@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());
}
}
}
@Override
public double similarity(SparseVector vec1, SparseVector vec2) {
final double distance;
// One of the vector is empty
if (Scalars.isZero(vec1.norm()) || Scalars.isZero(vec2.norm())) {
return Double.NaN;
}
LongSet ts = LongUtils.setUnion(vec1.keySet(), vec2.keySet());
MutableSparseVector v1 = MutableSparseVector.create(ts);
v1.fill(0);
v1.set(vec1);
v1.multiply(1.0 / v1.norm());
v1.addScaled(vec2, -1.0 / vec2.norm());
distance = v1.norm();
return 1 - distance;
}
@Override
public boolean equals(Object o) {
if (this == o) {
return true;
} else if (o instanceof SparseVector) {
SparseVector vo = (SparseVector) o;
int sz = size();
int osz = vo.size();
if (sz != osz) {
return false;
} else {
if (!this.keySet().equals(vo.keySet())) {
return false; // same keys
}
// we know that sparse vector values are always in key order. so just compare them.
return this.values().equals(vo.values());
}
} else {
return false;
}
}
@Override
public LongSet keySet() {
return vector.keySet();
}