/**
* Generates statistics (used for splitting) based on the
* current position in the tree (as defined by an
* attribute mask).
*
* @return A Vector that contains the available attributes.
* Each attribute's internal statistics array is
* populated with appropriate data. The supplied
* stats array is filled with counts of the number of
* examples that fall into each of the target classes
* at the current position in the tree.
*/
public List<Attribute> generateStats(AttributeMask mask, int[] stats)
{
// First, we fill the stats array - this is not the
// most efficient approach, since we're looping through
// the data several times.
getExampleCounts(mask, DatasetUse.getTrainingExamples(), stats, null);
// Now, we have to go through the attribute mask
// and locate the attributes that are still available.
List<Attribute> results = new List<Attribute>();
// Create a new mask that we can modify.
AttributeMask newMask = new AttributeMask(mask);
// We don't use position 0, that's where the target attribute is.
for (int i = 1; i < mask.getNumAttributes(); i++)
{
if (newMask.isMasked(i) == AttributeMask.UNUSED)
{
// This attribute is available, so we calculate stats for it.
Attribute att = null;
try
{
att = DatasetUse.getAttributeByNum(i);
}
catch (Exception e)
{
// This can't happen!!
return null;
}
int[][] attStats = att.getStatsArray();
// Modify the mask and fill in the arrays.
for (int j = 0; j < att.getNumValues(); j++)
{
newMask.mask(i, j);
getExampleCounts(newMask, DatasetUse.getTrainingExamples(), attStats[j], null);
}
// Reset the mask.
newMask.unmask(i);
results.Add(att);
}
}
return results;
}
