public override void SetPreference(long userID, long itemID, float value)
{
IDataModel dataModel = GetDataModel();
double prefDelta;
try {
float?oldPref = dataModel.GetPreferenceValue(userID, itemID);
prefDelta = !oldPref.HasValue ? value : value - oldPref.Value;
} catch (NoSuchUserException nsee) {
prefDelta = value;
}
base.SetPreference(userID, itemID, value);
lock (this) {
//buildAveragesLock.writeLock().lock();
IRunningAverage average = itemAverages.Get(itemID);
if (average == null)
{
IRunningAverage newAverage = new FullRunningAverage();
newAverage.AddDatum(prefDelta);
itemAverages.Put(itemID, newAverage);
}
else
{
average.ChangeDatum(prefDelta);
}
}
//finally {
//buildAveragesLock.writeLock().unlock();
//}
}
public override double GetEvaluation(IDictionary <User, ICollection <Preference> > testUserPrefs,
Recommender recommender)
{
RunningAverage average = new FullRunningAverage();
foreach (KeyValuePair <User, ICollection <Preference> > entry in testUserPrefs)
{
foreach (Preference realPref in entry.Value)
{
User testUser = entry.Key;
try
{
double estimatedPreference =
recommender.EstimatePreference(testUser.ID, realPref.Item.ID);
if (!double.IsNaN(estimatedPreference))
{
double diff = realPref.Value - estimatedPreference;
average.AddDatum(diff * diff);
}
}
catch (NoSuchElementException nsee)
{
// It's possible that an item exists in the test data but not training data in which case
// NSEE will be thrown. Just ignore it and move on.
log.Info("Element exists in test data but not training data: " + testUser.ID, nsee);
}
}
}
return(Math.Sqrt(average.Average));
}
public void toyExample()
{
SVDRecommender svdRecommender = new SVDRecommender(dataModel, factorizer);
/// 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();
while (userIDs.MoveNext())
{
long userID = userIDs.Current;
foreach (IPreference pref in dataModel.GetPreferencesFromUser(userID))
{
double rating = pref.GetValue();
double estimate = svdRecommender.EstimatePreference(userID, pref.GetItemID());
double err = rating - estimate;
avg.AddDatum(err * err);
}
}
double rmse = Math.Sqrt(avg.GetAverage());
Assert.True(rmse < 0.2);
}
public void testRecommenderWithSyntheticData()
{
setUpSyntheticData();
factorizer = new ParallelSGDFactorizer(dataModel, rank, lambda, numIterations, 0.01, 1, 0, 0);
svdRecommender = new SVDRecommender(dataModel, factorizer);
/// 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();
while (userIDs.MoveNext())
{
long userID = userIDs.Current;
foreach (IPreference pref in dataModel.GetPreferencesFromUser(userID))
{
double rating = pref.GetValue();
double estimate = svdRecommender.EstimatePreference(userID, pref.GetItemID());
double err = rating - estimate;
avg.AddDatum(err * err);
}
}
double rmse = Math.Sqrt(avg.GetAverage());
logger.Info("rmse: " + rmse);
Assert.True(rmse < 0.2);
}
public double Estimate(long itemID)
{
IRunningAverage average = new FullRunningAverage();
double[] similarities = similarity.ItemSimilarities(itemID, toItemIDs);
for (int i = 0; i < toItemIDs.Length; i++)
{
long toItemID = toItemIDs[i];
Tuple <long, long> pair = new Tuple <long, long>(toItemID, itemID);
if (rescorer != null && rescorer.IsFiltered(pair))
{
continue;
}
double estimate = similarities[i];
if (rescorer != null)
{
estimate = rescorer.Rescore(pair, estimate);
}
if (excludeItemIfNotSimilarToAll || !Double.IsNaN(estimate))
{
average.AddDatum(estimate);
}
}
double averageEstimate = average.GetAverage();
return(averageEstimate == 0 ? Double.NaN : averageEstimate);
}
public double averateRating(long itemID)
{
IPreferenceArray prefs = dataModel.GetPreferencesForItem(itemID);
IRunningAverage avg = new FullRunningAverage();
foreach (IPreference pref in prefs)
{
avg.AddDatum(pref.GetValue());
}
return(avg.GetAverage());
}
public void toyExampleImplicit()
{
var observations = new double[4, 4] {
{ 5.0, 5.0, 2.0, 0 },
{ 2.0, 0, 3.0, 5.0 },
{ 0, 5.0, 0, 3.0 },
{ 3.0, 0, 0, 5.0 }
};
var preferences = new double[4, 4] {
{ 1.0, 1.0, 1.0, 0 },
{ 1.0, 0, 1.0, 1.0 },
{ 0, 1.0, 0, 1.0 },
{ 1.0, 0, 0, 1.0 }
};
double alpha = 20;
ALSWRFactorizer factorizer = new ALSWRFactorizer(dataModel, 3, 0.065, 5, true, alpha);
SVDRecommender svdRecommender = new SVDRecommender(dataModel, factorizer);
IRunningAverage avg = new FullRunningAverage();
for (int sliceIdx = 0; sliceIdx < preferences.GetLength(0); sliceIdx++)
{
var slice = MatrixUtil.viewRow(preferences, sliceIdx);
for (var eIndex = 0; eIndex < slice.Length; eIndex++)
{
var e = slice[eIndex];
long userID = sliceIdx + 1;
long itemID = eIndex + 1;
if (!Double.IsNaN(e))
{
double pref = e;
double estimate = svdRecommender.EstimatePreference(userID, itemID);
double confidence = 1 + alpha * observations[sliceIdx, eIndex];
double err = confidence * (pref - estimate) * (pref - estimate);
avg.AddDatum(err);
Console.WriteLine("Comparing preference of user [{0}] towards item [{1}], was [{2}] with confidence [{3}] "
+ "estimate is [{4}]", sliceIdx, eIndex, pref, confidence, estimate);
}
}
}
double rmse = Math.Sqrt(avg.GetAverage());
Console.WriteLine("RMSE: {0}", rmse);
Assert.True(rmse < 0.4);
}
double getAveragePreference()
{
IRunningAverage average = new FullRunningAverage();
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
foreach (IPreference pref in dataModel.GetPreferencesFromUser(it.Current))
{
average.AddDatum(pref.GetValue());
}
}
return(average.GetAverage());
}
public double Estimate(Item item)
{
RunningAverage average = new FullRunningAverage();
foreach (User user in cluster)
{
Preference pref = user.GetPreferenceFor(item.ID);
if (pref != null)
{
average.AddDatum(pref.Value);
}
}
return(average.Average);
}
/**
* {@inheritDoc}
*/
public override void SetPreference(Object userID, Object itemID, double value)
{
DataModel dataModel = this.DataModel;
double prefDelta;
try
{
User theUser = dataModel.GetUser(userID);
Preference oldPref = theUser.GetPreferenceFor(itemID);
prefDelta = oldPref == null ? value : value - oldPref.Value;
}
catch (NoSuchElementException)
{
prefDelta = value;
}
base.SetPreference(userID, itemID, value);
buildAveragesLock.AcquireWriterLock(Constants.INFINITE_TIMEOUT);
try
{
RunningAverage itemAverage;
if (!itemAverages.TryGetValue(itemID, out itemAverage) || itemAverage == null)
{
RunningAverage newItemAverage = new FullRunningAverage();
newItemAverage.AddDatum(prefDelta);
itemAverages.Add(itemID, newItemAverage);
}
else
{
itemAverage.ChangeDatum(prefDelta);
}
RunningAverage userAverage;
if (!userAverages.TryGetValue(userID, out userAverage) || userAverage == null)
{
RunningAverage newUserAverage = new FullRunningAverage();
newUserAverage.AddDatum(prefDelta);
userAverages.Add(userID, newUserAverage);
}
else
{
userAverage.ChangeDatum(prefDelta);
}
overallAveragePrefValue.ChangeDatum(prefDelta);
} finally {
buildAveragesLock.ReleaseWriterLock();
}
}
public Double GetValue(User key)
{
RunningAverage average = new FullRunningAverage();
Preference[] prefs = key.GetPreferencesAsArray();
if (prefs.Length == 0)
{
return(0.0);
}
foreach (Preference pref in prefs)
{
average.AddDatum(pref.Value);
}
return(average.Average);
}
public double Estimate(Item item)
{
RunningAverage average = new FullRunningAverage();
foreach (Item toItem in toItems)
{
Pair <Item, Item> pair = new Pair <Item, Item>(toItem, item);
if (rescorer.IsFiltered(pair))
{
continue;
}
double estimate = correlation.GetItemCorrelation(toItem, item);
estimate = rescorer.Rescore(pair, estimate);
average.AddDatum(estimate);
}
return(average.Average);
}
public float Get(long key)
{
IPreferenceArray prefs = inf.dataModel.GetPreferencesFromUser(key);
int size = prefs.Length();
if (size == 0)
{
return(ZERO);
}
IRunningAverage average = new FullRunningAverage();
for (int i = 0; i < size; i++)
{
average.AddDatum(prefs.GetValue(i));
}
return((float)average.GetAverage());
}
public override void SetPreference(Object userID, Object itemID, double value)
{
double prefDelta;
try
{
User theUser = this.DataModel.GetUser(userID);
Preference oldPref = theUser.GetPreferenceFor(itemID);
prefDelta = oldPref == null ? value : value - oldPref.Value;
}
catch
{
prefDelta = value;
}
base.SetPreference(userID, itemID, value);
buildAveragesLock.AcquireWriterLock(Constants.INFINITE_TIMEOUT);
try
{
RunningAverage average = null;
if (!itemAverages.TryGetValue(itemID, out average))
{
RunningAverage newAverage = new FullRunningAverage();
newAverage.AddDatum(prefDelta);
itemAverages.Add(itemID, newAverage);
}
else
{
average.ChangeDatum(prefDelta);
}
}
finally
{
buildAveragesLock.ReleaseWriterLock();
}
}
public IRStatistics Evaluate(RecommenderBuilder recommenderBuilder,
DataModel dataModel,
int at,
double relevanceThreshold,
double evaluationPercentage)
{
if (recommenderBuilder == null)
{
throw new ArgumentNullException("recommenderBuilder is null");
}
if (dataModel == null)
{
throw new ArgumentNullException("dataModel is null");
}
if (at < 1)
{
throw new ArgumentException("at must be at least 1");
}
if (double.IsNaN(evaluationPercentage) || evaluationPercentage <= 0.0 || evaluationPercentage > 1.0)
{
throw new ArgumentException("Invalid evaluationPercentage: " + evaluationPercentage);
}
if (double.IsNaN(relevanceThreshold))
{
throw new ArgumentException("Invalid relevanceThreshold: " + evaluationPercentage);
}
RunningAverage precision = new FullRunningAverage();
RunningAverage recall = new FullRunningAverage();
foreach (User user in dataModel.GetUsers())
{
Object id = user.ID;
if (random.NextDouble() < evaluationPercentage)
{
ICollection <Item> relevantItems = new HashedSet <Item>(/* at */);
Preference[] prefs = user.GetPreferencesAsArray();
foreach (Preference pref in prefs)
{
if (pref.Value >= relevanceThreshold)
{
relevantItems.Add(pref.Item);
}
}
int numRelevantItems = relevantItems.Count;
if (numRelevantItems > 0)
{
ICollection <User> trainingUsers = new List <User>(dataModel.GetNumUsers());
foreach (User user2 in dataModel.GetUsers())
{
if (id.Equals(user2.ID))
{
ICollection <Preference> trainingPrefs = new List <Preference>();
prefs = user2.GetPreferencesAsArray();
foreach (Preference pref in prefs)
{
if (!relevantItems.Contains(pref.Item))
{
trainingPrefs.Add(pref);
}
}
if (trainingPrefs.Count > 0)
{
User trainingUser = new GenericUser <String>(id.ToString(), trainingPrefs);
trainingUsers.Add(trainingUser);
}
}
else
{
trainingUsers.Add(user2);
}
}
DataModel trainingModel = new GenericDataModel(trainingUsers);
Recommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
try
{
trainingModel.GetUser(id);
}
catch (NoSuchElementException)
{
continue; // Oops we excluded all prefs for the user -- just move on
}
int intersectionSize = 0;
foreach (RecommendedItem recommendedItem in recommender.Recommend(id, at))
{
if (relevantItems.Contains(recommendedItem.Item))
{
intersectionSize++;
}
}
precision.AddDatum((double)intersectionSize / (double)at);
recall.AddDatum((double)intersectionSize / (double)numRelevantItems);
}
}
}
return(new IRStatisticsImpl(precision.Average, recall.Average));
}
public IRStatistics Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
IDRescorer rescorer,
int at,
double relevanceThreshold,
double evaluationPercentage)
{
//Preconditions.checkArgument(recommenderBuilder != null, "recommenderBuilder is null");
//Preconditions.checkArgument(dataModel != null, "dataModel is null");
//Preconditions.checkArgument(at >= 1, "at must be at least 1");
//Preconditions.checkArgument(evaluationPercentage > 0.0 && evaluationPercentage <= 1.0,
// "Invalid evaluationPercentage: " + evaluationPercentage + ". Must be: 0.0 < evaluationPercentage <= 1.0");
int numItems = dataModel.GetNumItems();
IRunningAverage precision = new FullRunningAverage();
IRunningAverage recall = new FullRunningAverage();
IRunningAverage fallOut = new FullRunningAverage();
IRunningAverage nDCG = new FullRunningAverage();
int numUsersRecommendedFor = 0;
int numUsersWithRecommendations = 0;
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
if (random.nextDouble() >= evaluationPercentage)
{
// Skipped
continue;
}
var stopWatch = new System.Diagnostics.Stopwatch();
stopWatch.Start();
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
// List some most-preferred items that would count as (most) "relevant" results
double theRelevanceThreshold = Double.IsNaN(relevanceThreshold) ? computeThreshold(prefs) : relevanceThreshold;
FastIDSet relevantItemIDs = dataSplitter.GetRelevantItemsIDs(userID, at, theRelevanceThreshold, dataModel);
int numRelevantItems = relevantItemIDs.Count();
if (numRelevantItems <= 0)
{
continue;
}
FastByIDMap <IPreferenceArray> trainingUsers = new FastByIDMap <IPreferenceArray>(dataModel.GetNumUsers());
var it2 = dataModel.GetUserIDs();
while (it2.MoveNext())
{
dataSplitter.ProcessOtherUser(userID, relevantItemIDs, trainingUsers, it2.Current, dataModel);
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingUsers)
: dataModelBuilder.BuildDataModel(trainingUsers);
try {
trainingModel.GetPreferencesFromUser(userID);
} catch (NoSuchUserException nsee) {
continue; // Oops we excluded all prefs for the user -- just move on
}
int size = numRelevantItems + trainingModel.GetItemIDsFromUser(userID).Count();
if (size < 2 * at)
{
// Really not enough prefs to meaningfully evaluate this user
continue;
}
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
int intersectionSize = 0;
var recommendedItems = recommender.Recommend(userID, at, rescorer);
foreach (IRecommendedItem recommendedItem in recommendedItems)
{
if (relevantItemIDs.Contains(recommendedItem.GetItemID()))
{
intersectionSize++;
}
}
int numRecommendedItems = recommendedItems.Count;
// Precision
if (numRecommendedItems > 0)
{
precision.AddDatum((double)intersectionSize / (double)numRecommendedItems);
}
// Recall
recall.AddDatum((double)intersectionSize / (double)numRelevantItems);
// Fall-out
if (numRelevantItems < size)
{
fallOut.AddDatum((double)(numRecommendedItems - intersectionSize)
/ (double)(numItems - numRelevantItems));
}
// nDCG
// In computing, assume relevant IDs have relevance 1 and others 0
double cumulativeGain = 0.0;
double idealizedGain = 0.0;
for (int i = 0; i < numRecommendedItems; i++)
{
IRecommendedItem item = recommendedItems[i];
double discount = 1.0 / log2(i + 2.0); // Classical formulation says log(i+1), but i is 0-based here
if (relevantItemIDs.Contains(item.GetItemID()))
{
cumulativeGain += discount;
}
// otherwise we're multiplying discount by relevance 0 so it doesn't do anything
// Ideally results would be ordered with all relevant ones first, so this theoretical
// ideal list starts with number of relevant items equal to the total number of relevant items
if (i < numRelevantItems)
{
idealizedGain += discount;
}
}
if (idealizedGain > 0.0)
{
nDCG.AddDatum(cumulativeGain / idealizedGain);
}
// Reach
numUsersRecommendedFor++;
if (numRecommendedItems > 0)
{
numUsersWithRecommendations++;
}
stopWatch.Stop();
log.Info("Evaluated with user {} in {}ms", userID, stopWatch.ElapsedMilliseconds);
log.Info("Precision/recall/fall-out/nDCG/reach: {} / {} / {} / {} / {}",
precision.GetAverage(), recall.GetAverage(), fallOut.GetAverage(), nDCG.GetAverage(),
(double)numUsersWithRecommendations / (double)numUsersRecommendedFor);
}
return(new IRStatisticsImpl(
precision.GetAverage(),
recall.GetAverage(),
fallOut.GetAverage(),
nDCG.GetAverage(),
(double)numUsersWithRecommendations / (double)numUsersRecommendedFor));
}
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);
}