private void train()
{
factorization = factorizer.Factorize();
try {
persistenceStrategy.MaybePersist(factorization);
} catch (IOException e) {
throw new TasteException("Error persisting factorization", e);
}
}
public void testFactorizerWithWithSyntheticData()
{
setUpSyntheticData();
var stopWatch = new System.Diagnostics.Stopwatch();
stopWatch.Start();
factorizer = new ParallelSGDFactorizer(dataModel, rank, lambda, numIterations, 0.01, 1, 0, 0);
Factorization factorization = factorizer.Factorize();
stopWatch.Stop();
long duration = stopWatch.ElapsedMilliseconds;
/// a hold out test would be better, but this is just a toy example so we only check that the
/// factorization is close to the original matrix
IRunningAverage avg = new FullRunningAverage();
var userIDs = dataModel.GetUserIDs();
IEnumerator <long> itemIDs;
while (userIDs.MoveNext())
{
long userID = userIDs.Current;
foreach (IPreference pref in dataModel.GetPreferencesFromUser(userID))
{
double rating = pref.GetValue();
var userVector = factorization.getUserFeatures(userID);
var itemVector = factorization.getItemFeatures(pref.GetItemID());
double estimate = vectorDot(userVector, itemVector);
double err = rating - estimate;
avg.AddDatum(err * err);
}
}
double sum = 0.0;
userIDs = dataModel.GetUserIDs();
while (userIDs.MoveNext())
{
long userID = userIDs.Current;
var userVector = factorization.getUserFeatures(userID);
double regularization = vectorDot(userVector, userVector);
sum += regularization;
}
itemIDs = dataModel.GetItemIDs();
while (itemIDs.MoveNext())
{
long itemID = itemIDs.Current;
var itemVector = factorization.getUserFeatures(itemID);
double regularization = vectorDot(itemVector, itemVector);
sum += regularization;
}
double rmse = Math.Sqrt(avg.GetAverage());
double loss = avg.GetAverage() / 2 + lambda / 2 * sum;
logger.Info("RMSE: " + rmse + ";\tLoss: " + loss + ";\tTime Used: " + duration + "ms");
Assert.True(rmse < 0.2);
}
public void testFactorizerWithWithSyntheticData()
{
setUpSyntheticData();
var stopWatch = new System.Diagnostics.Stopwatch();
stopWatch.Start();
factorizer = new ParallelSGDFactorizer(dataModel, rank, lambda, numIterations, 0.01, 1, 0, 0);
Factorization factorization = factorizer.Factorize();
stopWatch.Stop();
long duration = stopWatch.ElapsedMilliseconds;
/// a hold out test would be better, but this is just a toy example so we only check that the
/// factorization is close to the original matrix
IRunningAverage avg = new FullRunningAverage();
var userIDs = dataModel.GetUserIDs();
IEnumerator<long> itemIDs;
while (userIDs.MoveNext()) {
long userID = userIDs.Current;
foreach (IPreference pref in dataModel.GetPreferencesFromUser(userID)) {
double rating = pref.GetValue();
var userVector = factorization.getUserFeatures(userID);
var itemVector = factorization.getItemFeatures(pref.GetItemID());
double estimate = vectorDot( userVector, itemVector);
double err = rating - estimate;
avg.AddDatum(err * err);
}
}
double sum = 0.0;
userIDs = dataModel.GetUserIDs();
while (userIDs.MoveNext()) {
long userID = userIDs.Current;
var userVector = factorization.getUserFeatures(userID);
double regularization = vectorDot( userVector, userVector);
sum += regularization;
}
itemIDs = dataModel.GetItemIDs();
while (itemIDs.MoveNext()) {
long itemID = itemIDs.Current;
var itemVector = factorization.getUserFeatures(itemID);
double regularization = vectorDot( itemVector, itemVector);
sum += regularization;
}
double rmse = Math.Sqrt(avg.GetAverage());
double loss = avg.GetAverage() / 2 + lambda / 2 * sum;
logger.Info("RMSE: " + rmse + ";\tLoss: " + loss + ";\tTime Used: " + duration + "ms");
Assert.True(rmse < 0.2);
}
public override IEnumerable <long> Factorize(long n)
{
// Trivial cases
if (n < 0)
{
throw new ArgumentOutOfRangeException();
}
if (n == 1 || n == 0)
{
return new long[] { }
}
;
if (_memory.Contains(n))
{
return new long[] { n }
}
;
// Remove factors already calculated
var factors = new List <long>();
foreach (var prime in _memory)
{
if (n < _fullySeached && prime * prime > n)
{
break;
}
while (n % prime == 0)
{
factors.Add(prime);
n /= prime;
if (n == 1)
{
break;
}
}
}
if (n == 1)
{
return(factors.AsEnumerable());
}
if (_memory.Contains(n))
{
factors.Add(n);
return(factors.AsEnumerable());
}
// Caculate new factors
var newPrimes = Factorizer.Factorize(n);
_memory.UnionWith(newPrimes);
factors.AddRange(newPrimes);
return(factors.AsEnumerable());
}
