/**
* Method that finds all association rules.
*
* @exception Exception if an attribute is numeric
*/
private void findRulesQuickly() throws Exception {
FastVector[] rules;
RuleGeneration currentItemSet;
// Build rules
for (int j = 0; j < m_Ls.size(); j++) {
FastVector currentItemSets = (FastVector) m_Ls.elementAt(j);
Enumeration enumItemSets = currentItemSets.elements();
while (enumItemSets.hasMoreElements()) {
currentItemSet = new RuleGeneration((ItemSet) enumItemSets.nextElement());
m_best =
currentItemSet.generateRules(
m_numRules, m_midPoints, m_priors, m_expectation, m_instances, m_best, m_count);
m_count = currentItemSet.m_count;
if (!m_bestChanged && currentItemSet.m_change) m_bestChanged = true;
// update minimum expected predictive accuracy to get into the n best
if (m_best.size() > 0) m_expectation = ((RuleItem) m_best.first()).accuracy();
else m_expectation = 0;
}
}
}
/**
* Method that generates all large itemsets with a minimum support, and from these all association
* rules.
*
* @param instances the instances to be used for generating the associations
* @exception Exception if rules can't be built successfully
*/
public void buildAssociations(Instances instances) throws Exception {
int temp = m_premiseCount, exactNumber = m_numRules - 5;
if (instances.checkForStringAttributes()) {
throw new Exception("Can't handle string attributes!");
}
m_instances = instances;
m_instances.setClassIndex(m_instances.numAttributes() - 1);
// prior estimation
m_priorEstimator = new PriorEstimation(m_instances, m_numRandRules, m_numIntervals, false);
m_priors = m_priorEstimator.estimatePrior();
m_midPoints = m_priorEstimator.getMidPoints();
m_Ls = new FastVector();
m_hashtables = new FastVector();
for (int i = 1; i < m_instances.numAttributes(); i++) {
m_bestChanged = false;
// find large item sets
findLargeItemSets(i);
// find association rules (rule generation procedure)
findRulesQuickly();
if (m_bestChanged) {
temp = m_premiseCount;
while (RuleGeneration.expectation(m_premiseCount, m_premiseCount, m_midPoints, m_priors)
<= m_expectation) {
m_premiseCount++;
if (m_premiseCount > m_instances.numInstances()) break;
}
}
if (m_premiseCount > m_instances.numInstances()) {
// Reserve space for variables
m_allTheRules = new FastVector[3];
m_allTheRules[0] = new FastVector();
m_allTheRules[1] = new FastVector();
m_allTheRules[2] = new FastVector();
int k = 0;
while (m_best.size() > 0 && exactNumber > 0) {
m_allTheRules[0].insertElementAt((ItemSet) ((RuleItem) m_best.last()).premise(), k);
m_allTheRules[1].insertElementAt((ItemSet) ((RuleItem) m_best.last()).consequence(), k);
m_allTheRules[2].insertElementAt(new Double(((RuleItem) m_best.last()).accuracy()), k);
boolean remove = m_best.remove(m_best.last());
k++;
exactNumber--;
}
return;
}
if (temp != m_premiseCount && m_Ls.size() > 0) {
FastVector kSets = (FastVector) m_Ls.lastElement();
m_Ls.removeElementAt(m_Ls.size() - 1);
kSets = ItemSet.deleteItemSets(kSets, m_premiseCount, Integer.MAX_VALUE);
m_Ls.addElement(kSets);
}
}
// Reserve space for variables
m_allTheRules = new FastVector[3];
m_allTheRules[0] = new FastVector();
m_allTheRules[1] = new FastVector();
m_allTheRules[2] = new FastVector();
int k = 0;
while (m_best.size() > 0 && exactNumber > 0) {
m_allTheRules[0].insertElementAt((ItemSet) ((RuleItem) m_best.last()).premise(), k);
m_allTheRules[1].insertElementAt((ItemSet) ((RuleItem) m_best.last()).consequence(), k);
m_allTheRules[2].insertElementAt(new Double(((RuleItem) m_best.last()).accuracy()), k);
boolean remove = m_best.remove(m_best.last());
k++;
exactNumber--;
}
}
