public void testExactSizeMatch()
{
SamplinglongPrimitiveIterator t = new SamplinglongPrimitiveIterator(
countingIterator(10), 1);
for (int i = 0; i < 10; i++) {
Assert.True(t.MoveNext());
Assert.AreEqual(i, (int)t.Current );
}
Assert.False(t.MoveNext());
}
public override long[] GetUserNeighborhood(long userID)
{
IDataModel dataModel = getDataModel();
IUserSimilarity userSimilarityImpl = getUserSimilarity();
TopItems.IEstimator <long> estimator = new Estimator(userSimilarityImpl, userID, minSimilarity);
var userIDs = SamplinglongPrimitiveIterator.MaybeWrapIterator(dataModel.GetUserIDs(),
getSamplingRate());
return(TopItems.GetTopUsers(n, userIDs, null, estimator));
}
private void addSomeOf(FastIDSet possibleItemIDs, FastIDSet itemIDs)
{
if (itemIDs.Count() > maxItemsPerUser)
{
var it =
new SamplinglongPrimitiveIterator(itemIDs.GetEnumerator(), (double)maxItemsPerUser / itemIDs.Count());
while (it.MoveNext())
{
possibleItemIDs.Add(it.Current);
}
}
else
{
possibleItemIDs.AddAll(itemIDs);
}
}
public void testSample()
{
double p = 0.1;
int n = 1000;
double sd = Math.Sqrt(n * p * (1.0 - p));
for (int i = 0; i < 1000; i++) {
SamplinglongPrimitiveIterator t = new SamplinglongPrimitiveIterator(countingIterator(n), p);
int k = 0;
while (t.MoveNext()) {
long v = t.Current;
k++;
Assert.True(v >= 0L);
Assert.True(v < 1000L);
}
// Should be +/- 5 standard deviations except in about 1 out of 1.7M cases
Assert.True(k >= 100 - 5 * sd);
Assert.True(k <= 100 + 5 * sd);
}
}
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel)
{
var preferredItemIDsIterator = ((IEnumerable <long>)preferredItemIDs).GetEnumerator();
if (preferredItemIDs.Length > maxItems)
{
double samplingRate = (double)maxItems / preferredItemIDs.Length;
log.Info("preferredItemIDs.Length {0}, samplingRate {1}", preferredItemIDs.Length, samplingRate);
preferredItemIDsIterator =
new SamplinglongPrimitiveIterator(preferredItemIDsIterator, samplingRate);
}
FastIDSet possibleItemsIDs = new FastIDSet();
while (preferredItemIDsIterator.MoveNext())
{
long itemID = preferredItemIDsIterator.Current;
IPreferenceArray prefs = dataModel.GetPreferencesForItem(itemID);
int prefsLength = prefs.Length();
if (prefsLength > maxUsersPerItem)
{
var sampledPrefs =
new FixedSizeSamplingIterator <IPreference>(maxUsersPerItem, prefs.GetEnumerator());
while (sampledPrefs.MoveNext())
{
addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(sampledPrefs.Current.GetUserID()));
}
}
else
{
for (int i = 0; i < prefsLength; i++)
{
addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(prefs.GetUserID(i)));
}
}
}
possibleItemsIDs.RemoveAll(preferredItemIDs);
return(possibleItemsIDs);
}
public override long[] GetUserNeighborhood(long userID)
{
IDataModel dataModel = getDataModel();
FastIDSet neighborhood = new FastIDSet();
var usersIterable = SamplinglongPrimitiveIterator.MaybeWrapIterator(dataModel
.GetUserIDs(), getSamplingRate());
IUserSimilarity userSimilarityImpl = getUserSimilarity();
while (usersIterable.MoveNext())
{
long otherUserID = usersIterable.Current;
if (userID != otherUserID)
{
double theSimilarity = userSimilarityImpl.UserSimilarity(userID, otherUserID);
if (!Double.IsNaN(theSimilarity) && theSimilarity >= threshold)
{
neighborhood.Add(otherUserID);
}
}
}
return(neighborhood.ToArray());
}
public static LoadStatistics runLoad(IRecommender recommender, int howMany)
{
IDataModel dataModel = recommender.GetDataModel();
int numUsers = dataModel.GetNumUsers();
double sampleRate = 1000.0 / numUsers;
var userSampler =
SamplinglongPrimitiveIterator.MaybeWrapIterator(dataModel.GetUserIDs(), sampleRate);
if (userSampler.MoveNext())
{
recommender.Recommend(userSampler.Current, howMany); // Warm up
}
var callables = new List <Action>();
while (userSampler.MoveNext())
{
callables.Add(new LoadCallable(recommender, userSampler.Current).call);
}
AtomicInteger noEstimateCounter = new AtomicInteger();
IRunningAverageAndStdDev timing = new FullRunningAverageAndStdDev();
AbstractDifferenceRecommenderEvaluator.execute(callables, noEstimateCounter, timing);
return(new LoadStatistics(timing));
}
private void addSomeOf(FastIDSet possibleItemIDs, FastIDSet itemIDs) {
if (itemIDs.Count() > maxItemsPerUser) {
var it =
new SamplinglongPrimitiveIterator(itemIDs.GetEnumerator(), (double) maxItemsPerUser / itemIDs.Count() );
while (it.MoveNext()) {
possibleItemIDs.Add(it.Current);
}
} else {
possibleItemIDs.AddAll(itemIDs);
}
}
protected override FastIDSet doGetCandidateItems(long[] preferredItemIDs, IDataModel dataModel) {
var preferredItemIDsIterator = ((IEnumerable<long>)preferredItemIDs).GetEnumerator();
if (preferredItemIDs.Length > maxItems) {
double samplingRate = (double) maxItems / preferredItemIDs.Length;
log.Info("preferredItemIDs.Length {0}, samplingRate {1}", preferredItemIDs.Length, samplingRate);
preferredItemIDsIterator =
new SamplinglongPrimitiveIterator(preferredItemIDsIterator, samplingRate);
}
FastIDSet possibleItemsIDs = new FastIDSet();
while (preferredItemIDsIterator.MoveNext()) {
long itemID = preferredItemIDsIterator.Current;
IPreferenceArray prefs = dataModel.GetPreferencesForItem(itemID);
int prefsLength = prefs.Length();
if (prefsLength > maxUsersPerItem) {
var sampledPrefs =
new FixedSizeSamplingIterator<IPreference>(maxUsersPerItem, prefs.GetEnumerator());
while (sampledPrefs.MoveNext()) {
addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(sampledPrefs.Current.GetUserID()));
}
} else {
for (int i = 0; i < prefsLength; i++) {
addSomeOf(possibleItemsIDs, dataModel.GetItemIDsFromUser(prefs.GetUserID(i)));
}
}
}
possibleItemsIDs.RemoveAll(preferredItemIDs);
return possibleItemsIDs;
}
public void testSmallInput()
{
SamplinglongPrimitiveIterator t = new SamplinglongPrimitiveIterator(
countingIterator(1), 0.9999);
Assert.True(t.MoveNext());
Assert.AreEqual(0L, t.Current);
Assert.False(t.MoveNext());
}
