Class DataTransformProcess

JSAT/src/jsat/datatransform/DataTransformProcess.java:25–230

Performing a transform on the whole data set before training a classifier can add bias to the results. For proper evaluation, the transforms must be learned from the training set and not contain any knowledge from the testing set. A DataTransformProcess aids in this by providing a mechanism to conta

 * @author Edward Raff
 */
public class DataTransformProcess implements DataTransform, Parameterized
{

    private static final long serialVersionUID = -2844495690944305885L;
    @ParameterHolder(skipSelfNamePrefix = true)
    private List<DataTransform> transformSource;
    private List<DataTransform> learnedTransforms;


    /**
     * Creates a new transform process that is empty. Transform factories must 
     * be added using 
     * {@link #addTransform(jsat.datatransform.DataTransformFactory) }.
     */
    public DataTransformProcess()
    {
        transformSource = new ArrayList<DataTransform>();
        learnedTransforms = new ArrayList<DataTransform>();   
    }
    
    /**
     * Creates a new transform process from the listed factories, which will be
     * applied in order by index. 
     * 
     * @param transforms the array of factories to apply as the data transform process
     */
    public DataTransformProcess(DataTransform... transforms)
    {
        this();
        for(DataTransform dt : transforms)
            this.addTransform(dt);
    }
    
    /**
     * Adds a transform to the list of transforms. Transforms are learned and 
     * applied in the order in which they are added. 
     * @param transform the factory for the transform to add
     */
    public void addTransform(DataTransform transform)
    {
        transformSource.add(transform);
    }
    
    /**
     * 
     * @return the number of transforms currently chained in this transform 
     * process
     */
    public int getNumberOfTransforms()
    {
        return transformSource.size();
    }
    
    /**
     * Consolidates transformation objects when possible. Currently only works with {@link RemoveAttributeTransform}
     */
    private void consolidateTransforms()
    {