// Generate C(k+1) by join itemset-pairs in F(k)
private static List<Itemset> generateCandidates(List<Itemset> frequentItemsets) {
if (frequentItemsets.isEmpty() || frequentItemsets.size() == 1) {
return new ArrayList<>();
}
Collections.sort(frequentItemsets);
List<Itemset> candidates = new ArrayList<>();
Itemset candidate;
for (int i = 0, j = 1; i != frequentItemsets.size(); ) {
while (j != frequentItemsets.size()
&& Itemset.generateCandidate(frequentItemsets.get(i), frequentItemsets.get(j)) != null) {
++j;
}
for (int k = i; k != j; ++k) {
for (int l = k + 1; l != j; ++l) {
Itemset itemset =
(Itemset.generateCandidate(frequentItemsets.get(k), frequentItemsets.get(l)));
assert itemset != null;
candidates.add(itemset);
}
}
i = j;
j++;
}
return candidates;
}
// Prune itemsets from C(k+1) that violate downward closure
private static List<Itemset> prune(List<Itemset> candidates, List<Itemset> frequentItemsets) {
List<Itemset> prunedCandicates = new ArrayList<>();
for (Itemset candidate : candidates) {
if (frequentItemsets.containsAll(candidate.downwardClosure())) {
prunedCandicates.add(candidate);
}
}
return prunedCandicates;
}
/**
* 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);
}
}
}
/**
* Add a new row to the database. If this is to be the first row added to the database you must
* have called setColumnNames() before.
*
* @param itemset the new row to be added to the data file
* @exception IOException from library call
* @exception DBException column names have not been set or an invalid item was contained in the
* itemset
*/
public void addRow(Itemset itemset) throws IOException, DBException {
if (wroteColumnNames == false) throw new DBException("Column names must be set first");
int size = itemset.size();
for (int i = 0; i < size; i++)
if (itemset.get(i) > numColumns) throw new DBException("Attempt to write invalid item");
if (needReposition == true) {
outStream.seek(lastPosition);
needReposition = false;
}
outStream.writeInt(size);
CRC = updateCRC(CRC, size);
int item;
for (int i = 0; i < size; i++) {
item = itemset.get(i);
outStream.writeInt(item);
CRC = updateCRC(CRC, item);
}
numRows++;
}
/** sample usage and testing */
public static void main(String[] args) {
Itemset is1 = new Itemset();
is1.add(1);
is1.add(2);
Itemset is2 = new Itemset();
is2.add(3);
is2.add(2);
Itemset is3 = new Itemset();
is3.add(3);
is3.add(1);
Itemset is4 = new Itemset();
is4.add(33);
is4.add(3);
ArrayList colNames = new ArrayList(3);
colNames.add("cheese");
colNames.add("pizza");
colNames.add("beer");
System.out.println("\n\nCreating invalid database:");
try {
RandomAccessFile invalid = new RandomAccessFile("invalid.db", "rw");
invalid.writeChars(ID + " - a bogus file that looks like a valid one");
invalid.close();
} catch (Exception e) {
System.out.println("Shouldn't have happened: " + e);
}
System.out.println("\n\nCreating corrupted database:");
try {
DBWriter corrupted = new DBWriter("corrupted.db");
try {
corrupted.addRow(is1);
} catch (DBException e) {
System.out.println(e);
}
corrupted.setDescription("a corrupted database");
corrupted.setColumnNames(colNames);
corrupted.addRow(is1);
corrupted.setDescription("a corrupted database - 2");
corrupted.setColumnNames(colNames);
corrupted.addRow(is2);
corrupted.setDescription("a corrupted database - 3");
corrupted.addRow(is3);
try {
corrupted.addRow(is4);
} catch (DBException e) {
System.out.println(e);
}
corrupted.close();
System.out.println("corrupting file");
RandomAccessFile raf = new RandomAccessFile("corrupted.db", "rw");
raf.seek(770);
// replace the 2 in the second itemset with a 3
raf.writeInt(3);
raf.close();
} catch (Exception e) {
System.out.println("Shouldn't have happened: " + e);
}
System.out.println("\n\nCreating empty database:");
try {
DBWriter empty = new DBWriter("empty.db");
empty.setDescription("an empty database");
empty.setColumnNames(colNames);
empty.close();
} catch (Exception e) {
System.out.println("Shouldn't have happened: " + e);
}
System.out.println("\n\nCreating correct database:");
try {
DBWriter correct = new DBWriter("correct.db");
correct.setDescription("a correct database");
correct.setColumnNames(colNames);
correct.addRow(is1);
correct.setDescription("a correct database - 2");
correct.setColumnNames(colNames);
correct.addRow(is2);
correct.setDescription("a correct database - 3");
correct.addRow(is3);
correct.close();
correct = new DBWriter("correct.db");
correct.setColumnNames(colNames);
correct.addRow(is1);
correct.setDescription("a correct database - 4");
correct.setColumnNames(colNames);
correct.addRow(is2);
correct.setDescription("a correct database - 5");
correct.addRow(is3);
correct.close();
} catch (Exception e) {
System.out.println("Shouldn't have happened: " + e);
}
System.out.println("\n\nOpening and closing DBWriter:");
try {
DBWriter bummer = new DBWriter("bummer.db");
bummer.close();
} catch (Exception e) {
System.out.println("Shouldn't have happened: " + e);
}
}
