Example usage for weka.core Attribute enumerateValues

Introduction

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

Prototype

public finalEnumeration<Object> enumerateValues() 

Source Link

Document

Returns an enumeration of all the attribute's values if the attribute is nominal, string, or relation-valued, null otherwise.

Usage

From source file:cezeri.utils.FactoryInstance.java

public static String[] getOriginalClasses(Instances data) {
    Attribute att = data.attribute(data.classIndex());
    String[] ret = new String[data.numClasses()];
    Enumeration enu = att.enumerateValues();
    int q = 0;/*from  ww  w. jav  a 2s  . c  o  m*/
    while (enu.hasMoreElements()) {
        ret[q++] = (String) enu.nextElement();
    }
    return ret;
}

---

From source file:com.yahoo.labs.samoa.instances.WekaToSamoaInstanceConverter.java

License:Apache License

/**
* Get Samoa attribute from a weka attribute.
*
* @param index the index/*from w  ww. j a v a2  s. co  m*/
* @param attribute the attribute
* @return the attribute
*/
protected Attribute samoaAttribute(int index, weka.core.Attribute attribute) {
    Attribute samoaAttribute;
    if (attribute.isNominal()) {
        Enumeration enu = attribute.enumerateValues();
        List<String> attributeValues = new ArrayList<String>();
        while (enu.hasMoreElements()) {
            attributeValues.add((String) enu.nextElement());
        }
        samoaAttribute = new Attribute(attribute.name(), attributeValues);
    } else {
        samoaAttribute = new Attribute(attribute.name());
    }
    return samoaAttribute;
}

---

From source file:de.ugoe.cs.cpdp.dataprocessing.NominalAttributeFilter.java

License:Apache License

@Override
public void apply(Instances testdata, Instances traindata) {
    int indexOfConfidenceAttribute = -1;

    // Find index of the named confidence attribute to filter for
    for (int i = 0; i < traindata.numAttributes(); i++) {
        if (traindata.attribute(i).name().equals(nominalAttributeName)) {
            indexOfConfidenceAttribute = i;
        }/*  w  ww.j  ava  2  s . c  o m*/
    }

    // if it was not found return
    if (indexOfConfidenceAttribute == -1) {
        return;
    }

    // Find index of nominal values
    Attribute confidenceAttribute = traindata.attribute(indexOfConfidenceAttribute);
    ArrayList<Object> nominalValuesOfConfidenceAttribute = Collections
            .list(confidenceAttribute.enumerateValues());
    ArrayList<Double> indexOfnominalAttributeValues = new ArrayList<Double>();

    for (int k = 0; k < nominalValuesOfConfidenceAttribute.size(); k++) {
        for (String attributeValue : nominalAttributeValues) {
            if (((String) nominalValuesOfConfidenceAttribute.get(k)).equals(attributeValue)) {
                indexOfnominalAttributeValues.add((double) k);
            }
        }
    }

    // Go through all instances and check if nominal attribute equals
    for (int j = traindata.numInstances() - 1; j >= 0; j--) {
        Instance wekaInstance = traindata.get(j);

        // delete all instances where nominal attribute has the value of one of the parameter
        if (indexOfnominalAttributeValues.contains(wekaInstance.value(indexOfConfidenceAttribute))) {
            traindata.delete(j);
        }
    }
}

---

From source file:edu.illinois.cs.cogcomp.lbjava.learn.WekaWrapper.java

License:Open Source License

/**
 * Produces a set of scores indicating the degree to which each possible discrete classification
 * value is associated with the given example object.
 **///from  w w  w  . java  2  s  .co m
public ScoreSet scores(int[] exampleFeatures, double[] exampleValues) {
    double[] dist = getDistribution(exampleFeatures, exampleValues);

    /*
     * Assuming that the first Attribute in our attributeInfo vector is the class attribute,
     * decide which case we are in
     */
    Attribute classAtt = (Attribute) attributeInfo.elementAt(0);

    ScoreSet scores = new ScoreSet();

    if (classAtt.isNominal() || classAtt.isString()) {
        Enumeration enumeratedValues = classAtt.enumerateValues();

        int i = 0;
        while (enumeratedValues.hasMoreElements()) {
            if (i >= dist.length) {
                System.err.println(
                        "WekaWrapper: Error - scores found more possible values than " + "probabilities.");
                new Exception().printStackTrace();
                System.exit(1);
            }
            double s = dist[i];
            String v = (String) enumeratedValues.nextElement();
            scores.put(v, s);
            ++i;
        }
    } else if (classAtt.isNumeric()) {
        System.err.println("WekaWrapper: Error - The 'scores' function should not be called "
                + "when the class attribute is numeric.");
        new Exception().printStackTrace();
        System.exit(1);
    } else {
        System.err.println(
                "WekaWrapper: Error - ScoreSet: Class Types must be either " + "Nominal, String, or Numeric.");
        new Exception().printStackTrace();
        System.exit(1);
    }

    return scores;
}

---

From source file:elh.eus.absa.Features.java

License:Open Source License

/**
 * Creates a feature set from a previously saved model. This allows to load previously saved feature sets. 
 * /*from w ww. java 2 s . co  m*/
 * @param model string: path to the serialized model containing header information
 * @throws IOException 
 */
private void createFeatureSetFromModel(String model) throws IOException {
    try {
        WekaWrapper ww = new WekaWrapper(model);
        Instances header = ww.loadHeader(model);

        int attNum = header.numAttributes();
        for (int i = 0; i < attNum; i++) {
            Attribute att = header.attribute(i);
            String name = att.name();
            if (att.isNumeric()) {
                addNumericFeature(name);
                //System.out.println("numeric feature: "+name);
            } else if (att.isNominal()) {
                //System.out.println("nominal feature: "+name+" - "+att.toString());
                ArrayList<String> vals = new ArrayList<String>();
                Enumeration<Object> e = att.enumerateValues();
                while (e.hasMoreElements()) {
                    vals.add(e.nextElement().toString());
                }
                addNominalFeature(name, vals);
            }
        }

        //General polarity lexicon
        if (header.attribute("polLexGen_posScore") != null) {
            this.polarLexiconGen = new Lexicon(new File(params.getProperty("polarLexiconGeneral")), "lemma");
            System.err.println("Features : createFeatureSet() - General polarity lexicon loaded -> "
                    + params.getProperty("polarLexiconGeneral") + " (" + this.polarLexiconGen.size()
                    + " entries)");
            System.out.println("Features : createFeatureSet() - General polarity lexicon loaded -> "
                    + params.getProperty("polarLexiconGeneral") + " (" + this.polarLexiconGen.size()
                    + " entries)");
        }

        //Domain polarity lexicon
        if (header.attribute("polLexDom_posScore") != null) {
            //this.polarLexiconDom = loadPolarityLexiconFromFile(params.getProperty("polarLexiconDomain"), "polLexDom_");
            this.polarLexiconDom = new Lexicon(new File(params.getProperty("polarLexiconDomain")), "lemma");
            System.err.println("Features : createFeatureSet() - Domain polarity lexicon loaded -> "
                    + params.getProperty("polarLexiconDomain") + " (" + this.polarLexiconDom.size()
                    + " entries)");
            System.out.println("Features : createFeatureSet() - Domain polarity lexicon loaded -> "
                    + params.getProperty("polarLexiconDomain") + " (" + this.polarLexiconDom.size()
                    + " entries)");
        }

        // Load clark cluster category info from files
        loadClusterFeatures("clark");

        // Load brown cluster category info from files
        loadClusterFeatures("brown");

        // Load word2vec cluster category info from files
        loadClusterFeatures("word2vec");

    } catch (Exception e) {
        System.err.println("Features::createFeatureSetFromFile -> error when loading model header");
        e.printStackTrace();
    }

}

---

From source file:en_deep.mlprocess.manipulation.featmodif.ReplaceMissing.java

License:Open Source License

/**
 * Set the output format if the class is nominal.
 *///from www .j av a 2  s  .co  m
private void setOutputFormat() {

    FastVector newAtts;
    Instances outputFormat;

    newAtts = new FastVector();

    BitSet attrSrc = new BitSet();

    for (int j = 0; j < getInputFormat().numAttributes(); j++) {

        Attribute att = null;
        Attribute srcAtt = getInputFormat().attribute(j);

        if (!m_Columns.isInRange(j) || srcAtt.indexOfValue(m_ReplVal) >= 0) {
            att = (Attribute) srcAtt.copy();
        } else if (srcAtt.isNominal()) {

            Enumeration<String> valsEnum = srcAtt.enumerateValues();
            ArrayList<String> valsList = new ArrayList<String>();

            while (valsEnum.hasMoreElements()) {
                valsList.add(valsEnum.nextElement());
            }
            valsList.add(m_ReplVal);

            att = new Attribute(srcAtt.name(), valsList);
        } else { // string attributes
            att = (Attribute) srcAtt.copy();
            att.addStringValue(m_ReplVal);
        }

        newAtts.addElement(att);
        attrSrc.set(j);
    }

    outputFormat = new Instances(getInputFormat().relationName(), newAtts, 0);
    outputFormat.setClassIndex(getInputFormat().classIndex());

    setOutputFormat(outputFormat);

    m_StringToCopy = new AttributeLocator(getInputFormat(), Attribute.STRING, MathUtils.findTrue(attrSrc));
}

---

From source file:gov.va.chir.tagline.TagLineEvaluator.java

License:Open Source License

private List<Set<Object>> getFoldDocIds(final Attribute attrDocId) {
    // Setup list of docs per fold
    final List<Set<Object>> folds = new ArrayList<Set<Object>>();

    for (int i = 0; i < numFolds; i++) {
        folds.add(new HashSet<Object>());
    }//ww  w  .  j a  v  a  2s.co m

    // Get distinct values
    final List<Object> docIds = new ArrayList<Object>();
    final Enumeration<?> enumer = attrDocId.enumerateValues();

    while (enumer.hasMoreElements()) {
        docIds.add((Object) enumer.nextElement());
    }

    if (docIds.size() < numFolds) {
        throw new IllegalStateException(String.format(
                "Number of folds must be less than or equal to number of "
                        + "distinct document IDs [num folds = %d | " + "num distinct document IDs = %d]",
                numFolds, docIds.size()));
    }

    // Randomly assign doc IDs to folds
    final Random random = new Random(randomSeed);

    int i = 0;
    int selected = -1;
    while (!docIds.isEmpty()) {
        selected = random.nextInt(docIds.size());
        folds.get(i).add(docIds.get(selected));
        docIds.remove(selected);

        if (++i >= numFolds) {
            i = 0;
        }
    }

    return folds;
}

---

From source file:lu.lippmann.cdb.graph.GraphUtil.java

License:Open Source License

public static void updateVariables(final Instances dataSet, final GraphWithOperations gr) {
    for (final CVariable var : gr.getVariables()) {
        final Attribute attribute = dataSet.attribute(var.getKey());
        if (attribute == null)
            throw new IllegalStateException("Attribute '" + var.getKey() + "' not found in dataset!?");
        if (attribute.isNominal()) {
            var.setType(CadralType.ENUMERATION);
            final List<String> values = new ArrayList<String>();
            final Enumeration<?> eval = attribute.enumerateValues();
            while (eval.hasMoreElements()) {
                values.add((String) eval.nextElement());
            }/*from  w ww .  j a va2s  . c o m*/
            var.setValues(values);
        } else if (attribute.isNumeric()) {
            var.setType(CadralType.NUMERIC);
        } else {
            var.setType(CadralType.UNKNOWN);
        }
    }
}

---

From source file:lu.lippmann.cdb.lab.beta.shih.Shih2010.java

License:Open Source License

public Shih2010(Instances instances, boolean ignoreClass, boolean needsToResample, double theta) {
    try {/* w  ww  .  j ava  2  s  . co  m*/
        this.instances = instances;
        this.theta = theta;
        this.resample = needsToResample;
        if (needsToResample) {
            final Resample rs = new Resample();
            if (this.instances.numInstances() > MAX_INSTANCES_TAKEN) {
                rs.setInputFormat(instances);
                rs.setSampleSizePercent(MAX_INSTANCES_TAKEN * 100.0 / this.instances.numInstances());
                this.instances = Filter.useFilter(instances, rs);
            }
        }

        //System.out.println("Size = " + this.instances.numInstances());

        this.mapDomain = new HashMap<Integer, Set<String>>();

        if (ignoreClass) {
            this.instances.setClassIndex(-1);
        }

        //Save index of nominal & categorial attributes
        //Build a map i-DOM -> Attribute index
        this.idxsC = new ArrayList<Integer>();
        this.idxsN = new ArrayList<Integer>();
        int nn = 0;

        for (int i = 0; i < instances.numAttributes(); i++) {
            if (!instances.attribute(i).isNumeric())
                mapDomain.put(i, new HashSet<String>());
        }

        //Create map index & domain
        this.mapIndex = new HashMap<Integer, Map<String, Integer>>();
        int mapIdx = 0;
        for (int i = 0; i < instances.numAttributes(); i++) {
            Attribute attribute = instances.attribute(i);
            if (!attribute.isNumeric()) {
                idxsC.add(i); //i-th attribute is nominal
                final Map<String, Integer> mapIndexAttribute = new HashMap<String, Integer>();
                mapIndex.put(i, mapIndexAttribute);
                Enumeration<?> en = attribute.enumerateValues();
                while (en.hasMoreElements()) {
                    String catVal = en.nextElement().toString();
                    boolean created = mapDomain.get(i).add(catVal);
                    if (created) {
                        mapIndexAttribute.put(catVal, mapIdx++);
                    }
                }
                nn += mapDomain.get(i).size(); //count total nominal values
            } else {
                idxsN.add(i);
            }
        }

        this.n = nn;
        this.base = new ArrayList<TupleSI>();
        this.noBase = new ArrayList<TupleSI>();
        this.M = new int[n][n];
        this.D = new double[n][n];
        this.F = new HashMap<TupleSI, Double>();
        this.computeBase();
        this.computeMatrixMDF();
    } catch (Exception e) {
        e.printStackTrace();
    }

}

---

From source file:lu.lippmann.cdb.lab.beta.shih.Shih2010.java

License:Open Source License

/**
 * // w  w w .  ja  va  2s.  c o  m
 * @param dataSet
 * @return
 */
private void computeBase() {
    //Save base
    int attributeIndex = -1;
    int max = 0;
    for (int i = 0; i < instances.numAttributes(); i++) {
        final Attribute attribute = instances.attribute(i);

        //Ignore class attribute if needed
        if (attribute.index() == instances.classIndex() && ignoreClass)
            continue;

        if (!attribute.isNumeric()) {
            int size = instances.attributeStats(i).nominalCounts.length;
            if (size > max) {
                attributeIndex = i;
                max = size;
            }
        }
    }
    final Attribute maxAttribute = instances.attribute(attributeIndex);
    Enumeration<?> en = maxAttribute.enumerateValues();
    while (en.hasMoreElements()) {
        base.add(new TupleSI(en.nextElement().toString(), attributeIndex));
    }
    this.baseIndex = attributeIndex;

    //Save noBase
    for (int i = 0; i < instances.numAttributes(); i++) {
        Attribute attribute = instances.attribute(i);
        if (attribute.index() == instances.classIndex() && ignoreClass)
            continue;
        if (i != attributeIndex && !instances.attribute(i).isNumeric()) {
            Enumeration<?> enb = attribute.enumerateValues();
            while (enb.hasMoreElements()) {
                noBase.add(new TupleSI(enb.nextElement().toString(), i));
            }
        }
    }
}

---

• «
• 1
• 2
• 3
• »