/** Test falling back to an empty user. */
@Test
public void testUserMeanBaselineFallback() {
ItemScorer mean = makeGlobalMean();
ItemScorer pred =
new UserMeanItemScorer(
new PrefetchingUserEventDAO(dao), mean, new RatingVectorUserHistorySummarizer(), 0);
// unseen user - should be global mean
assertThat(pred.score(10, 10), closeTo(RATINGS_DAT_MEAN, 0.001));
}
@Test
public void testItemMeanBaseline() {
ItemScorer pred = new ItemMeanRatingItemScorer.Builder(dao, 0.0).get();
long[] items = {5, 7, 10};
double[] values = {3, 6, 4};
SparseVector map = MutableSparseVector.wrap(items, values).freeze();
// unseen item, should be global mean
assertThat(pred.score(10, 2), closeTo(RATINGS_DAT_MEAN, 0.001));
// seen item - should be item average
assertThat(pred.score(10, 5), closeTo(3.0, 0.001));
}
@Test
public void testUserItemMeanBaseline() {
ItemScorer base = new ItemMeanRatingItemScorer.Builder(dao, 0.0).get();
ItemScorer pred =
new UserMeanItemScorer(
new PrefetchingUserEventDAO(dao), base, new RatingVectorUserHistorySummarizer(), 0);
// we use user 8 - their average offset is 0.5
// unseen item, should be global mean + user offset
assertThat(pred.score(8, 10), closeTo(RATINGS_DAT_MEAN + 0.5, 0.001));
// seen item - should be item average + user offset
assertThat(pred.score(8, 5), closeTo(3.5, 0.001));
}
/**
* Build a rating matrix from the rating data. Each user's ratings are first normalized by
* subtracting a baseline score (usually a mean).
*
* @param userMapping The index mapping of user IDs to column numbers.
* @param itemMapping The index mapping of item IDs to row numbers.
* @return A matrix storing the <i>normalized</i> user ratings.
*/
private RealMatrix createRatingMatrix(IdIndexMapping userMapping, IdIndexMapping itemMapping) {
final int nusers = userMapping.size();
final int nitems = itemMapping.size();
// Create a matrix with users on rows and items on columns
logger.info("creating {} by {} rating matrix", nusers, nitems);
RealMatrix matrix = MatrixUtils.createRealMatrix(nusers, nitems);
// populate it with data
Cursor<UserHistory<Event>> users = userEventDAO.streamEventsByUser();
try {
for (UserHistory<Event> user : users) {
// Get the row number for this user
int u = userMapping.getIndex(user.getUserId());
MutableSparseVector ratings = Ratings.userRatingVector(user.filter(Rating.class));
MutableSparseVector baselines = MutableSparseVector.create(ratings.keySet());
baselineScorer.score(user.getUserId(), baselines);
// TODO Populate this user's row with their ratings, minus the baseline scores
for (VectorEntry entry : ratings.fast(State.SET)) {
long itemid = entry.getKey();
int i = itemMapping.getIndex(itemid);
double rating = entry.getValue();
double baseline = baselines.get(itemid);
matrix.setEntry(u, i, rating - baseline);
}
}
} finally {
users.close();
}
return matrix;
}
@Override
public void predict(long uid, @Nonnull MutableSparseVector predictions) {
logger.debug("predicting {} items for {}", predictions.keyDomain().size(), uid);
OrdRecModel params = new OrdRecModel(quantizer);
SparseVector ratings = makeUserVector(uid, userEventDao);
LongSet keySet = LongUtils.setUnion(ratings.keySet(), predictions.keyDomain());
MutableSparseVector scores = MutableSparseVector.create(keySet);
itemScorer.score(uid, scores);
params.train(ratings, scores);
logger.debug("trained parameters for {}: {}", uid, params);
Vector probabilities = Vector.createLength(params.getLevelCount());
Long2ObjectMap<IVector> distChannel = null;
if (reportDistribution) {
distChannel = predictions.addChannel(RATING_PROBABILITY_CHANNEL);
}
for (VectorEntry e : predictions.fast(VectorEntry.State.EITHER)) {
long iid = e.getKey();
double score = scores.get(iid);
params.getProbDistribution(score, probabilities);
int mlIdx = probabilities.maxElementIndex();
predictions.set(e, quantizer.getIndexValue(mlIdx));
if (distChannel != null) {
distChannel.put(e.getKey(), probabilities.immutable());
}
}
}
private double prediction(long user, long item) {
double baseline = baselineScorer.score(user, item);
try {
RealMatrix userFeature = model.getUserVector(user);
RealMatrix featureWeights = model.getFeatureWeights();
RealMatrix itemFeature = model.getItemVector(item);
double product =
userFeature.multiply(featureWeights).multiply(itemFeature.transpose()).getEntry(0, 0);
return baseline + product;
} catch (NullPointerException npe) {
return baseline;
}
}
@Test
public void testMeanBaseline() {
ItemScorer pred = makeGlobalMean();
SparseVector pv = pred.score(10L, itemSet(2l));
assertEquals(RATINGS_DAT_MEAN, pv.get(2l), 0.00001);
}
