Example usage for weka.attributeSelection AttributeSelection selectAttributesCVSplit

Introduction

In this page you can find the example usage for weka.attributeSelection AttributeSelection selectAttributesCVSplit.

Prototype

public void selectAttributesCVSplit(Instances split) throws Exception 

Source Link

Document

Select attributes for a split of the data.

Usage

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

License:Open Source License

/**
 * Executes the flow item./*w w  w.j  av a 2  s. c  om*/
 *
 * @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;
}

---