/**
* Find association rules in a database, given the set of frequent itemsets.
*
* @param cacheReader the object used to read from the cache
* @param minSupport the minimum support
* @param minConfidence the minimum confidence
* @return a Vector containing all association rules found
*/
public Vector findAssociations(DBCacheReader cacheReader, float minSupport, float minConfidence) {
min_support = minSupport;
min_confidence = minConfidence;
// create the vector where we'll put the rules
rules = new Vector();
// read from cache supports of frequent itemsets
initializeSupports(cacheReader);
// get the frequent itemsets
Vector frequent = supports.getItemsets();
// generate rules from each frequent itemset
for (int i = 0; i < frequent.size(); i++) {
// get a frequent itemset
Itemset is_frequent = (Itemset) frequent.get(i);
// skip it if it's too small
if (is_frequent.size() <= 1) continue;
// get all possible 1 item consequents
Vector consequents = new Vector(is_frequent.size());
for (int k = 0; k < is_frequent.size(); k++) {
int item = is_frequent.getItem(k);
Itemset is_consequent = new Itemset(1);
is_consequent.addItem(item);
// is_consequent now contains a possible consequent
// verify now that the rule having this consequent
// satisfies our requirements
Itemset is_antecedent = is_frequent.subtract(is_consequent);
float antecedent_support = (float) 0.00001;
try {
antecedent_support = supports.getSupport(is_antecedent);
} catch (SETException e) {
System.err.println("Error geting support from SET!!!\n" + e);
}
float confidence = is_frequent.getSupport() / antecedent_support;
if (confidence >= min_confidence) {
consequents.add(is_consequent);
// we add the rule to our collection if it satisfies
// our conditions
rules.add(
new AssociationRule(
is_antecedent, is_consequent, is_frequent.getSupport(), confidence));
}
}
// call the ap_genrules procedure for generating all rules
// out of this frequent itemset
ap_genrules(is_frequent, consequents);
}
return rules;
}
/**
* It adds a sequence from an array of string that we have to interpret
*
* @param integers
* @param sequenceID
*/
public void addSequence(String[] integers, int sequenceID) {
long timestamp = -1;
Sequence sequence = new Sequence(sequences.size());
sequence.setID(sequenceID);
Itemset itemset = new Itemset();
int inicio = 0;
Map<Item, Boolean> counted = new HashMap<Item, Boolean>();
for (int i = inicio; i < integers.length; i++) {
if (integers[i].codePointAt(0) == '<') { // Timestamp
String value = integers[i].substring(1, integers[i].length() - 1);
timestamp = Long.parseLong(value);
itemset.setTimestamp(timestamp);
} else if (integers[i].equals("-1")) { // end of an itemset
long time = itemset.getTimestamp() + 1;
sequence.addItemset(itemset);
itemset = new Itemset();
itemset.setTimestamp(time);
} else if (integers[i].equals("-2")) { // end of a sequence
sequences.add(sequence);
} else {
// extract the value for an item
Item item = itemFactory.getItem(Integer.parseInt(integers[i]));
if (counted.get(item) == null) {
counted.put(item, Boolean.TRUE);
BitSet appearances = frequentItems.get(item);
if (appearances == null) {
appearances = new BitSet();
frequentItems.put(item, appearances);
}
appearances.set(sequence.getId());
}
itemset.addItem(item);
}
}
}
/**
* This method creates a copy of the sequence and add a given item to the last itemset of the
* sequence. It sets the support of the sequence as the support of the item.
*
* @param prefix the sequence
* @param item the item
* @return the new sequence
*/
private SequentialPattern appendItemToPrefixOfSequence(SequentialPattern prefix, String item) {
SequentialPattern newPrefix = prefix.cloneSequence();
Itemset itemset = newPrefix.get(newPrefix.size() - 1);
itemset.addItem(item);
return newPrefix;
}
/**
* Find association rules in a database, given the set of frequent itemsets and a set of
* restrictions.
*
* @param cacheReader the object used to read from the cache
* @param minSupport the minimum support
* @param minConfidence the minimum confidence
* @param inAntecedent the items that must appear in the antecedent of each rule, if null then
* this constraint is ignored
* @param inConsequent the items that must appear in the consequent of each rule, if null then
* this constraint is ignored
* @param ignored the items that should be ignored, if null then this constraint is ignored
* @param maxAntecedent the maximum number of items that can appear in the antecedent of each
* rule, if 0 then this constraint is ignored
* @param minConsequent the minimum number of items that should appear in the consequent of each
* rule, if 0 then this constraint is ignored
* @return a Vector containing all association rules found
*/
public Vector findAssociations(
DBCacheReader cacheReader,
float minSupport,
float minConfidence,
Itemset inAntecedent,
Itemset inConsequent,
Itemset ignored,
int maxAntecedent,
int minConsequent) {
min_support = minSupport;
min_confidence = minConfidence;
is_in_antecedent = inAntecedent;
is_in_consequent = inConsequent;
is_ignored = ignored;
max_antecedent = maxAntecedent;
min_consequent = minConsequent;
// create the vector where we'll put the rules
rules = new Vector();
// read from cache supports of frequent itemsets
initializeSupports(cacheReader);
// get the frequent itemsets
Vector frequent = supports.getItemsets();
if (frequent.size() == 0) return rules;
// if we need to ignore some items
if (ignored != null) {
// remove all frequent itemsets that contain
// items to be ignored; their subsets that do
// not contain those items will remain
for (int i = 0; i < frequent.size(); i++) {
Itemset is = (Itemset) frequent.get(i);
if (is.doesIntersect(ignored)) {
// replace this element with last, delete last,
// and don't advance index
frequent.set(i, frequent.lastElement());
frequent.remove(frequent.size() - 1);
i--;
}
}
if (frequent.size() == 0) return rules;
}
// if we need to have some items in the antecedent or consequent
if (inAntecedent != null || inConsequent != null) {
// remove frequent itemsets that don't have the
// required items
for (int i = 0; i < frequent.size(); i++) {
Itemset is = (Itemset) frequent.get(i);
if (inAntecedent != null && !inAntecedent.isIncludedIn(is)) {
// replace this element with last, delete last,
// and don't advance index
frequent.set(i, frequent.lastElement());
frequent.remove(frequent.size() - 1);
i--;
} else if (inConsequent != null && !inConsequent.isIncludedIn(is)) {
// replace this element with last, delete last,
// and don't advance index
frequent.set(i, frequent.lastElement());
frequent.remove(frequent.size() - 1);
i--;
}
}
if (frequent.size() == 0) return rules;
}
// generate rules from each frequent itemset
for (int i = 0; i < frequent.size(); i++) {
// get a frequent itemset
Itemset is_frequent = (Itemset) frequent.get(i);
// skip it if it's too small
if (is_frequent.size() <= 1 || is_frequent.size() <= minConsequent) continue;
// get all possible 1 item consequents
Vector consequents = new Vector(is_frequent.size());
for (int k = 0; k < is_frequent.size(); k++) {
int item = is_frequent.getItem(k);
Itemset is_consequent = new Itemset(1);
is_consequent.addItem(item);
// is_consequent now contains a possible consequent
// verify now that the rule having this consequent
// satisfies our requirements
Itemset is_antecedent = is_frequent.subtract(is_consequent);
float antecedent_support = (float) 0.00001;
try {
antecedent_support = supports.getSupport(is_antecedent);
} catch (SETException e) {
System.err.println("Error geting support from SET!!!\n" + e);
}
float confidence = is_frequent.getSupport() / antecedent_support;
if (confidence >= min_confidence) {
consequents.add(is_consequent);
// check whether it also satisfies our constraints
boolean approved = true;
if (approved && is_in_antecedent != null && !is_in_antecedent.isIncludedIn(is_antecedent))
approved = false;
if (approved && is_in_consequent != null && !is_in_consequent.isIncludedIn(is_consequent))
approved = false;
if (approved && max_antecedent > 0 && is_antecedent.size() > max_antecedent)
approved = false;
if (approved && min_consequent > 0 && is_consequent.size() < min_consequent)
approved = false;
// if the rule satisifes all requirements then
// we add it to the rules collection
if (approved)
rules.add(
new AssociationRule(
is_antecedent, is_consequent, is_frequent.getSupport(), confidence));
}
}
// call the ap-genrules procedure for generating all rules
// out of this frequent itemset
ap_genrules_constraint(is_frequent, consequents);
}
return rules;
}