public void testStrategy()
{
List <IPreference> prefsOfUser123 = new List <IPreference>();
prefsOfUser123.Add(new GenericPreference(123L, 1L, 1.0f));
List <IPreference> prefsOfUser456 = new List <IPreference>();
prefsOfUser456.Add(new GenericPreference(456L, 1L, 1.0f));
prefsOfUser456.Add(new GenericPreference(456L, 2L, 1.0f));
List <IPreference> prefsOfUser789 = new List <IPreference>();
prefsOfUser789.Add(new GenericPreference(789L, 1L, 0.5f));
prefsOfUser789.Add(new GenericPreference(789L, 3L, 1.0f));
IPreferenceArray prefArrayOfUser123 = new GenericUserPreferenceArray(prefsOfUser123);
FastByIDMap <IPreferenceArray> userData = new FastByIDMap <IPreferenceArray>();
userData.Put(123L, prefArrayOfUser123);
userData.Put(456L, new GenericUserPreferenceArray(prefsOfUser456));
userData.Put(789L, new GenericUserPreferenceArray(prefsOfUser789));
IDataModel dataModel = new GenericDataModel(userData);
ICandidateItemsStrategy strategy =
new SamplingCandidateItemsStrategy(1, 1, 1, dataModel.GetNumUsers(), dataModel.GetNumItems());
FastIDSet candidateItems = strategy.GetCandidateItems(123L, prefArrayOfUser123, dataModel);
Assert.True(candidateItems.Count() <= 1);
Assert.False(candidateItems.Contains(1L));
}
public double UserSimilarity(long userID1, long userID2)
{
IDataModel dataModel = getDataModel();
FastIDSet xPrefs = dataModel.GetItemIDsFromUser(userID1);
FastIDSet yPrefs = dataModel.GetItemIDsFromUser(userID2);
int xPrefsSize = xPrefs.Count();
int yPrefsSize = yPrefs.Count();
if (xPrefsSize == 0 && yPrefsSize == 0)
{
return(Double.NaN);
}
if (xPrefsSize == 0 || yPrefsSize == 0)
{
return(0.0);
}
int intersectionSize =
xPrefsSize < yPrefsSize?yPrefs.IntersectionSize(xPrefs) : xPrefs.IntersectionSize(yPrefs);
if (intersectionSize == 0)
{
return(Double.NaN);
}
int unionSize = xPrefsSize + yPrefsSize - intersectionSize;
return((double)intersectionSize / (double)unionSize);
}
public void testStrategy()
{
FastIDSet allItemIDs = new FastIDSet();
allItemIDs.AddAll(new long[] { 1L, 2L, 3L });
FastIDSet preferredItemIDs = new FastIDSet(1);
preferredItemIDs.Add(2L);
var dataModelMock = new DynamicMock(typeof(IDataModel));
dataModelMock.ExpectAndReturn("GetNumItems", 3);
dataModelMock.ExpectAndReturn("GetItemIDs", allItemIDs.GetEnumerator());
IPreferenceArray prefArrayOfUser123 = new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(123L, 2L, 1.0f)
});
ICandidateItemsStrategy strategy = new AllUnknownItemsCandidateItemsStrategy();
//EasyMock.replay(dataModel);
FastIDSet candidateItems = strategy.GetCandidateItems(123L, prefArrayOfUser123, (IDataModel)dataModelMock.MockInstance);
Assert.AreEqual(2, candidateItems.Count());
Assert.True(candidateItems.Contains(1L));
Assert.True(candidateItems.Contains(3L));
dataModelMock.Verify();
//EasyMock.verify(dataModel);
}
public void testClear()
{
FastIDSet set = new FastIDSet();
set.Add(1);
set.Clear();
Assert.AreEqual(0, set.Count());
Assert.True(set.IsEmpty());
Assert.False(set.Contains(1));
}
public double UserSimilarity(long userID1, long userID2)
{
IDataModel dataModel = getDataModel();
FastIDSet prefs1 = dataModel.GetItemIDsFromUser(userID1);
FastIDSet prefs2 = dataModel.GetItemIDsFromUser(userID2);
int prefs1Size = prefs1.Count();
int prefs2Size = prefs2.Count();
int intersectionSize = prefs1Size < prefs2Size?prefs2.IntersectionSize(prefs1) : prefs1.IntersectionSize(prefs2);
return(doSimilarity(prefs1Size, prefs2Size, intersectionSize));
}
protected override void prepareTraining()
{
base.prepareTraining();
var random = RandomUtils.getRandom();
p = new double[dataModel.GetNumUsers()][];
for (int i = 0; i < p.Length; i++)
{
p[i] = new double[numFeatures];
for (int feature = 0; feature < FEATURE_OFFSET; feature++)
{
p[i][feature] = 0;
}
for (int feature = FEATURE_OFFSET; feature < numFeatures; feature++)
{
p[i][feature] = random.nextGaussian() * randomNoise;
}
}
y = new double[dataModel.GetNumItems()][];
for (int i = 0; i < y.Length; i++)
{
y[i] = new double[numFeatures];
for (int feature = 0; feature < FEATURE_OFFSET; feature++)
{
y[i][feature] = 0;
}
for (int feature = FEATURE_OFFSET; feature < numFeatures; feature++)
{
y[i][feature] = random.nextGaussian() * randomNoise;
}
}
/// get internal item IDs which we will need several times
itemsByUser = new Dictionary <int, List <int> >();
var userIDs = dataModel.GetUserIDs();
while (userIDs.MoveNext())
{
long userId = userIDs.Current;
int userIdx = userIndex(userId);
FastIDSet itemIDsFromUser = dataModel.GetItemIDsFromUser(userId);
List <int> itemIndexes = new List <int>(itemIDsFromUser.Count());
itemsByUser[userIdx] = itemIndexes;
foreach (long itemID2 in itemIDsFromUser)
{
int i2 = itemIndex(itemID2);
itemIndexes.Add(i2);
}
}
}
public FastIDSet GetRelevantItemsIDs(long userID,
int at,
double relevanceThreshold,
IDataModel dataModel) {
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
FastIDSet relevantItemIDs = new FastIDSet(at);
prefs.SortByValueReversed();
for (int i = 0; i < prefs.Length() && relevantItemIDs.Count() < at; i++) {
if (prefs.GetValue(i) >= relevanceThreshold) {
relevantItemIDs.Add(prefs.GetItemID(i));
}
}
return relevantItemIDs;
}
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 FastIDSet GetRelevantItemsIDs(long userID,
int at,
double relevanceThreshold,
IDataModel dataModel)
{
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
FastIDSet relevantItemIDs = new FastIDSet(at);
prefs.SortByValueReversed();
for (int i = 0; i < prefs.Length() && relevantItemIDs.Count() < at; i++)
{
if (prefs.GetValue(i) >= relevanceThreshold)
{
relevantItemIDs.Add(prefs.GetItemID(i));
}
}
return(relevantItemIDs);
}
public override int GetNumUsersWithPreferenceFor(long itemID1, long itemID2)
{
FastIDSet userIDs1 = preferenceForItems.Get(itemID1);
if (userIDs1 == null)
{
return(0);
}
FastIDSet userIDs2 = preferenceForItems.Get(itemID2);
if (userIDs2 == null)
{
return(0);
}
return(userIDs1.Count() < userIDs2.Count()
? userIDs2.IntersectionSize(userIDs1)
: userIDs1.IntersectionSize(userIDs2));
}
public override IPreferenceArray GetPreferencesForItem(long itemID)
{
FastIDSet userIDs = preferenceForItems.Get(itemID);
if (userIDs == null)
{
throw new NoSuchItemException(itemID);
}
IPreferenceArray prefArray = new BooleanItemPreferenceArray(userIDs.Count());
int i = 0;
var it = userIDs.GetEnumerator();
while (it.MoveNext())
{
prefArray.SetUserID(i, it.Current);
prefArray.SetItemID(i, itemID);
i++;
}
return(prefArray);
}
/// @throws NoSuchUserException
/// if there is no such user
public override IPreferenceArray GetPreferencesFromUser(long userID)
{
FastIDSet itemIDs = preferenceFromUsers.Get(userID);
if (itemIDs == null)
{
throw new NoSuchUserException(userID);
}
IPreferenceArray prefArray = new BooleanUserPreferenceArray(itemIDs.Count());
int i = 0;
var it = itemIDs.GetEnumerator();
while (it.MoveNext())
{
prefArray.SetUserID(i, userID);
prefArray.SetItemID(i, it.Current);
i++;
}
return(prefArray);
}
public void testStrategy()
{
FastIDSet itemIDsFromUser123 = new FastIDSet();
itemIDsFromUser123.Add(1L);
FastIDSet itemIDsFromUser456 = new FastIDSet();
itemIDsFromUser456.Add(1L);
itemIDsFromUser456.Add(2L);
List <IPreference> prefs = new List <IPreference>();
prefs.Add(new GenericPreference(123L, 1L, 1.0f));
prefs.Add(new GenericPreference(456L, 1L, 1.0f));
IPreferenceArray preferencesForItem1 = new GenericItemPreferenceArray(prefs);
var dataModelMock = new DynamicMock(typeof(IDataModel));
dataModelMock.ExpectAndReturn("GetPreferencesForItem", preferencesForItem1, (1L));
dataModelMock.ExpectAndReturn("GetItemIDsFromUser", itemIDsFromUser123, (123L));
dataModelMock.ExpectAndReturn("GetItemIDsFromUser", itemIDsFromUser456, (456L));
IPreferenceArray prefArrayOfUser123 =
new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(123L, 1L, 1.0f)
});
ICandidateItemsStrategy strategy = new PreferredItemsNeighborhoodCandidateItemsStrategy();
//EasyMock.replay(dataModel);
FastIDSet candidateItems = strategy.GetCandidateItems(123L, prefArrayOfUser123, (IDataModel)dataModelMock.MockInstance);
Assert.AreEqual(1, candidateItems.Count());
Assert.True(candidateItems.Contains(2L));
dataModelMock.Verify(); // EasyMock.verify(dataModel);
}
public double UserSimilarity(long userID1, long userID2)
{
IDataModel dataModel = getDataModel();
FastIDSet prefs1 = dataModel.GetItemIDsFromUser(userID1);
FastIDSet prefs2 = dataModel.GetItemIDsFromUser(userID2);
long prefs1Size = prefs1.Count();
long prefs2Size = prefs2.Count();
long intersectionSize =
prefs1Size < prefs2Size?prefs2.IntersectionSize(prefs1) : prefs1.IntersectionSize(prefs2);
if (intersectionSize == 0)
{
return(Double.NaN);
}
long numItems = dataModel.GetNumItems();
double logLikelihood =
LogLikelihood.logLikelihoodRatio(intersectionSize,
prefs2Size - intersectionSize,
prefs1Size - intersectionSize,
numItems - prefs1Size - prefs2Size + intersectionSize);
return(1.0 - 1.0 / (1.0 + logLikelihood));
}
public void testSizeEmpty()
{
FastIDSet set = new FastIDSet();
Assert.AreEqual(0, set.Count());
Assert.True(set.IsEmpty());
set.Add(1);
Assert.AreEqual(1, set.Count());
Assert.False(set.IsEmpty());
set.Remove(1);
Assert.AreEqual(0, set.Count());
Assert.True(set.IsEmpty());
}
public override int GetNumUsersWithPreferenceFor(long itemID)
{
FastIDSet userIDs1 = preferenceForItems.Get(itemID);
return(userIDs1 == null ? 0 : userIDs1.Count());
}
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 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 testVersusHashSet()
{
FastIDSet actual = new FastIDSet(1);
var expected = new HashSet<int>(); //1000000
var r = RandomUtils.getRandom();
for (int i = 0; i < 1000000; i++) {
double d = r.nextDouble();
var key = r.nextInt(100);
if (d < 0.4) {
Assert.AreEqual(expected.Contains(key), actual.Contains(key));
} else {
if (d < 0.7) {
Assert.AreEqual(expected.Add(key), actual.Add(key));
} else {
Assert.AreEqual(expected.Remove(key), actual.Remove(key));
}
Assert.AreEqual(expected.Count, actual.Count() );
Assert.AreEqual(expected.Count==0, actual.IsEmpty());
}
}
}
