Example usage for weka.core Instance setValue

Introduction

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

Prototype

public void setValue(Attribute att, String value);

Source Link

Document

Sets a value of an nominal or string attribute to the given value.

Usage

From source file:fk.stardust.localizer.machinelearn.WekaFaultLocalizer.java

License:Open Source License

@Override
public Ranking<T> localize(final ISpectra<T> spectra) {

    // == 1. Create Weka training instance

    final List<INode<T>> nodes = new ArrayList<>(spectra.getNodes());

    // nominal true/false values
    final List<String> tf = new ArrayList<String>();
    tf.add("t");//from ww w.j  av a 2 s  .  co  m
    tf.add("f");

    // create an attribute for each component
    final Map<INode<T>, Attribute> attributeMap = new HashMap<INode<T>, Attribute>();
    final ArrayList<Attribute> attributeList = new ArrayList<Attribute>(); // NOCS: Weka needs ArrayList..
    for (final INode<T> node : nodes) {
        final Attribute attribute = new Attribute(node.toString(), tf);
        attributeList.add(attribute);
        attributeMap.put(node, attribute);
    }

    // create class attribute (trace success)
    final Attribute successAttribute = new Attribute("success", tf);
    attributeList.add(successAttribute);

    // create weka training instance
    final Instances trainingSet = new Instances("TraceInfoInstances", attributeList, 1);
    trainingSet.setClassIndex(attributeList.size() - 1);

    // == 2. add traces to training set

    // add an instance for each trace
    for (final ITrace<T> trace : spectra.getTraces()) {
        final Instance instance = new DenseInstance(nodes.size() + 1);
        instance.setDataset(trainingSet);
        for (final INode<T> node : nodes) {
            instance.setValue(attributeMap.get(node), trace.isInvolved(node) ? "t" : "f");
        }
        instance.setValue(successAttribute, trace.isSuccessful() ? "t" : "f");
        trainingSet.add(instance);
    }

    // == 3. use prediction to localize faults

    // build classifier
    try {
        final Classifier classifier = this.buildClassifier(this.classifierName, this.classifierOptions,
                trainingSet);
        final Ranking<T> ranking = new Ranking<>();

        System.out.println("begin classifying");
        int classified = 0;

        final Instance instance = new DenseInstance(nodes.size() + 1);
        instance.setDataset(trainingSet);
        for (final INode<T> node : nodes) {
            instance.setValue(attributeMap.get(node), "f");
        }
        instance.setValue(successAttribute, "f");

        for (final INode<T> node : nodes) {
            classified++;
            if (classified % 1000 == 0) {
                System.out.println(String.format("Classified %d nodes.", classified));
            }

            // contain only the current node in the network
            instance.setValue(attributeMap.get(node), "t");

            // predict with which probability this setup leads to a failing network
            final double[] distribution = classifier.distributionForInstance(instance);
            ranking.rank(node, distribution[1]);

            // reset involvment for node
            instance.setValue(attributeMap.get(node), "f");
        }
        return ranking;
    } catch (final Exception e) { // NOCS: Weka throws only raw exceptions
        throw new RuntimeException(e);
    }
}

---

From source file:form.ml.ClassifierTemplate.java

/**
 * make the Instance weka object from a String
 *
 * @param text the String to be converted
 * @return Instance object//from   w w w.  j a  va2s .  c o  m
 */
private Instance makeInstance(String text) {
    Instance instance = new Instance(2);
    Attribute attribute = train.attribute("text");
    instance.setValue(attribute, attribute.addStringValue(text));
    instance.setDataset(train);
    return instance;
}

---

From source file:fr.loria.synalp.jtrans.phonetiseur.Classifieurs.java

License:Open Source License

private void setval(Instance ii, int i, String s) {
    try {/*www  . j  av  a  2 s .c  o  m*/
        ii.setValue(i, s);
    } catch (IllegalArgumentException e) {
        System.err.println(String.format("setval failed (ii: %s, i: %d, s: %s), %s", ii, i, s, e));
    }
}

---

From source file:gnusmail.filters.mail_metadata.MultilabelFolder.java

License:Open Source License

@Override
public void updateInstance(Instance inst, Document doc) {
    if (doc instanceof MailMessage) {
        Message m = ((MailMessage) doc).getMessage();
        MessageInfo mi = new MessageInfo(m);
        List<String> listOfFolders = extractFoldersFromHierarchy(mi.getFolderAsString());
        for (Attribute att : attList) {
            if (listOfFolders.contains(att.name())) {
                inst.setValue(att, "1");
            } else {
                inst.setValue(att, "0");
            }/*  w  w  w.ja  v  a 2 s  .  c o  m*/
        }
    }
}

---

From source file:gnusmail.filters.SingleAttFilter.java

License:Open Source License

@Override
public void updateInstance(Instance inst, Document document) {
    try {/*  ww  w  .j  a v a 2s . c om*/
        int index = attribute.indexOfValue(getSingleValue(document));
        inst.setValue(attribute, index);
    } catch (MessagingException e) {
        inst.setMissing(attribute);
    }
}

---

From source file:gnusmail.filters.SingleNumericAttFilter.java

License:Open Source License

@Override
public void updateInstance(Instance inst, Document doc) {
    try {//from w w  w.  j  ava  2s.c  o m
        inst.setValue(attribute, getSingleValue(doc));
    } catch (MessagingException e) {
        inst.setMissing(attribute);
    }
}

---

From source file:gnusmail.filters.WordFrequency.java

License:Open Source License

@Override
public void updateInstance(Instance inst, Document doc) {
    Set<String> stringThisDocument = new HashSet<String>();
    List<Token> tokens = tokenizeDocument(doc);
    for (Token token : tokens) {
        String stemmedForm = token.getStemmedForm();
        if (stemmedForm.length() > 2) {
            stringThisDocument.add(stemmedForm);
        }//from   w w w . j av a2 s.com
    }

    for (Attribute att : attList) {
        if (stringThisDocument.contains(att.name())) { //TODO esto es lento...mejorar. Pondria un getWords en Documnet
            inst.setValue(att, "True");
        } else {
            inst.setValue(att, "False");
        }
    }
}

---

From source file:gov.va.chir.tagline.dao.DatasetUtil.java

License:Open Source License

public static Instances createDataset(final Collection<Document> documents) {

    // Key = feature name | Value = number representing NUMERIC, NOMINAL, etc.
    final Map<String, Integer> featureType = new TreeMap<String, Integer>();

    // Key = feature name | Values = distinct values for NOMINAL values
    final Map<String, Set<String>> nominalFeatureMap = new HashMap<String, Set<String>>();

    final Set<String> labels = new TreeSet<String>();
    final Set<String> docIds = new TreeSet<String>();

    // First scan -- determine attribute values
    for (Document document : documents) {
        processFeatures(document.getFeatures(), featureType, nominalFeatureMap);
        docIds.add(document.getName());/*from  ww  w.  j a  v  a  2  s  .  c o m*/

        for (Line line : document.getLines()) {
            processFeatures(line.getFeatures(), featureType, nominalFeatureMap);

            labels.add(line.getLabel());
        }
    }

    final ArrayList<Attribute> attributes = new ArrayList<Attribute>();

    // Add Document and Line IDs as first two attributes
    //final Attribute docId = new Attribute(DOC_ID, (ArrayList<String>) null);
    final Attribute docId = new Attribute(DOC_ID, new ArrayList<String>(docIds));
    final Attribute lineId = new Attribute(LINE_ID);

    attributes.add(docId);
    attributes.add(lineId);

    // Build attributes
    for (String feature : featureType.keySet()) {
        final int type = featureType.get(feature);

        if (type == Attribute.NUMERIC) {
            attributes.add(new Attribute(feature));
        } else {
            if (nominalFeatureMap.containsKey(feature)) {
                attributes.add(new Attribute(feature, new ArrayList<String>(nominalFeatureMap.get(feature))));
            }
        }
    }

    // Add class attribute
    Attribute classAttr = new Attribute(LABEL, new ArrayList<String>(labels));
    attributes.add(classAttr);

    final Instances instances = new Instances("train", attributes, documents.size());

    // Second scan -- add data
    for (Document document : documents) {
        final Map<String, Object> docFeatures = document.getFeatures();

        for (Line line : document.getLines()) {
            final Instance instance = new DenseInstance(attributes.size());

            final Map<String, Object> lineFeatures = line.getFeatures();
            lineFeatures.putAll(docFeatures);

            instance.setValue(docId, document.getName());
            instance.setValue(lineId, line.getLineId());
            instance.setValue(classAttr, line.getLabel());

            for (Attribute attribute : attributes) {
                if (!attribute.equals(docId) && !attribute.equals(lineId) && !attribute.equals(classAttr)) {
                    final String name = attribute.name();
                    final Object obj = lineFeatures.get(name);

                    if (obj instanceof Double) {
                        instance.setValue(attribute, ((Double) obj).doubleValue());
                    } else if (obj instanceof Integer) {
                        instance.setValue(attribute, ((Integer) obj).doubleValue());
                    } else {
                        instance.setValue(attribute, obj.toString());
                    }
                }
            }

            instances.add(instance);
        }
    }

    // Set last attribute as class
    instances.setClassIndex(attributes.size() - 1);

    return instances;
}

---

From source file:gov.va.chir.tagline.dao.DatasetUtil.java

License:Open Source License

@SuppressWarnings("unchecked")
public static Instances createDataset(final Instances header, final Collection<Document> documents)
        throws Exception {

    // Update header to include all docIDs from the passed in documents
    // (Weka requires all values for nominal features)
    final Set<String> docIds = new TreeSet<String>();

    for (Document document : documents) {
        docIds.add(document.getName());/*from   w ww . j a va2  s .  c om*/
    }

    final AddValues avf = new AddValues();
    avf.setLabels(StringUtils.join(docIds, ","));

    // Have to add 1 because SingleIndex.setValue() has a bug, expecting
    // the passed in index to be 1-based rather than 0-based. Why? I have 
    // no idea.
    // Calling path: AddValues.setInputFormat() -->
    //               SingleIndex.setUpper() -->
    //               SingleIndex.setValue()
    avf.setAttributeIndex(String.valueOf(header.attribute(DOC_ID).index() + 1));

    avf.setInputFormat(header);
    final Instances newHeader = Filter.useFilter(header, avf);

    final Instances instances = new Instances(newHeader, documents.size());

    // Map attributes
    final Map<String, Attribute> attrMap = new HashMap<String, Attribute>();

    final Enumeration<Attribute> en = newHeader.enumerateAttributes();

    while (en.hasMoreElements()) {
        final Attribute attr = en.nextElement();

        attrMap.put(attr.name(), attr);
    }

    attrMap.put(newHeader.classAttribute().name(), newHeader.classAttribute());

    final Attribute docId = attrMap.get(DOC_ID);
    final Attribute lineId = attrMap.get(LINE_ID);
    final Attribute classAttr = attrMap.get(LABEL);

    // Add data
    for (Document document : documents) {
        final Map<String, Object> docFeatures = document.getFeatures();

        for (Line line : document.getLines()) {
            final Instance instance = new DenseInstance(attrMap.size());

            final Map<String, Object> lineFeatures = line.getFeatures();
            lineFeatures.putAll(docFeatures);

            instance.setValue(docId, document.getName());
            instance.setValue(lineId, line.getLineId());

            if (line.getLabel() == null) {
                instance.setMissing(classAttr);
            } else {
                instance.setValue(classAttr, line.getLabel());
            }

            for (Attribute attribute : attrMap.values()) {
                if (!attribute.equals(docId) && !attribute.equals(lineId) && !attribute.equals(classAttr)) {
                    final String name = attribute.name();
                    final Object obj = lineFeatures.get(name);

                    if (obj instanceof Double) {
                        instance.setValue(attribute, ((Double) obj).doubleValue());
                    } else if (obj instanceof Integer) {
                        instance.setValue(attribute, ((Integer) obj).doubleValue());
                    } else {
                        instance.setValue(attribute, obj.toString());
                    }
                }
            }

            instances.add(instance);
        }
    }

    // Set last attribute as class
    instances.setClassIndex(attrMap.size() - 1);

    return instances;
}

---

From source file:gr.demokritos.iit.cpgislanddetection.io.FileCreatorARFF.java

public Instances createARFF(List<Vector<Integer>> listVector, String nameClass) throws ParseException {

    // Declare four numeric attributes
    Attribute Attribute1 = new Attribute("adenine");
    Attribute Attribute2 = new Attribute("thymine");
    Attribute Attribute3 = new Attribute("cytosine");
    Attribute Attribute4 = new Attribute("guanine");

    // Declare the class attribute along with its values
    FastVector fvClassVal = new FastVector(2);
    fvClassVal.addElement("yes");
    fvClassVal.addElement("no");
    Attribute ClassAttribute = new Attribute("theClass", fvClassVal);

    // Declare the feature vector
    FastVector fvWekaAttributes = new FastVector(5);
    fvWekaAttributes.addElement(Attribute1);
    fvWekaAttributes.addElement(Attribute2);
    fvWekaAttributes.addElement(Attribute3);
    fvWekaAttributes.addElement(Attribute4);
    fvWekaAttributes.addElement(ClassAttribute);

    // Create an empty training set
    int capacity = listVector.size() + 7;
    Instances isTrainingSet = new Instances("isCpG", fvWekaAttributes, capacity);

    // Set class index
    isTrainingSet.setClassIndex(4);// w  ww.j av a2s.  c  om

    // Create the instances from the file with vectors
    for (int i = 0; i < listVector.size(); i++) {
        Instance instance = new Instance(5);
        instance.setValue((Attribute) fvWekaAttributes.elementAt(0), listVector.get(i).get(0));
        instance.setValue((Attribute) fvWekaAttributes.elementAt(1), listVector.get(i).get(1));
        instance.setValue((Attribute) fvWekaAttributes.elementAt(2), listVector.get(i).get(2));
        instance.setValue((Attribute) fvWekaAttributes.elementAt(3), listVector.get(i).get(3));
        instance.setValue((Attribute) fvWekaAttributes.elementAt(4), nameClass);

        //add the instance in training set
        isTrainingSet.add(instance);

    }
    System.out.println(isTrainingSet);
    return isTrainingSet;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• »