@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());
}
}
}
/**
* The constructor of OrdRecParameter. It use the quantized values of rating to initialize t1
* and beta. Each threshold is initialized as the mean of two contiguous rating values. Since
* the index of quantizer is always an successive non-negative integer begin from 0, so t1 will
* initialize as 0.5, and the interval between two thresholds will be 1.
*
* @param qtz The quantizer for ratings
*/
private OrdRecModel(Quantizer qtz) {
qtzValues = qtz.getValues();
levelCount = qtzValues.length();
t1 = (qtzValues.get(0) + qtzValues.get(1)) / 2;
beta = Vector.createLength(levelCount - 2);
double tr = t1;
for (int i = 1; i <= beta.length(); i++) {
double trnext = (qtzValues.get(i) + qtzValues.get(i + 1)) * 0.5;
beta.set(i - 1, Math.log(trnext - tr));
tr = trnext;
}
}
/** The train function of OrdRec. Get all parameters after learning process. */
@SuppressWarnings("ConstantConditions")
private void train(SparseVector ratings, MutableSparseVector scores) {
Vector dbeta = Vector.createLength(beta.length());
double dt1;
// n is the number of iteration;
for (int j = 0; j < iterationCount; j++) {
for (VectorEntry rating : ratings.fast()) {
long iid = rating.getKey();
double score = scores.get(iid);
int r = quantizer.index(rating.getValue());
double probEqualR = getProbEQ(score, r);
double probLessR = getProbLE(score, r);
double probLessR_1 = getProbLE(score, r - 1);
dt1 =
learningRate
/ probEqualR
* (probLessR * (1 - probLessR) * derivateOfBeta(r, 0, t1)
- probLessR_1 * (1 - probLessR_1) * derivateOfBeta(r - 1, 0, t1)
- regTerm * t1);
double dbetaK;
for (int k = 0; k < beta.length(); k++) {
dbetaK =
learningRate
/ probEqualR
* (probLessR * (1 - probLessR) * derivateOfBeta(r, k + 1, beta.get(k))
- probLessR_1
* (1 - probLessR_1)
* derivateOfBeta(r - 1, k + 1, beta.get(k))
- regTerm * beta.get(k));
dbeta.set(k, dbetaK);
}
t1 = t1 + dt1;
beta.add(dbeta);
}
}
}