/**
* Sample a dataset
*
* @param numSamples the number of samples to getFromOrigin
* @param rng the rng to use
* @param withReplacement whether to allow duplicates (only tracked by example row number)
* @return the sample dataset
*/
public FloatDataSet sample(int numSamples, RandomGenerator rng, boolean withReplacement) {
if (numSamples >= numExamples()) return this;
else {
FloatMatrix examples = new FloatMatrix(numSamples, getFirst().columns);
FloatMatrix outcomes = new FloatMatrix(numSamples, numOutcomes());
Set<Integer> added = new HashSet<Integer>();
for (int i = 0; i < numSamples; i++) {
int picked = rng.nextInt(numExamples());
if (!withReplacement)
while (added.contains(picked)) {
picked = rng.nextInt(numExamples());
}
examples.putRow(i, get(picked).getFirst());
outcomes.putRow(i, get(picked).getSecond());
}
return new FloatDataSet(examples, outcomes);
}
}
@Test
public void testNextBitSetRandom() {
RandomGenerator random = RandomManager.getRandom();
for (int i = 0; i < 100; i++) {
BitSet bitSet = new BitSet(NUM_BITS);
for (int j = 0; j < 20 + random.nextInt(50); j++) {
bitSet.set(random.nextInt(NUM_BITS));
}
int from = random.nextInt(NUM_BITS);
int nextSet = bitSet.nextSetBit(from);
if (nextSet == -1) {
for (int j = from; j < NUM_BITS; j++) {
assertFalse(bitSet.get(j));
}
} else {
for (int j = from; j < nextSet; j++) {
assertFalse(bitSet.get(j));
}
assertTrue(bitSet.get(nextSet));
}
}
}
@Test
public void testLSHEffect() {
RandomGenerator random = RandomManager.getRandom();
PoissonDistribution itemPerUserDist =
new PoissonDistribution(
random,
20,
PoissonDistribution.DEFAULT_EPSILON,
PoissonDistribution.DEFAULT_MAX_ITERATIONS);
int features = 20;
ALSServingModel mainModel = new ALSServingModel(features, true, 1.0, null);
ALSServingModel lshModel = new ALSServingModel(features, true, 0.5, null);
int userItemCount = 20000;
for (int user = 0; user < userItemCount; user++) {
String userID = "U" + user;
float[] vec = VectorMath.randomVectorF(features, random);
mainModel.setUserVector(userID, vec);
lshModel.setUserVector(userID, vec);
int itemsPerUser = itemPerUserDist.sample();
Collection<String> knownIDs = new ArrayList<>(itemsPerUser);
for (int i = 0; i < itemsPerUser; i++) {
knownIDs.add("I" + random.nextInt(userItemCount));
}
mainModel.addKnownItems(userID, knownIDs);
lshModel.addKnownItems(userID, knownIDs);
}
for (int item = 0; item < userItemCount; item++) {
String itemID = "I" + item;
float[] vec = VectorMath.randomVectorF(features, random);
mainModel.setItemVector(itemID, vec);
lshModel.setItemVector(itemID, vec);
}
int numRecs = 10;
Mean meanMatchLength = new Mean();
for (int user = 0; user < userItemCount; user++) {
String userID = "U" + user;
List<Pair<String, Double>> mainRecs =
mainModel.topN(new DotsFunction(mainModel.getUserVector(userID)), null, numRecs, null);
List<Pair<String, Double>> lshRecs =
lshModel.topN(new DotsFunction(lshModel.getUserVector(userID)), null, numRecs, null);
int i = 0;
while (i < lshRecs.size() && i < mainRecs.size() && lshRecs.get(i).equals(mainRecs.get(i))) {
i++;
}
meanMatchLength.increment(i);
}
log.info("Mean matching prefix: {}", meanMatchLength.getResult());
assertTrue(meanMatchLength.getResult() >= 4.0);
meanMatchLength.clear();
for (int item = 0; item < userItemCount; item++) {
String itemID = "I" + item;
List<Pair<String, Double>> mainRecs =
mainModel.topN(
new CosineAverageFunction(mainModel.getItemVector(itemID)), null, numRecs, null);
List<Pair<String, Double>> lshRecs =
lshModel.topN(
new CosineAverageFunction(lshModel.getItemVector(itemID)), null, numRecs, null);
int i = 0;
while (i < lshRecs.size() && i < mainRecs.size() && lshRecs.get(i).equals(mainRecs.get(i))) {
i++;
}
meanMatchLength.increment(i);
}
log.info("Mean matching prefix: {}", meanMatchLength.getResult());
assertTrue(meanMatchLength.getResult() >= 5.0);
}
