Example usage for weka.core Instances Instances

List of usage examples for weka.core Instances Instances

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

Introduction

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

Prototype

public Instances(Instances dataset)

Source Link

Document

Constructor copying all instances and references to the header information from the given set of instances.

Usage

From source file:activeSegmentation.learning.WekaDataSet.java

License:Open Source License

/**
 * Constructs a WekaDataset//ww w.  j  av a2  s  . c o m
 *
 * @param arffFilePath The path to the arff file
 */
public WekaDataSet(String arffFilePath) {
    try {
        dataset = new Instances(new FileReader(arffFilePath));
    } catch (IOException ex) {
        Logger.getLogger(WekaDataSet.class.getName()).log(Level.SEVERE, null, ex);
    }

}

From source file:activeSegmentation.learning.WekaDataSet.java

License:Open Source License

/**
 * Creates a Weka dataset from an Instances object
 *
 * @param dataset The weka dataset//from  www.j a  va2  s.  c  o m
 */
public WekaDataSet(Instances dataset) {
    this.dataset = new Instances(dataset);
}

From source file:activeSegmentation.learning.WekaDataSet.java

License:Open Source License

/**
 * Creates a Weka Dataset from other Weka Dataset.
 *
 * @param dataset The dataset to use.//  w w w  .  j a  v a  2  s . c  om
 */
public WekaDataSet(IDataSet dataset) {
    this.dataset = new Instances(dataset.getDataset());
}

From source file:adams.data.instancesanalysis.pls.PLS1.java

License:Open Source License

/**
 * Performs predictions on the data./*from ww w .j a v  a 2 s .  com*/
 *
 * @param data   the input data
 * @return      the predicted data
 */
protected Instances predict(Instances data) {
    Instances result;
    Instances tmpInst;
    int i;
    int j;
    Matrix x;
    Matrix X;
    Matrix T;
    Matrix t;

    result = new Instances(getOutputFormat());

    for (i = 0; i < data.numInstances(); i++) {
        // work on each instance
        tmpInst = new Instances(data, 0);
        tmpInst.add((Instance) data.instance(i).copy());
        x = MatrixHelper.getX(tmpInst);
        X = new Matrix(1, getNumComponents());
        T = new Matrix(1, getNumComponents());

        for (j = 0; j < getNumComponents(); j++) {
            MatrixHelper.setVector(x, X, j);
            // 1. step: tj = xj * wj
            t = x.times(MatrixHelper.getVector(m_W, j));
            MatrixHelper.setVector(t, T, j);
            // 2. step: xj+1 = xj - tj*pj^T (tj is 1x1 matrix!)
            x = x.minus(MatrixHelper.getVector(m_P, j).transpose().times(t.get(0, 0)));
        }

        switch (m_PredictionType) {
        case ALL:
            tmpInst = MatrixHelper.toInstances(getOutputFormat(), T, T.times(m_b_hat));
            break;
        case NONE:
        case EXCEPT_CLASS:
            tmpInst = MatrixHelper.toInstances(getOutputFormat(), T, MatrixHelper.getY(tmpInst));
            break;
        default:
            throw new IllegalStateException("Unhandled prediction type: " + m_PredictionType);
        }

        result.add(tmpInst.instance(0));

    }

    return result;
}

From source file:adams.data.instancesanalysis.PLS.java

License:Open Source License

/**
 * Performs the actual analysis./* w  w w .ja v a2s. com*/
 *
 * @param data   the data to analyze
 * @return      null if successful, otherwise error message
 * @throws Exception   if analysis fails
 */
@Override
protected String doAnalyze(Instances data) throws Exception {
    String result;
    Remove remove;
    weka.filters.supervised.attribute.PLS pls;
    WekaInstancesToSpreadSheet conv;
    SpreadSheet transformed;
    Matrix matrix;
    SpreadSheet loadings;
    Row row;
    int i;
    int n;

    m_Loadings = null;
    m_Scores = null;

    data = new Instances(data);
    data.deleteWithMissingClass();

    if (!m_AttributeRange.isAllRange()) {
        if (isLoggingEnabled())
            getLogger().info("Filtering attribute range: " + m_AttributeRange.getRange());
        remove = new Remove();
        remove.setAttributeIndicesArray(m_AttributeRange.getIntIndices());
        remove.setInvertSelection(true);
        remove.setInputFormat(data);
        data = Filter.useFilter(data, remove);
    }
    if (isLoggingEnabled())
        getLogger().info("Performing PLS...");

    pls = new weka.filters.supervised.attribute.PLS();
    pls.setAlgorithm(m_Algorithm);
    pls.setInputFormat(data);
    data = Filter.useFilter(data, pls);
    conv = new WekaInstancesToSpreadSheet();
    conv.setInput(data);
    result = conv.convert();
    if (result == null) {
        transformed = (SpreadSheet) conv.getOutput();
        matrix = pls.getLoadings();
        loadings = new DefaultSpreadSheet();
        for (i = 0; i < matrix.getColumnDimension(); i++)
            loadings.getHeaderRow().addCell("L-" + (i + 1)).setContentAsString("Loading-" + (i + 1));
        for (n = 0; n < matrix.getRowDimension(); n++) {
            row = loadings.addRow();
            for (i = 0; i < matrix.getColumnDimension(); i++)
                row.addCell("L-" + (i + 1)).setContent(matrix.get(n, i));
        }
        m_Loadings = loadings;
        m_Scores = transformed;
    }

    return result;
}

From source file:adams.flow.transformer.WekaAttributeSelection.java

License:Open Source License

/**
 * Executes the flow item.//w  w w  .j av a  2s  .c o m
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instances data;
    Instances reduced;
    Instances transformed;
    AttributeSelection eval;
    boolean crossValidate;
    int fold;
    Instances train;
    WekaAttributeSelectionContainer cont;
    SpreadSheet stats;
    int i;
    Row row;
    int[] selected;
    double[][] ranked;
    Range range;
    String rangeStr;
    boolean useReduced;

    result = null;

    try {
        if (m_InputToken.getPayload() instanceof Instances)
            data = (Instances) m_InputToken.getPayload();
        else
            data = (Instances) ((WekaTrainTestSetContainer) m_InputToken.getPayload())
                    .getValue(WekaTrainTestSetContainer.VALUE_TRAIN);

        if (result == null) {
            crossValidate = (m_Folds >= 2);

            // setup evaluation
            eval = new AttributeSelection();
            eval.setEvaluator(m_Evaluator);
            eval.setSearch(m_Search);
            eval.setFolds(m_Folds);
            eval.setSeed((int) m_Seed);
            eval.setXval(crossValidate);

            // select attributes
            if (crossValidate) {
                Random random = new Random(m_Seed);
                data = new Instances(data);
                data.randomize(random);
                if ((data.classIndex() > -1) && data.classAttribute().isNominal()) {
                    if (isLoggingEnabled())
                        getLogger().info("Stratifying instances...");
                    data.stratify(m_Folds);
                }
                for (fold = 0; fold < m_Folds; fold++) {
                    if (isLoggingEnabled())
                        getLogger().info("Creating splits for fold " + (fold + 1) + "...");
                    train = data.trainCV(m_Folds, fold, random);
                    if (isLoggingEnabled())
                        getLogger().info("Selecting attributes using all but fold " + (fold + 1) + "...");
                    eval.selectAttributesCVSplit(train);
                }
            } else {
                eval.SelectAttributes(data);
            }

            // generate reduced/transformed dataset
            reduced = null;
            transformed = null;
            if (!crossValidate) {
                reduced = eval.reduceDimensionality(data);
                if (m_Evaluator instanceof AttributeTransformer)
                    transformed = ((AttributeTransformer) m_Evaluator).transformedData(data);
            }

            // generated stats
            stats = null;
            if (!crossValidate) {
                stats = new DefaultSpreadSheet();
                row = stats.getHeaderRow();

                useReduced = false;
                if (m_Search instanceof RankedOutputSearch) {
                    i = reduced.numAttributes();
                    if (reduced.classIndex() > -1)
                        i--;
                    ranked = eval.rankedAttributes();
                    useReduced = (ranked.length == i);
                }

                if (useReduced) {
                    for (i = 0; i < reduced.numAttributes(); i++)
                        row.addCell("" + i).setContent(reduced.attribute(i).name());
                    row = stats.addRow();
                    for (i = 0; i < reduced.numAttributes(); i++)
                        row.addCell(i).setContent(0.0);
                } else {
                    for (i = 0; i < data.numAttributes(); i++)
                        row.addCell("" + i).setContent(data.attribute(i).name());
                    row = stats.addRow();
                    for (i = 0; i < data.numAttributes(); i++)
                        row.addCell(i).setContent(0.0);
                }

                if (m_Search instanceof RankedOutputSearch) {
                    ranked = eval.rankedAttributes();
                    for (i = 0; i < ranked.length; i++)
                        row.getCell((int) ranked[i][0]).setContent(ranked[i][1]);
                } else {
                    selected = eval.selectedAttributes();
                    for (i = 0; i < selected.length; i++)
                        row.getCell(selected[i]).setContent(1.0);
                }
            }

            // selected attributes
            rangeStr = null;
            if (!crossValidate) {
                range = new Range();
                range.setIndices(eval.selectedAttributes());
                rangeStr = range.getRange();
            }

            // setup container
            if (crossValidate)
                cont = new WekaAttributeSelectionContainer(data, reduced, transformed, eval, m_Seed, m_Folds);
            else
                cont = new WekaAttributeSelectionContainer(data, reduced, transformed, eval, stats, rangeStr);
            m_OutputToken = new Token(cont);
        }
    } catch (Exception e) {
        m_OutputToken = null;
        result = handleException("Failed to process data:", e);
    }

    return result;
}

From source file:adams.flow.transformer.WekaInstancesAppend.java

License:Open Source License

/**
 * Executes the flow item./*from ww w.  j  av a  2 s.c  o  m*/
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    String[] filesStr;
    File[] files;
    int i;
    int n;
    Instances[] inst;
    Instances full;
    String msg;
    StringBuilder relation;
    double[] values;

    result = null;

    // get filenames
    files = null;
    inst = null;
    if (m_InputToken.getPayload() instanceof String[]) {
        filesStr = (String[]) m_InputToken.getPayload();
        files = new File[filesStr.length];
        for (i = 0; i < filesStr.length; i++)
            files[i] = new PlaceholderFile(filesStr[i]);
    } else if (m_InputToken.getPayload() instanceof File[]) {
        files = (File[]) m_InputToken.getPayload();
    } else if (m_InputToken.getPayload() instanceof Instances[]) {
        inst = (Instances[]) m_InputToken.getPayload();
    } else {
        throw new IllegalStateException("Unhandled input type: " + m_InputToken.getPayload().getClass());
    }

    // load data?
    if (files != null) {
        inst = new Instances[files.length];
        for (i = 0; i < files.length; i++) {
            try {
                inst[i] = DataSource.read(files[i].getAbsolutePath());
            } catch (Exception e) {
                result = handleException("Failed to load dataset: " + files[i], e);
                break;
            }
        }
    }

    // test compatibility
    if (result == null) {
        for (i = 0; i < inst.length - 1; i++) {
            for (n = i + 1; n < inst.length; n++) {
                if ((msg = inst[i].equalHeadersMsg(inst[n])) != null) {
                    result = "Dataset #" + (i + 1) + " and #" + (n + 1) + " are not compatible:\n" + msg;
                    break;
                }
            }
            if (result != null)
                break;
        }
    }

    // append
    if (result == null) {
        full = new Instances(inst[0]);
        relation = new StringBuilder(inst[0].relationName());
        for (i = 1; i < inst.length; i++) {
            relation.append("+" + inst[i].relationName());
            for (Instance row : inst[i]) {
                values = row.toDoubleArray();
                for (n = 0; n < values.length; n++) {
                    if (row.attribute(n).isString())
                        values[n] = full.attribute(n).addStringValue(row.stringValue(n));
                    else if (row.attribute(n).isRelationValued())
                        values[n] = full.attribute(n).addRelation(row.relationalValue(n));
                }
                if (row instanceof SparseInstance)
                    row = new SparseInstance(row.weight(), values);
                else
                    row = new DenseInstance(row.weight(), values);
                full.add(row);
            }
        }
        full.setRelationName(relation.toString());
        m_OutputToken = new Token(full);
    }

    return result;
}

From source file:adams.flow.transformer.WekaRandomSplit.java

License:Open Source License

/**
 * Executes the flow item.//from ww w  . j  a v  a2  s  . c  o  m
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instances inst;
    RandomSplitGenerator generator;

    result = null;
    inst = new Instances((Instances) m_InputToken.getPayload());

    try {
        generator = (RandomSplitGenerator) OptionUtils.shallowCopy(m_Generator);
        generator.setData(inst);
        generator.setSeed(m_Seed);
        generator.setPercentage(m_Percentage);
        generator.setPreserveOrder(m_PreserveOrder);
        generator.setUseViews(m_CreateView);
    } catch (Exception e) {
        generator = null;
        result = handleException("Failed to generate split!", e);
    }

    if (result == null)
        m_OutputToken = new Token(generator.next());

    updateProvenance(m_OutputToken);

    return result;
}

From source file:adams.flow.transformer.WekaSetInstancesValue.java

License:Open Source License

/**
 * Executes the flow item.//from ww w.  java 2s.  c o  m
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instances inst;
    int row;
    int index;

    result = null;

    inst = (Instances) m_InputToken.getPayload();
    inst = new Instances(inst);
    m_Row.setMax(inst.numInstances());
    m_Column.setData(inst);
    row = m_Row.getIntIndex();
    index = m_Column.getIntIndex();

    if (row == -1)
        result = "Failed to retrieve row: " + m_Row.getIndex();
    else if (index == -1)
        result = "Failed to retrieve column: " + m_Column.getIndex();

    if (result == null) {
        try {
            if (m_Value.equals("?")) {
                inst.instance(row).setMissing(index);
            } else {
                switch (inst.attribute(index).type()) {
                case Attribute.NUMERIC:
                    inst.instance(row).setValue(index, Utils.toDouble(m_Value));
                    break;

                case Attribute.DATE:
                    inst.instance(row).setValue(index, inst.attribute(index).parseDate(m_Value));
                    break;

                case Attribute.NOMINAL:
                case Attribute.STRING:
                    inst.instance(row).setValue(index, m_Value);
                    break;

                case Attribute.RELATIONAL:
                    result = "Relational attributes cannot be set!";
                    break;

                default:
                    result = "Unhandled attribute type: " + inst.attribute(index).type();
                }
            }
        } catch (Exception e) {
            result = handleException("Failed to set value: " + m_Column.getIndex() + " -> " + m_Value, e);
        }
    }

    // broadcast data
    if (result == null)
        m_OutputToken = new Token(inst);

    return result;
}

From source file:adams.flow.transformer.WekaSubsets.java

License:Open Source License

/**
 * Executes the flow item.// w  ww.j a v a2s  .  c o m
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instances data;
    Double old;
    Double curr;
    int i;
    int index;
    Instance inst;

    result = null;

    m_Queue.clear();

    // copy and sort data
    data = new Instances((Instances) m_InputToken.getPayload());
    m_Index.setData(data);
    ;
    index = m_Index.getIntIndex();
    data.sort(index);

    // create subsets
    old = null;
    i = 0;
    while (i < data.numInstances()) {
        inst = data.instance(i);
        curr = inst.value(index);
        if ((old == null) || !curr.equals(old)) {
            m_Queue.add(new Instances(data, data.numInstances()));
            old = curr;
        }
        m_Queue.get(m_Queue.size() - 1).add(inst);
        i++;
    }

    // compact subsets
    for (Instances sub : m_Queue)
        sub.compactify();

    return result;
}