n], prec));
                }
            }
        } else {
            if (Instance.isMissingValue(predValue))
                result.append(" " + "?");
            else
                result.append(" " + Utils.doubleToString(
                        classifier.distributionForInstance(withMissing)[(int) predValue], prec));
        }
    }

    // attributes
    result.append(" " + attributeValuesString(withMissing, attributesToOutput) + "\n");

    return result.toString();
}

From source file:cotraining.copy.Evaluation_D.java

License:Open Source License

/**
 * Builds a string listing the attribute values in a specified range of indices,
 * separated by commas and enclosed in brackets.
 *
 * @param instance the instance to print the values from
 * @param attRange the range of the attributes to list
 * @return a string listing values of the attributes in the range
 *///from  w  w w.  j a  va  2 s.  com
protected static String attributeValuesString(Instance instance, Range attRange) {
    StringBuffer text = new StringBuffer();
    if (attRange != null) {
        boolean firstOutput = true;
        attRange.setUpper(instance.numAttributes() - 1);
        for (int i = 0; i < instance.numAttributes(); i++)
            if (attRange.isInRange(i) && i != instance.classIndex()) {
                if (firstOutput)
                    text.append("(");
                else
                    text.append(",");
                text.append(instance.toString(i));
                firstOutput = false;
            }
        if (!firstOutput)
            text.append(")");
    }
    return text.toString();
}

From source file:couchdb.CouchDBService.java

/**
 * Metoda do zapisywania danych do bazy.
 *
 * @param fileName nazwa pliku z danymi, akceptowalny format to pliki ARFF
 * @param dataBaseName nazwa bazy danych
 *//* w ww. ja va  2 s.  c o  m*/
public void importData(String fileName, String dataBaseName) {
    WekaService ws = new WekaService(fileName);
    ArrayList<String> listOfAttributesNames = ws.getAttributesName();
    ArrayList<Instance> listOfInstances = ws.getInstances();
    Database db = session.getDatabase(dataBaseName);
    for (int i = 0; i < listOfInstances.size(); i++) {
        Instance instance = listOfInstances.get(i);
        Document doc = new Document();
        doc.setId(String.valueOf(i));
        for (int j = 0; j < instance.numAttributes(); j++) {
            doc.put(listOfAttributesNames.get(j), instance.toString(j));
        }
        db.saveDocument(doc);
    }

}

From source file:dataMining.KMeans.java

/**
 * Metoda do sprawdzania czy instancje podane jako parametr s takie same.
 *
 * @param insA piewrsza instanca/*from   w  ww  .  j  a v a 2  s .  c  om*/
 * @param insB druga instancja
 * @return True, jeli s takie same, false w przeciwnym wypadku.
 */
private boolean equals(Instance insA, Instance insB) {
    if (insA.numAttributes() != insB.numAttributes()) {
        throw new NullPointerException("Rna liczba atrybutw");
    } else {
        int countTheSame = 0;
        for (int i = 0; i < insA.numAttributes(); i++) {
            double a = 0;
            double b = 0;
            try {
                a = Double.parseDouble(insA.toString(i));
            } catch (NumberFormatException ex) {
                a = 0;
            }
            try {
                b = Double.parseDouble(insB.toString(i));
            } catch (NumberFormatException ex) {
                b = 0;
            }
            if (Math.abs(a - b) == 0) {
                countTheSame++;
            }

        }
        int countAttr = insB.numAttributes();

        if (countTheSame == countAttr) {
            return true;
        } else {
            return false;
        }

    }

}

From source file:dataMining.KMeans.java

/**
 * Metoda do wyznaczania nowych rodkw grup.
 *
 * @return lista zawierajca nowe rodki.// ww w.j a v a2 s. co  m
 */
private ArrayList<Instance> makeNewMeans() {
    ArrayList<Instance> listOfMeans = new ArrayList<>();
    for (Instance i : groups.keySet()) {
        ArrayList<Instance> list = groups.get(i);
        double[] tab = new double[i.numAttributes()];
        for (Instance in : list) {
            for (int j = 0; j < tab.length; j++) {
                double d = 0;
                try {
                    d = Double.parseDouble(in.toString(j));
                } catch (NumberFormatException ex) {
                    d = 0;
                }
                tab[j] = tab[j] + d;
            }
        }
        for (int j = 0; j < tab.length; j++) {
            tab[j] = tab[j] / list.size();
        }
        Instance ins = new Instance(tab.length);
        for (int j = 0; j < tab.length; j++) {
            ins.setValue(j, tab[j]);
        }
        listOfMeans.add(ins);
    }
    return listOfMeans;
}

From source file:dataMining.KMeans.java

/**
 * Metoda do wyznaczania odlegoci pomiedzy obiektami podanymi jako
 * parametr. Odlego liczona metryk Euklidesow.
 *
 * @param a pierwszy obiekt/*from   w  w w . j  a  v a 2 s.  c om*/
 * @param b drugi obiekt
 * @return Odlego pomidzy obiektami.
 */
private double euclid(Instance a, Instance b) {
    float sum = 0;
    float attrA = 0;
    float attrB = 0;
    for (int i = 0; i < a.numAttributes(); i++) {
        try {
            attrA = Float.parseFloat(a.toString(i));
        } catch (NumberFormatException ex) {
            attrA = 0;
        }
        try {
            attrB = Float.parseFloat(b.toString(i));
        } catch (NumberFormatException ex) {
            attrB = 0;
        }

        float d = attrA - attrB;
        sum = sum + d * d;
    }
    return Math.sqrt(sum);
}