Examples with Instances weka.core.Instances used on opensource projects

Example 1 with Instances

use of weka.core.Instances in project mcib3d-core by mcib3d.

the class DataSet method loadDataARFF.

public void loadDataARFF(String fileName) {
    Instances dataTmp = null;
    try {
        dataTmp = new Instances(new BufferedReader(new FileReader(fileName)));
    } catch (IOException e) {
        e.printStackTrace();
    }
    dataTmp.setClassIndex(attributes.getClassIndex());
    if (dataTmp.numAttributes() == attributes.size())
        instances = dataTmp;
    else
        IJ.log("Pb readind arff, number of attributes different");
}

Example 2 with Instances

use of weka.core.Instances in project 490 by pauleibye.

the class MainFrame method createCSVandArff.

// convert our weird arraylist to a sick ARFF file and save it
public void createCSVandArff(FeatureExtractor FE) {
    try {
        File file = new File("csv.txt");
        if (!file.exists()) {
            file.createNewFile();
            PrintWriter writer = new PrintWriter(file);
            for (String s : FE.getFileFeatures()) {
                writer.println(s);
            }
            writer.close();
        }
        File arff = new File("data.arff");
        if (!arff.exists()) {
            CSVLoader loader = new CSVLoader();
            loader.setSource(file);
            Instances data = loader.getDataSet();
            ArffSaver saver = new ArffSaver();
            saver.setInstances(data);
            saver.setFile(arff);
            saver.writeBatch();
        }
    } catch (IOException e) {
        System.out.println("Exception Occurred:");
        e.printStackTrace();
    }
}

Example 3 with Instances

use of weka.core.Instances in project iobserve-analysis by research-iobserve.

the class AbstractClustering method createInstances.

/**
 * It transforms the user sessions(userSessions in form of counts of their called operation
 * signatures) to Weka instances that can be used for the clustering.
 *
 * @param countModel
 *            contains the userSessions in form of counts of called operation signatures
 * @param listOfDistinctOperationSignatures
 *            contains the extracted distinct operation signatures of the input
 *            entryCallSequenceModel
 * @return the Weka instances that hold the data that is used for the clustering
 */
protected Instances createInstances(final List<UserSessionAsCountsOfCalls> countModel, final List<String> listOfDistinctOperationSignatures) {
    final int numberOfDistinctOperationSignatures = listOfDistinctOperationSignatures.size();
    final FastVector fvWekaAttributes = new FastVector(numberOfDistinctOperationSignatures);
    for (int i = 0; i < numberOfDistinctOperationSignatures; i++) {
        final String attributeName = "Attribute" + i;
        final Attribute attribute = new Attribute(attributeName);
        fvWekaAttributes.addElement(attribute);
    }
    final Instances clusterSet = new Instances("CallCounts", fvWekaAttributes, countModel.size());
    for (final UserSessionAsCountsOfCalls userSession : countModel) {
        int indexOfAttribute = 0;
        final Instance instance = new Instance(numberOfDistinctOperationSignatures);
        for (int row = 0; row < listOfDistinctOperationSignatures.size(); row++) {
            instance.setValue((Attribute) fvWekaAttributes.elementAt(indexOfAttribute), userSession.getAbsoluteCountOfCalls()[row]);
            indexOfAttribute++;
        }
        clusterSet.add(instance);
    }
    return clusterSet;
}

Example 4 with Instances

use of weka.core.Instances in project iobserve-analysis by research-iobserve.

the class BehaviorModelTable method toInstances.

/**
 * create an Instances object for clustering.
 *
 * @return instance
 */
public Instances toInstances() {
    final FastVector fastVector = new FastVector();
    // add transitions
    for (int i = 0; i < this.signatures.size(); i++) {
        for (int j = 0; j < this.signatures.size(); j++) {
            if (this.transitions[i][j] > AbstractBehaviorModelTable.TRANSITION_THRESHOLD) {
                final Attribute attribute = new Attribute(AbstractBehaviorModelTable.EDGE_INDICATOR + this.inverseSignatures[i] + AbstractBehaviorModelTable.EDGE_DIVIDER + this.inverseSignatures[j]);
                fastVector.addElement(attribute);
            } else {
                continue;
            }
        }
    }
    // add informations
    this.signatures.values().stream().forEach(pair -> Arrays.stream(pair.getSecond()).forEach(callInformation -> fastVector.addElement(new Attribute(AbstractBehaviorModelTable.INFORMATION_INDICATOR + this.inverseSignatures[pair.getFirst()] + AbstractBehaviorModelTable.INFORMATION_DIVIDER + callInformation.getSignature()))));
    // TODO name
    final Instances instances = new Instances("Test", fastVector, 0);
    final Instance instance = this.toInstance();
    instances.add(instance);
    return instances;
}

Example 5 with Instances

use of weka.core.Instances in project cia by Hack23.

the class WordCounterImpl method calculateWordCount.

@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);
    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(TOKEN_DELIMITERS);
    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;
}