Example usage for weka.filters.unsupervised.attribute AddExpression setInputFormat

Introduction

In this page you can find the example usage for weka.filters.unsupervised.attribute AddExpression setInputFormat.

Prototype

@Override
public boolean setInputFormat(Instances instanceInfo) throws Exception 

Source Link

Document

Sets the format of the input instances.

Usage

From source file:es.bsc.autonomic.powermodeller.tools.classifiers.WekaWrapper.java

License:Apache License

public static DataSet processDataSet(DataSet ds, VariableParser parser) {

    String independent = ds.getIndependent();

    if (independent == null)
        throw new WekaWrapperException("Independent variable is not set in dataset.");

    HashMap<String, String> expression_list = parser.getNewMetrics();
    Instances data = convertDataSetToInstances(ds);

    try {//from   www .  j a  v  a2 s.c  o m
        // Apply filters for all the new variables
        for (Map.Entry<String, String> entry : expression_list.entrySet()) {
            String key = entry.getKey();
            String value = entry.getValue();
            logger.debug("Generating new variable " + key + " as " + value);

            AddExpression add_filter = new AddExpression();
            add_filter.setName(key);
            add_filter.setExpression(value);
            add_filter.setInputFormat(data);

            data = useFilter(data, add_filter);

        }

    } catch (Exception e) {
        logger.error("Error while processing new variables", e);
        throw new WekaWrapperException("Error while processing new variables");
    }

    // Iterate over all the columns and keep only the ones contained in variables list
    List<String> variables = parser.getColumns();

    // Append independent variable to the list of variables to keep
    variables.add(independent);

    // Remove unneeded attributes
    try {

        // it's important to iterate from last to first, because when we remove
        // an instance, the rest shifts by one position.
        for (int i = data.numAttributes() - 1; i >= 0; i--) {
            String n = data.attribute(i).name();
            if (!variables.contains(data.attribute(i).name())) {
                logger.trace("Deleting unnecessary attribute " + data.attribute(i).name());
                data.deleteAttributeAt(i);
            }
        }

        data.toString();
    } catch (Exception e) {
        logger.error("Error while removing unneeded variables", e);
        throw new WekaWrapperException("Error while removing unneeded variables");
    }

    // Convert Instances in csv and return the new DataSet
    String new_path = CoreConfiguration.getNewCSVFileName();
    try {
        CSVSaver saver = new CSVSaver();
        saver.setInstances(data);
        saver.setFile(new File(new_path));
        saver.writeBatch();
    } catch (Exception e) {
        logger.error("Error while removing unneeded variables", e);
        throw new WekaWrapperException("Error while removing unneeded variables");
    }

    DataSet ret = new DataSet(new_path);
    ret.setIndependent(independent);
    return ret;
}

---