public virtual IEnumerator <long> GetUserIDs()
{
if (tempPrefs == null)
{
return(_delegate.GetUserIDs());
}
return(new PlusAnonymousUserlongPrimitiveIterator(_delegate.GetUserIDs(), TEMP_USER_ID));
}
private int countPreferences()
{
int numPreferences = 0;
var userIDs = dataModel.GetUserIDs();
while (userIDs.MoveNext())
{
IPreferenceArray preferencesFromUser = dataModel.GetPreferencesFromUser(userIDs.Current);
numPreferences += preferencesFromUser.Length();
}
return(numPreferences);
}
public RandomRecommender(IDataModel dataModel) : base(dataModel)
{
float maxPref = float.NegativeInfinity;
float minPref = float.PositiveInfinity;
var userIterator = dataModel.GetUserIDs();
while (userIterator.MoveNext())
{
long userID = userIterator.Current;
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
for (int i = 0; i < prefs.Length(); i++)
{
float prefValue = prefs.GetValue(i);
if (prefValue < minPref)
{
minPref = prefValue;
}
if (prefValue > maxPref)
{
maxPref = prefValue;
}
}
}
this.minPref = minPref;
this.maxPref = maxPref;
}
private void buildAverageDiffs()
{
lock (this) {
//buildAveragesLock.writeLock().lock();
IDataModel dataModel = GetDataModel();
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(it.Current);
int size = prefs.Length();
for (int i = 0; i < size; i++)
{
long itemID = prefs.GetItemID(i);
IRunningAverage average = itemAverages.Get(itemID);
if (average == null)
{
average = new FullRunningAverage();
itemAverages.Put(itemID, average);
}
average.AddDatum(prefs.GetValue(i));
}
}
}
//finally {
//buildAveragesLock.writeLock().unlock();
//}
}
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 static void Evaluate(IDataModel model1,
IDataModel model2,
int samples,
IRunningAverage tracker,
String tag)
{
printHeader();
var users = model1.GetUserIDs();
while (users.MoveNext())
{
long userID = users.Current;
IPreferenceArray prefs1 = model1.GetPreferencesFromUser(userID);
IPreferenceArray prefs2 = model2.GetPreferencesFromUser(userID);
prefs1.SortByValueReversed();
prefs2.SortByValueReversed();
FastIDSet commonSet = new FastIDSet();
long maxItemID = setBits(commonSet, prefs1, samples);
FastIDSet otherSet = new FastIDSet();
maxItemID = Math.Max(maxItemID, setBits(otherSet, prefs2, samples));
int max = mask(commonSet, otherSet, maxItemID);
max = Math.Min(max, samples);
if (max < 2)
{
continue;
}
long[] items1 = getCommonItems(commonSet, prefs1, max);
long[] items2 = getCommonItems(commonSet, prefs2, max);
double variance = scoreCommonSubset(tag, userID, samples, max, items1, items2);
tracker.AddDatum(variance);
}
}
public GenericUserSimilarity(IUserSimilarity otherSimilarity,
IDataModel dataModel,
int maxToKeep)
{
long[] userIDs = longIteratorToList(dataModel.GetUserIDs());
IEnumerator <UserUserSimilarity> it = new DataModelSimilaritiesIterator(otherSimilarity, userIDs);
var keptSimilarities = TopItems.GetTopUserUserSimilarities(maxToKeep, it);
initSimilarityMaps(keptSimilarities.GetEnumerator());
}
/// Exports the simple user IDs and associated item IDs in the data model.
///
/// @return a {@link FastByIDMap} mapping user IDs to {@link FastIDSet}s representing
/// that user's associated items
public static FastByIDMap <FastIDSet> toDataMap(IDataModel dataModel)
{
FastByIDMap <FastIDSet> data = new FastByIDMap <FastIDSet>(dataModel.GetNumUsers());
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
data.Put(userID, dataModel.GetItemIDsFromUser(userID));
}
return(data);
}
/// <summary>Exports the simple user IDs and preferences in the data model.</summary>
/// <returns>a <see cref="FastByIDMap"/> mapping user IDs to <see cref="IPreferenceArray"/>s representing that user's preferences</returns>
public static FastByIDMap <IPreferenceArray> ToDataMap(IDataModel dataModel)
{
FastByIDMap <IPreferenceArray> data = new FastByIDMap <IPreferenceArray>(dataModel.GetNumUsers());
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
data.Put(userID, dataModel.GetPreferencesFromUser(userID));
}
return(data);
}
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));
}
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());
}
private void cachePreferences(IDataModel dataModel)
{
int numPreferences = countPreferences(dataModel);
preferences = new IPreference[numPreferences];
var userIDs = dataModel.GetUserIDs();
int index = 0;
while (userIDs.MoveNext())
{
long userID = userIDs.Current;
IPreferenceArray preferencesFromUser = dataModel.GetPreferencesFromUser(userID);
foreach (IPreference preference in preferencesFromUser)
{
preferences[index++] = preference;
}
}
}
public virtual double Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
double trainingPercentage,
double evaluationPercentage)
{
//Preconditions.checkNotNull(recommenderBuilder);
//Preconditions.checkNotNull(dataModel);
//Preconditions.checkArgument(trainingPercentage >= 0.0 && trainingPercentage <= 1.0,
// "Invalid trainingPercentage: " + trainingPercentage + ". Must be: 0.0 <= trainingPercentage <= 1.0");
//Preconditions.checkArgument(evaluationPercentage >= 0.0 && evaluationPercentage <= 1.0,
// "Invalid evaluationPercentage: " + evaluationPercentage + ". Must be: 0.0 <= evaluationPercentage <= 1.0");
log.Info("Beginning evaluation using {} of {}", trainingPercentage, dataModel);
int numUsers = dataModel.GetNumUsers();
FastByIDMap <IPreferenceArray> trainingPrefs = new FastByIDMap <IPreferenceArray>(
1 + (int)(evaluationPercentage * numUsers));
FastByIDMap <IPreferenceArray> testPrefs = new FastByIDMap <IPreferenceArray>(
1 + (int)(evaluationPercentage * numUsers));
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
if (random.nextDouble() < evaluationPercentage)
{
splitOneUsersPrefs(trainingPercentage, trainingPrefs, testPrefs, userID, dataModel);
}
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingPrefs)
: dataModelBuilder.BuildDataModel(trainingPrefs);
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
double result = getEvaluation(testPrefs, recommender);
log.Info("Evaluation result: {}", result);
return(result);
}
public RandomRecommender(IDataModel dataModel) : base(dataModel) {
float maxPref = float.NegativeInfinity;
float minPref = float.PositiveInfinity;
var userIterator = dataModel.GetUserIDs();
while (userIterator.MoveNext()) {
long userID = userIterator.Current;
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
for (int i = 0; i < prefs.Length(); i++) {
float prefValue = prefs.GetValue(i);
if (prefValue < minPref) {
minPref = prefValue;
}
if (prefValue > maxPref) {
maxPref = prefValue;
}
}
}
this.minPref = minPref;
this.maxPref = maxPref;
}
public void testPreferenceShufflerWithSyntheticData()
{
setUpSyntheticData();
ParallelSGDFactorizer.PreferenceShuffler shuffler = new ParallelSGDFactorizer.PreferenceShuffler(dataModel);
shuffler.shuffle();
shuffler.stage();
FastByIDMap <FastByIDMap <bool?> > checkedLst = new FastByIDMap <FastByIDMap <bool?> >();
for (int i = 0; i < shuffler.size(); i++)
{
IPreference pref = shuffler.get(i);
float?value = dataModel.GetPreferenceValue(pref.GetUserID(), pref.GetItemID());
Assert.AreEqual(pref.GetValue(), value.Value, 0.0);
if (!checkedLst.ContainsKey(pref.GetUserID()))
{
checkedLst.Put(pref.GetUserID(), new FastByIDMap <bool?>());
}
Assert.IsNull(checkedLst.Get(pref.GetUserID()).Get(pref.GetItemID()));
checkedLst.Get(pref.GetUserID()).Put(pref.GetItemID(), true);
}
var userIDs = dataModel.GetUserIDs();
int index = 0;
while (userIDs.MoveNext())
{
long userID = userIDs.Current;
IPreferenceArray preferencesFromUser = dataModel.GetPreferencesFromUser(userID);
foreach (IPreference preference in preferencesFromUser)
{
Assert.True(checkedLst.Get(preference.GetUserID()).Get(preference.GetItemID()).Value);
index++;
}
}
Assert.AreEqual(index, shuffler.size());
}
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 buildAverageDiffs()
{
lock (this) {
//buildAveragesLock.writeLock().lock();
IDataModel dataModel = GetDataModel();
var it = dataModel.GetUserIDs();
while (it.MoveNext())
{
long userID = it.Current;
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
int size = prefs.Length();
for (int i = 0; i < size; i++)
{
long itemID = prefs.GetItemID(i);
float value = prefs.GetValue(i);
addDatumAndCreateIfNeeded(itemID, value, itemAverages);
addDatumAndCreateIfNeeded(userID, value, userAverages);
overallAveragePrefValue.AddDatum(value);
}
}
} /*finally {
* buildAveragesLock.writeLock().unlock();
* }*/
}
public static void Evaluate(IDataModel model1,
IDataModel model2,
int samples,
IRunningAverage tracker,
String tag) {
printHeader();
var users = model1.GetUserIDs();
while (users.MoveNext()) {
long userID = users.Current;
IPreferenceArray prefs1 = model1.GetPreferencesFromUser(userID);
IPreferenceArray prefs2 = model2.GetPreferencesFromUser(userID);
prefs1.SortByValueReversed();
prefs2.SortByValueReversed();
FastIDSet commonSet = new FastIDSet();
long maxItemID = setBits(commonSet, prefs1, samples);
FastIDSet otherSet = new FastIDSet();
maxItemID = Math.Max(maxItemID, setBits(otherSet, prefs2, samples));
int max = mask(commonSet, otherSet, maxItemID);
max = Math.Min(max, samples);
if (max < 2) {
continue;
}
long[] items1 = getCommonItems(commonSet, prefs1, max);
long[] items2 = getCommonItems(commonSet, prefs2, max);
double variance = scoreCommonSubset(tag, userID, samples, max, items1, items2);
tracker.AddDatum(variance);
}
}
private void buildMappings()
{
userIDMapping = createIDMapping(dataModel.GetNumUsers(), dataModel.GetUserIDs());
itemIDMapping = createIDMapping(dataModel.GetNumItems(), dataModel.GetItemIDs());
}
public virtual double Evaluate(IRecommenderBuilder recommenderBuilder,
IDataModelBuilder dataModelBuilder,
IDataModel dataModel,
double trainingPercentage,
double evaluationPercentage) {
//Preconditions.checkNotNull(recommenderBuilder);
//Preconditions.checkNotNull(dataModel);
//Preconditions.checkArgument(trainingPercentage >= 0.0 && trainingPercentage <= 1.0,
// "Invalid trainingPercentage: " + trainingPercentage + ". Must be: 0.0 <= trainingPercentage <= 1.0");
//Preconditions.checkArgument(evaluationPercentage >= 0.0 && evaluationPercentage <= 1.0,
// "Invalid evaluationPercentage: " + evaluationPercentage + ". Must be: 0.0 <= evaluationPercentage <= 1.0");
log.Info("Beginning evaluation using {} of {}", trainingPercentage, dataModel);
int numUsers = dataModel.GetNumUsers();
FastByIDMap<IPreferenceArray> trainingPrefs = new FastByIDMap<IPreferenceArray>(
1 + (int) (evaluationPercentage * numUsers));
FastByIDMap<IPreferenceArray> testPrefs = new FastByIDMap<IPreferenceArray>(
1 + (int) (evaluationPercentage * numUsers));
var it = dataModel.GetUserIDs();
while (it.MoveNext()) {
long userID = it.Current;
if (random.nextDouble() < evaluationPercentage) {
splitOneUsersPrefs(trainingPercentage, trainingPrefs, testPrefs, userID, dataModel);
}
}
IDataModel trainingModel = dataModelBuilder == null ? new GenericDataModel(trainingPrefs)
: dataModelBuilder.BuildDataModel(trainingPrefs);
IRecommender recommender = recommenderBuilder.BuildRecommender(trainingModel);
double result = getEvaluation(testPrefs, recommender);
log.Info("Evaluation result: {}", result);
return result;
}
/// Exports the simple user IDs and associated item IDs in the data model.
///
/// @return a {@link FastByIDMap} mapping user IDs to {@link FastIDSet}s representing
/// that user's associated items
public static FastByIDMap<FastIDSet> toDataMap(IDataModel dataModel) {
FastByIDMap<FastIDSet> data = new FastByIDMap<FastIDSet>(dataModel.GetNumUsers());
var it = dataModel.GetUserIDs();
while (it.MoveNext()) {
long userID = it.Current;
data.Put(userID, dataModel.GetItemIDsFromUser(userID));
}
return data;
}
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));
}
private void cachePreferences(IDataModel dataModel) {
int numPreferences = countPreferences(dataModel);
preferences = new IPreference[numPreferences];
var userIDs = dataModel.GetUserIDs();
int index = 0;
while (userIDs.MoveNext()) {
long userID = userIDs.Current;
IPreferenceArray preferencesFromUser = dataModel.GetPreferencesFromUser(userID);
foreach (IPreference preference in preferencesFromUser) {
preferences[index++] = preference;
}
}
}
private long[] doMostSimilarUsers(int howMany, TopItems.IEstimator <long> estimator)
{
IDataModel model = GetDataModel();
return(TopItems.GetTopUsers(howMany, model.GetUserIDs(), null, estimator));
}
private int countPreferences(IDataModel dataModel) {
int numPreferences = 0;
var userIDs = dataModel.GetUserIDs();
while (userIDs.MoveNext()) {
IPreferenceArray preferencesFromUser = dataModel.GetPreferencesFromUser(userIDs.Current);
numPreferences += preferencesFromUser.Length();
}
return numPreferences;
}
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 GenericUserSimilarity(IUserSimilarity otherSimilarity, IDataModel dataModel)
{
long[] userIDs = longIteratorToList(dataModel.GetUserIDs());
initSimilarityMaps(new DataModelSimilaritiesIterator(otherSimilarity, userIDs));
}
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);
}
/// <summary>Exports the simple user IDs and preferences in the data model.</summary>
/// <returns>a <see cref="FastByIDMap"/> mapping user IDs to <see cref="IPreferenceArray"/>s representing that user's preferences</returns>
public static FastByIDMap<IPreferenceArray> ToDataMap(IDataModel dataModel) {
FastByIDMap<IPreferenceArray> data = new FastByIDMap<IPreferenceArray>(dataModel.GetNumUsers());
var it = dataModel.GetUserIDs();
while (it.MoveNext()) {
long userID = it.Current;
data.Put(userID, dataModel.GetPreferencesFromUser(userID));
}
return data;
}
public override Factorization Factorize()
{
log.Info("starting to compute the factorization...");
Features features = new Features(this);
/// feature maps necessary for solving for implicit feedback
IDictionary <int, double[]> userY = null;
IDictionary <int, double[]> itemY = null;
if (usesImplicitFeedback)
{
userY = userFeaturesMapping(dataModel.GetUserIDs(), dataModel.GetNumUsers(), features.getU());
itemY = itemFeaturesMapping(dataModel.GetItemIDs(), dataModel.GetNumItems(), features.getM());
}
IList <Task> tasks;
for (int iteration = 0; iteration < numIterations; iteration++)
{
log.Info("iteration {0}", iteration);
/// fix M - compute U
tasks = new List <Task>();
var userIDsIterator = dataModel.GetUserIDs();
try {
ImplicitFeedbackAlternatingLeastSquaresSolver implicitFeedbackSolver = usesImplicitFeedback
? new ImplicitFeedbackAlternatingLeastSquaresSolver(numFeatures, lambda, alpha, itemY) : null;
while (userIDsIterator.MoveNext())
{
long userID = userIDsIterator.Current;
var itemIDsFromUser = dataModel.GetItemIDsFromUser(userID).GetEnumerator();
IPreferenceArray userPrefs = dataModel.GetPreferencesFromUser(userID);
tasks.Add(Task.Factory.StartNew(() => {
List <double[]> featureVectors = new List <double[]>();
while (itemIDsFromUser.MoveNext())
{
long itemID = itemIDsFromUser.Current;
featureVectors.Add(features.getItemFeatureColumn(itemIndex(itemID)));
}
var userFeatures = usesImplicitFeedback
? implicitFeedbackSolver.solve(sparseUserRatingVector(userPrefs))
: AlternatingLeastSquaresSolver.solve(featureVectors, ratingVector(userPrefs), lambda, numFeatures);
features.setFeatureColumnInU(userIndex(userID), userFeatures);
}
));
}
} finally {
// queue.shutdown();
try {
Task.WaitAll(tasks.ToArray(), 1000 * dataModel.GetNumUsers());
} catch (AggregateException e) {
log.Warn("Error when computing user features", e);
throw e;
}
}
/// fix U - compute M
//queue = createQueue();
tasks = new List <Task>();
var itemIDsIterator = dataModel.GetItemIDs();
try {
ImplicitFeedbackAlternatingLeastSquaresSolver implicitFeedbackSolver = usesImplicitFeedback
? new ImplicitFeedbackAlternatingLeastSquaresSolver(numFeatures, lambda, alpha, userY) : null;
while (itemIDsIterator.MoveNext())
{
long itemID = itemIDsIterator.Current;
IPreferenceArray itemPrefs = dataModel.GetPreferencesForItem(itemID);
tasks.Add(Task.Factory.StartNew(() => {
var featureVectors = new List <double[]>();
foreach (IPreference pref in itemPrefs)
{
long userID = pref.GetUserID();
featureVectors.Add(features.getUserFeatureColumn(userIndex(userID)));
}
var itemFeatures = usesImplicitFeedback
? implicitFeedbackSolver.solve(sparseItemRatingVector(itemPrefs))
: AlternatingLeastSquaresSolver.solve(featureVectors, ratingVector(itemPrefs), lambda, numFeatures);
features.setFeatureColumnInM(itemIndex(itemID), itemFeatures);
}));
}
} finally {
try {
Task.WaitAll(tasks.ToArray(), 1000 * dataModel.GetNumItems());
//queue.awaitTermination(dataModel.getNumItems(), TimeUnit.SECONDS);
} catch (AggregateException e) {
log.Warn("Error when computing item features", e);
throw e;
}
}
}
log.Info("finished computation of the factorization...");
return(createFactorization(features.getU(), features.getM()));
}
public override IEnumerator <long> GetUserIDs()
{
return(_delegate.GetUserIDs());
}
