/**
* An implementation of the recursive decision tree
* learning algorithm. Given a parent node and an arc
* number, the method will attach a new decision 'sub'-tree
* below the parent node.
*
* @param parent The parent node for the new decision tree.
*
* @param arcNum The arc number (or path) along which the
* new subtree will be attached.
*
* @return true if an entire subtree was successfully added,
* false otherwise.
*/
public bool learnDT(DecisionTreeNode parent, int arcNum)
{
AttributeMask mask;
if (parent == null)
{
// We have to add at the root.
mask = new AttributeMask(DatasetUse.getNumAttributes());
}
else
{
mask = new AttributeMask(parent.getMask());
// Mask off the specified arc number.
try
{
mask.mask(DatasetUse.getAttributePosition(parent.getLabel()), arcNum);
}
catch (Exception e)
{
//e.printStackTrace();
return false;
}
}
// Now, classify the examples at the current position.
int[] conclusion = new int[8];
int result = classifyExamples(mask, conclusion, null, null, null);
Attribute target = DatasetUse.getTargetAttribute();
int numTargetVals = target.getNumValues();
String label;
if (result == DATASET_EMPTY)
{
// If no examples reach our current position
// we add a leaf with the most common target
// classfication for the parent node.
// Save testing results.
int numTestingExamplesReachHere = conclusion[5];
int bestTestingTargetIndex = conclusion[4];
int numTestingExamplesCorrectClass = conclusion[6];
int numTrainingExamplesCorrectClass = conclusion[7];
classifyExamples(parent.getMask(), conclusion, null, null, null);
try
{
label = target.getAttributeValueByNum(conclusion[0]);
}
catch (Exception e)
{
return false;
}
// We have to grab the counts again for the testing data...
int[] currTestingCounts = new int[target.getNumValues()];
getExampleCounts(mask, DatasetUse.getTestingExamples(), currTestingCounts, null);
// Mask target value and add a leaf to the tree.
mask.mask(0, conclusion[0]);
DecisionTreeNode node = Tree.addLeafNode(parent,
arcNum,
label,
mask,
0,
conclusion[0],
0,
currTestingCounts[conclusion[0]],
numTestingExamplesReachHere,
bestTestingTargetIndex,
numTestingExamplesCorrectClass,
numTrainingExamplesCorrectClass);
return true;
}
if (result == DATASET_IDENT_CONCL)
{
// Pure result - we can add a leaf node with the
// correct target attribute value.
try
{
label = target.getAttributeValueByNum(conclusion[0]);
}
catch (Exception e)
{
//e.printStackTrace();
return false;
}
// Mask target value and add a leaf to the tree.
mask.mask(0, conclusion[0]);
DecisionTreeNode node = Tree.addLeafNode(parent,
arcNum,
label,
mask,
conclusion[1],
conclusion[0],
conclusion[2],
conclusion[3],
conclusion[5],
conclusion[4],
conclusion[6],
conclusion[7]);
return true;
}
// Mixed conclusion - so we have to select
// an attribute to split on, and then build a
// new internal node with that attribute.
// First, generate statistics - this may take awhile.
int[] nodeStats = new int[numTargetVals];
List<Attribute> availableAtts = generateStats(mask, nodeStats);
if (availableAtts.Count == 0)
{
// No attributes left to split on - so use
// the most common target value at the current position.
try
{
label = target.getAttributeValueByNum(conclusion[0]);
}
catch (Exception e)
{
//e.printStackTrace();
return false;
}
mask.mask(0, conclusion[0]);
DecisionTreeNode node = Tree.addLeafNode(parent,
arcNum,
label,
mask,
conclusion[1],
conclusion[0],
conclusion[2],
conclusion[3],
conclusion[5],
conclusion[4],
conclusion[6],
conclusion[7]);
return true;
}
// Choose an attribute, based on the set of
// available attributes.
List<double> results = new List<double>();
Attribute att = chooseAttribute(availableAtts, nodeStats, results);
int attPos;
try
{
attPos = DatasetUse.getAttributePosition(att.getName());
}
catch (Exception e)
{
//e.printStackTrace();
return false;
}
DecisionTreeNode newParent = Tree.addInternalNode(parent,
arcNum,
attPos,
att,
mask,
conclusion[1],
conclusion[0],
conclusion[2],
conclusion[3],
conclusion[5],
conclusion[4],
conclusion[6],
conclusion[7]);
// Now, recursively decend along each branch of the new node.
for (int j = 0; j < newParent.getArcLabelCount(); j++)
{
// Recursive call.
if (!learnDT(newParent, j)) return false;
}
return true;
}
/**
* 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;
}
