scalebymean.java

MacroWeka扩展了著名数据挖掘工具weka

package chen.macroweka.filters.unsupervised.attribute;

import weka.filters.UnsupervisedFilter;
import weka.filters.Filter;
import weka.core.*;


public class ScaleByMean extends Filter implements UnsupervisedFilter
{
    /**
     * Sets the format of the input instances.
     *
     * @param instanceInfo an Instances object containing the input instance
     *                     structure (any instances contained in the object are ignored - only the
     *                     structure is required).
     * @return true if the outputFormat may be collected immediately
     * @throws Exception if the format couldn't be set successfully
     */
    public boolean setInputFormat(Instances instanceInfo) throws Exception
    {
        super.setInputFormat( instanceInfo );
        setOutputFormat( instanceInfo );
        return true;
    }

    /**
     * Signify that this batch of input to the filter is finished. If
     * the filter requires all instances prior to filtering, output()
     * may now be called to retrieve the filtered instances. Any
     * subsequent instances filtered should be filtered based on setting
     * obtained from the first batch (unless the inputFormat has been
     * re-assigned or new options have been set). This default
     * implementation assumes all instance processing occurs during
     * inputFormat() and input().
     *
     * @return true if there are instances pending output
     * @throws NullPointerException if no input structure has been defined,
     * @throws Exception            if there was a problem finishing the batch.
     */
    public boolean batchFinished() throws Exception
    {
        if (getInputFormat() == null) {
            throw new IllegalStateException("No input instance format defined");
        }

        for (int j=0; j<getInputFormat().numInstances(); ++j) {
            Instance instance = getInputFormat().instance( j );
            double [] values = new double [getInputFormat().numAttributes()];
            values = instance.toDoubleArray();

            for (int i=0; i<getInputFormat().numAttributes(); ++i) {

                AttributeStats as = getInputFormat().attributeStats( i );
                if (as.numericStats != null) {
                    values[i] = values[i] - as.numericStats.mean;
                }
            }
            Instance inst = new Instance( instance.weight(), values );
            inst.setDataset( instance.dataset() );
            push(inst);
        }

        m_NewBatch = true;
        return (numPendingOutput() != 0);
    }

    /**
     * Main method for testing this class.
     *
     * @param argv
     *            should contain arguments to the filter: use -h for help
     */
    public static void main(String[] argv) {
        try {
            if (Utils.getFlag('b', argv)) {
                Filter.batchFilterFile(new ScaleByMean(), argv);
            } else {
                Filter.filterFile(new ScaleByMean(), argv);
            }
        } catch (Exception ex) {
            System.out.println(ex.getMessage());
        }
    }
}