public void testContainsAndAdd()
{
FastIDSet set = new FastIDSet();
Assert.False(set.Contains(1));
set.Add(1);
Assert.True(set.Contains(1));
}
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 testGrow()
{
FastIDSet set = new FastIDSet(1);
set.Add(1);
set.Add(2);
Assert.True(set.Contains(1));
Assert.True(set.Contains(2));
}
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 void ProcessOtherUser(long userID,
FastIDSet relevantItemIDs,
FastByIDMap <IPreferenceArray> trainingUsers,
long otherUserID,
IDataModel dataModel)
{
IPreferenceArray prefs2Array = dataModel.GetPreferencesFromUser(otherUserID);
// If we're dealing with the very user that we're evaluating for precision/recall,
if (userID == otherUserID)
{
// then must remove all the test IDs, the "relevant" item IDs
List <IPreference> prefs2 = new List <IPreference>(prefs2Array.Length());
foreach (IPreference pref in prefs2Array)
{
if (!relevantItemIDs.Contains(pref.GetItemID()))
{
prefs2.Add(pref);
}
}
if (prefs2.Count > 0)
{
trainingUsers.Put(otherUserID, new GenericUserPreferenceArray(prefs2));
}
}
else
{
// otherwise just add all those other user's prefs
trainingUsers.Put(otherUserID, prefs2Array);
}
}
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 override float?GetPreferenceValue(long userID, long itemID)
{
FastIDSet itemIDs = preferenceFromUsers.Get(userID);
if (itemIDs == null)
{
throw new NoSuchUserException(userID);
}
if (itemIDs.Contains(itemID))
{
return(1.0f);
}
return(null);
}
private static long[] getCommonItems(FastIDSet commonSet, IEnumerable <IRecommendedItem> recs, int max)
{
long[] commonItems = new long[max];
int index = 0;
foreach (IRecommendedItem rec in recs)
{
long item = rec.GetItemID();
if (commonSet.Contains(item))
{
commonItems[index++] = item;
}
if (index == max)
{
break;
}
}
return(commonItems);
}
private static long[] getCommonItems(FastIDSet commonSet, IPreferenceArray prefs1, int max)
{
long[] commonItems = new long[max];
int index = 0;
for (int i = 0; i < prefs1.Length(); i++)
{
long item = prefs1.GetItemID(i);
if (commonSet.Contains(item))
{
commonItems[index++] = item;
}
if (index == max)
{
break;
}
}
return(commonItems);
}
/// This exists because FastIDSet has 'retainAll' as MASK, but there is
/// no count of the number of items in the set. size() is supposed to do
/// this but does not work.
private static int mask(FastIDSet commonSet, FastIDSet otherSet, long maxItemID)
{
int count = 0;
for (int i = 0; i <= maxItemID; i++)
{
if (commonSet.Contains(i))
{
if (otherSet.Contains(i))
{
count++;
}
else
{
commonSet.Remove(i);
}
}
}
return(count);
}
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 void ProcessOtherUser(long userID,
FastIDSet relevantItemIDs,
FastByIDMap<IPreferenceArray> trainingUsers,
long otherUserID,
IDataModel dataModel) {
IPreferenceArray prefs2Array = dataModel.GetPreferencesFromUser(otherUserID);
// If we're dealing with the very user that we're evaluating for precision/recall,
if (userID == otherUserID) {
// then must remove all the test IDs, the "relevant" item IDs
List<IPreference> prefs2 = new List<IPreference>(prefs2Array.Length());
foreach (IPreference pref in prefs2Array) {
if (!relevantItemIDs.Contains(pref.GetItemID())) {
prefs2.Add(pref);
}
}
if (prefs2.Count>0) {
trainingUsers.Put(otherUserID, new GenericUserPreferenceArray(prefs2));
}
} else {
// otherwise just add all those other user's prefs
trainingUsers.Put(otherUserID, prefs2Array);
}
}
/// This exists because FastIDSet has 'retainAll' as MASK, but there is
/// no count of the number of items in the set. size() is supposed to do
/// this but does not work.
private static int mask(FastIDSet commonSet, FastIDSet otherSet, long maxItemID) {
int count = 0;
for (int i = 0; i <= maxItemID; i++) {
if (commonSet.Contains(i)) {
if (otherSet.Contains(i)) {
count++;
} else {
commonSet.Remove(i);
}
}
}
return count;
}
private static long[] getCommonItems(FastIDSet commonSet, IEnumerable<IRecommendedItem> recs, int max) {
long[] commonItems = new long[max];
int index = 0;
foreach (IRecommendedItem rec in recs) {
long item = rec.GetItemID();
if (commonSet.Contains(item)) {
commonItems[index++] = item;
}
if (index == max) {
break;
}
}
return commonItems;
}
private static long[] getCommonItems(FastIDSet commonSet, IPreferenceArray prefs1, int max) {
long[] commonItems = new long[max];
int index = 0;
for (int i = 0; i < prefs1.Length(); i++) {
long item = prefs1.GetItemID(i);
if (commonSet.Contains(item)) {
commonItems[index++] = item;
}
if (index == max) {
break;
}
}
return commonItems;
}
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());
}
}
}
public void testReservedValues()
{
FastIDSet set = new FastIDSet();
try {
set.Add(Int64.MinValue);
Assert.Fail("Should have thrown IllegalArgumentException");
} catch (ArgumentException iae) { //IllegalArgumentException
// good
}
Assert.False(set.Contains(Int64.MinValue));
try {
set.Add(long.MaxValue);
Assert.Fail("Should have thrown IllegalArgumentException");
} catch (ArgumentException iae) {
// good
}
Assert.False(set.Contains(long.MaxValue));
}
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));
}
