public void persistAndLoad()
{
FastByIDMap<int?> userIDMapping = new FastByIDMap<int?>();
FastByIDMap<int?> itemIDMapping = new FastByIDMap<int?>();
userIDMapping.Put(123, 0);
userIDMapping.Put(456, 1);
itemIDMapping.Put(12, 0);
itemIDMapping.Put(34, 1);
double[][] userFeatures = new double[][] { new double[] { 0.1, 0.2, 0.3 }, new double[] { 0.4, 0.5, 0.6 } };
double[][] itemFeatures = new double[][] { new double[] { 0.7, 0.8, 0.9 }, new double[] { 1.0, 1.1, 1.2 } };
Factorization original = new Factorization(userIDMapping, itemIDMapping, userFeatures, itemFeatures);
var storage = Path.Combine( Path.GetTempPath(), "storage.bin");
try {
IPersistenceStrategy persistenceStrategy = new FilePersistenceStrategy(storage);
Assert.IsNull(persistenceStrategy.Load());
persistenceStrategy.MaybePersist(original);
Factorization clone = persistenceStrategy.Load();
Assert.True(original.Equals( clone ) );
} finally {
if (File.Exists(storage))
try { File.Delete(storage); } catch { }
}
}
public void setUpToyData()
{
this.rank = 3;
this.lambda = 0.01;
this.numIterations = 1000;
FastByIDMap <IPreferenceArray> userData = new FastByIDMap <IPreferenceArray>();
userData.Put(1L, new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(1L, 1L, 5.0f),
new GenericPreference(1L, 2L, 5.0f),
new GenericPreference(1L, 3L, 2.0f)
}));
userData.Put(2L, new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(2L, 1L, 2.0f),
new GenericPreference(2L, 3L, 3.0f),
new GenericPreference(2L, 4L, 5.0f)
}));
userData.Put(3L, new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(3L, 2L, 5.0f),
new GenericPreference(3L, 4L, 3.0f)
}));
userData.Put(4L, new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(4L, 1L, 3.0f),
new GenericPreference(4L, 4L, 5.0f)
}));
dataModel = new GenericDataModel(userData);
}
private void initSimilarityMaps(IEnumerator <ItemItemSimilarity> similarities)
{
while (similarities.MoveNext())
{
ItemItemSimilarity current = similarities.Current;
long num = current.getItemID1();
long num2 = current.getItemID2();
if (num != num2)
{
long num3;
long num4;
if (num < num2)
{
num3 = num;
num4 = num2;
}
else
{
num3 = num2;
num4 = num;
}
FastByIDMap <double?> map = this.similarityMaps.get(num3);
if (map == null)
{
map = new FastByIDMap <double?>();
this.similarityMaps.put(num3, map);
}
map.put(num4, new double?(current.getValue()));
this.doIndex(num3, num4);
this.doIndex(num4, num3);
}
}
}
public GenericItemSimilarity(ItemSimilarity otherSimilarity, DataModel dataModel)
{
this.similarityMaps = new FastByIDMap <FastByIDMap <double?> >();
this.similarItemIDsIndex = new FastByIDMap <FastIDSet>();
long[] itemIDs = GenericUserSimilarity.longIteratorToList(dataModel.getItemIDs());
this.initSimilarityMaps(new DataModelSimilaritiesIterator(otherSimilarity, itemIDs));
}
private void buildClusters()
{
DataModel model = getDataModel();
int numUsers = model.getNumUsers();
if (numUsers > 0)
{
List <FastIDSet> newClusters = new List <FastIDSet>();
// Begin with a cluster for each user:
var it = model.getUserIDs();
while (it.MoveNext())
{
FastIDSet newCluster = new FastIDSet();
newCluster.add(it.Current);
newClusters.Add(newCluster);
}
if (numUsers > 1)
{
findClusters(newClusters);
}
topRecsByUserID = computeTopRecsPerUserID(newClusters);
clustersByUserID = computeClustersPerUserID(newClusters);
allClusters = newClusters.ToArray();
}
else
{
topRecsByUserID = new FastByIDMap <List <RecommendedItem> >();
clustersByUserID = new FastByIDMap <FastIDSet>();
allClusters = NO_CLUSTERS;
}
}
public GenericDataModel(FastByIDMap <PreferenceArray> userData, FastByIDMap <FastByIDMap <DateTime?> > timestamps)
{
this.preferenceFromUsers = userData;
FastByIDMap <List <Preference> > data = new FastByIDMap <List <Preference> >();
FastIDSet set = new FastIDSet();
int num = 0;
float negativeInfinity = float.NegativeInfinity;
float positiveInfinity = float.PositiveInfinity;
foreach (KeyValuePair <long, PreferenceArray> pair in this.preferenceFromUsers.entrySet())
{
PreferenceArray array = pair.Value;
array.sortByItem();
foreach (Preference preference in array)
{
long key = preference.getItemID();
set.add(key);
List <Preference> list = data.get(key);
if (list == null)
{
list = new List <Preference>(2);
data.put(key, list);
}
list.Add(preference);
float num5 = preference.getValue();
if (num5 > negativeInfinity)
{
negativeInfinity = num5;
}
if (num5 < positiveInfinity)
{
positiveInfinity = num5;
}
}
if ((++num % 0x2710) == 0)
{
log.info("Processed {0} users", new object[] { num });
}
}
log.info("Processed {0} users", new object[] { num });
this.setMinPreference(positiveInfinity);
this.setMaxPreference(negativeInfinity);
this.itemIDs = set.toArray();
set = null;
Array.Sort <long>(this.itemIDs);
this.preferenceForItems = toDataMap(data, false);
foreach (KeyValuePair <long, PreferenceArray> pair in this.preferenceForItems.entrySet())
{
pair.Value.sortByUser();
}
this.userIDs = new long[userData.size()];
int num6 = 0;
foreach (long num7 in userData.Keys)
{
this.userIDs[num6++] = num7;
}
Array.Sort <long>(this.userIDs);
this.timestamps = timestamps;
}
public double itemSimilarity(long itemID1, long itemID2)
{
long num;
long num2;
if (itemID1 == itemID2)
{
return(1.0);
}
if (itemID1 < itemID2)
{
num = itemID1;
num2 = itemID2;
}
else
{
num = itemID2;
num2 = itemID1;
}
FastByIDMap <double?> map = this.similarityMaps.get(num);
if (map == null)
{
return(double.NaN);
}
double?nullable = map.get(num2);
return(!nullable.HasValue ? double.NaN : nullable.Value);
}
private void buildClusters()
{
DataModel model = getDataModel();
int numUsers = model.getNumUsers();
if (numUsers == 0)
{
topRecsByUserID = new FastByIDMap <List <RecommendedItem> >();
clustersByUserID = new FastByIDMap <FastIDSet>();
}
else
{
List <FastIDSet> clusters = new List <FastIDSet>();
// Begin with a cluster for each user:
var it = model.getUserIDs();
while (it.MoveNext())
{
FastIDSet newCluster = new FastIDSet();
newCluster.add(it.Current);
clusters.Add(newCluster);
}
bool done = false;
while (!done)
{
done = mergeClosestClusters(numUsers, clusters, done);
}
topRecsByUserID = computeTopRecsPerUserID(clusters);
clustersByUserID = computeClustersPerUserID(clusters);
allClusters = clusters.ToArray();
}
}
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 testGetUserIDs()
{
IPreferenceArray prefs = new GenericUserPreferenceArray(1);
long sampleUserID = 1;
prefs.SetUserID(0, sampleUserID);
long sampleItemID = 11;
prefs.SetItemID(0, sampleItemID);
FastByIDMap <IPreferenceArray> delegatePreferences = new FastByIDMap <IPreferenceArray>();
delegatePreferences.Put(sampleUserID, prefs);
PlusAnonymousConcurrentUserDataModel instance = getTestableWithDelegateData(10, delegatePreferences);
long anonymousUserID = instance.TakeAvailableUser().Value;
IPreferenceArray tempPrefs = new GenericUserPreferenceArray(1);
tempPrefs.SetUserID(0, anonymousUserID);
tempPrefs.SetItemID(0, 22);
instance.SetTempPrefs(tempPrefs, anonymousUserID);
var userIDs = instance.GetUserIDs();
userIDs.MoveNext();
Assert.AreEqual(sampleUserID, userIDs.Current);
Assert.False(userIDs.MoveNext());
}
private void pruneInconsequentialDiffs()
{
// Go back and prune inconsequential diffs. "Inconsequential" means, here, only represented by one
// data point, so possibly unreliable
var it1 = averageDiffs.entrySet().ToList();
for (int i = 0; i < it1.Count; i++)
{
FastByIDMap <RunningAverage> map = it1[i].Value;
var it2 = map.entrySet().ToList();
for (int j = 0; j < it2.Count; j++)
{
RunningAverage average = it2[j].Value;
if (average.getCount() <= 1)
{
map.remove(it2[j].Key);
}
}
if (map.isEmpty())
{
averageDiffs.remove(it1[i].Key);
}
else
{
map.rehash();
}
}
averageDiffs.rehash();
}
public void removeItemPref(long userID, long itemIDA, float prefValue)
{
PreferenceArray userPreferences = dataModel.getPreferencesFromUser(userID);
try
{
buildAverageDiffsLock.EnterWriteLock();
FastByIDMap <RunningAverage> aMap = averageDiffs.get(itemIDA);
int length = userPreferences.length();
for (int i = 0; i < length; i++)
{
long itemIDB = userPreferences.getItemID(i);
float bValue = userPreferences.getValue(i);
if (itemIDA < itemIDB)
{
if (aMap != null)
{
RunningAverage average = aMap.get(itemIDB);
if (average != null)
{
if (average.getCount() <= 1)
{
aMap.remove(itemIDB);
}
else
{
average.removeDatum(bValue - prefValue);
}
}
}
}
else if (itemIDA > itemIDB)
{
FastByIDMap <RunningAverage> bMap = averageDiffs.get(itemIDB);
if (bMap != null)
{
RunningAverage average = bMap.get(itemIDA);
if (average != null)
{
if (average.getCount() <= 1)
{
aMap.remove(itemIDA);
}
else
{
average.removeDatum(prefValue - bValue);
}
}
}
}
}
}
finally
{
buildAverageDiffsLock.ExitWriteLock();
}
}
/// <p>
/// Returns the similarity between two items. Note that similarity is assumed to be symmetric, that
/// {@code itemSimilarity(item1, item2) == itemSimilarity(item2, item1)}, and that
/// {@code itemSimilarity(item1,item1) == 1.0} for all items.
/// </p>
///
/// @param itemID1
/// first item
/// @param itemID2
/// second item
/// @return similarity between the two
public double ItemSimilarity(long itemID1, long itemID2)
{
if (itemID1 == itemID2)
{
return(1.0);
}
long firstID;
long secondID;
if (itemID1 < itemID2)
{
firstID = itemID1;
secondID = itemID2;
}
else
{
firstID = itemID2;
secondID = itemID1;
}
FastByIDMap <double?> nextMap = similarityMaps.Get(firstID);
if (nextMap == null)
{
return(Double.NaN);
}
double?similarity = nextMap.Get(secondID);
return(!similarity.HasValue ? Double.NaN : similarity.Value);
}
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 override void SetUp()
{
base.SetUp();
FastByIDMap <IPreferenceArray> userData = new FastByIDMap <IPreferenceArray>();
userData.Put(1L, new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(1L, 1L, 5.0f),
new GenericPreference(1L, 2L, 5.0f),
new GenericPreference(1L, 3L, 2.0f)
}));
userData.Put(2L, new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(2L, 1L, 2.0f),
new GenericPreference(2L, 3L, 3.0f),
new GenericPreference(2L, 4L, 5.0f)
}));
userData.Put(3L, new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(3L, 2L, 5.0f),
new GenericPreference(3L, 4L, 3.0f)
}));
userData.Put(4L, new GenericUserPreferenceArray(new List <IPreference>()
{
new GenericPreference(4L, 1L, 3.0f),
new GenericPreference(4L, 4L, 5.0f)
}));
dataModel = new GenericDataModel(userData);
factorizer = new ALSWRFactorizer(dataModel, 3, 0.065, 10);
}
public void setUpSyntheticData()
{
int numUsers = 2000;
int numItems = 1000;
double sparsity = 0.5;
this.rank = 20;
this.lambda = 0.000000001;
this.numIterations = 100;
var users = randomMatrix(numUsers, rank, 1);
var items = randomMatrix(rank, numItems, 1);
var ratings = times(users, items);
normalize(ratings, 5);
FastByIDMap <IPreferenceArray> userData = new FastByIDMap <IPreferenceArray>();
for (int userIndex = 0; userIndex < numUsers; userIndex++)
{
List <IPreference> row = new List <IPreference>();
for (int itemIndex = 0; itemIndex < numItems; itemIndex++)
{
if (random.nextDouble() <= sparsity)
{
row.Add(new GenericPreference(userIndex, itemIndex, (float)ratings[userIndex, itemIndex]));
}
}
userData.Put(userIndex, new GenericUserPreferenceArray(row));
}
dataModel = new GenericDataModel(userData);
}
internal static IDataModel BuildModel(IList <UserItem> userItems, bool isReviewBased)
{
FastByIDMap <IList <IPreference> > userPreferencesMap = new FastByIDMap <IList <IPreference> >();
foreach (var userItem in userItems)
{
var userPreferences = userPreferencesMap.Get(userItem.UserId);
if (userPreferences == null)
{
userPreferences = new List <IPreference>(3);
userPreferencesMap.Put(userItem.UserId, userPreferences);
}
if (isReviewBased)
{
userPreferences.Add(new GenericPreference(userItem.UserId, userItem.ItemId, userItem.Rating));
}
else
{
userPreferences.Add(new BooleanPreference(userItem.UserId, userItem.ItemId));
}
}
var resultUserPreferences = new FastByIDMap <IPreferenceArray>(userPreferencesMap.Count());
foreach (var entry in userPreferencesMap.EntrySet())
{
var prefList = (List <IPreference>)entry.Value;
resultUserPreferences.Put(entry.Key, isReviewBased ?
new GenericUserPreferenceArray(prefList) :
(IPreferenceArray) new BooleanUserPreferenceArray(prefList));
}
return(new GenericDataModel(resultUserPreferences));
}
public Factorization(FastByIDMap <int?> userIDMapping, FastByIDMap <int?> itemIDMapping, double[][] userFeatures, double[][] itemFeatures)
{
this.userIDMapping = userIDMapping;
this.itemIDMapping = itemIDMapping;
this.userFeatures = userFeatures;
this.itemFeatures = itemFeatures;
}
public Factorization(FastByIDMap<int?> userIDMapping, FastByIDMap<int?> itemIDMapping, double[][] userFeatures,
double[][] itemFeatures) {
this.userIDMapping = userIDMapping; //Preconditions.checkNotNull(
this.itemIDMapping = itemIDMapping; //Preconditions.checkNotNull();
this.userFeatures = userFeatures;
this.itemFeatures = itemFeatures;
}
public double userSimilarity(long userID1, long userID2)
{
long num;
long num2;
if (userID1 == userID2)
{
return(1.0);
}
if (userID1 < userID2)
{
num = userID1;
num2 = userID2;
}
else
{
num = userID2;
num2 = userID1;
}
FastByIDMap <double> map = this.similarityMaps.get(num);
if (map == null)
{
return(double.NaN);
}
return(map.get(num2));
}
public GenericDataModel GetUserBasedDataModel()
{
FastByIDMap <IPreferenceArray> data = new FastByIDMap <IPreferenceArray>();
IEnumerable <UserBookReview> allBookReviews = _userBookReviewRepository.GetListOf();
var everyReviewsUserId = allBookReviews.GroupBy(b => b.UserId).Select(x => x.Key).ToList();
foreach (int userId in everyReviewsUserId)
{
List <UserBookReview> bookReviewsForABook = (from userReviews in allBookReviews
where userReviews.UserId == userId
select userReviews).ToList();
List <IPreference> listOfPreferences = new List <IPreference>();
foreach (UserBookReview review in bookReviewsForABook)
{
int rating = review.Rating;
int bookId = review.BookId;
GenericPreference pref = new GenericPreference(userId, bookId, rating); /// userId, itemid, valueId
listOfPreferences.Add(pref);
}
GenericUserPreferenceArray dataArray = new GenericUserPreferenceArray(listOfPreferences);
data.Put(userId, dataArray);
}
return(new GenericDataModel(data));
}
private void initSimilarityMaps(IEnumerator <UserUserSimilarity> similarities)
{
while (similarities.MoveNext())
{
UserUserSimilarity current = similarities.Current;
long num = current.getUserID1();
long num2 = current.getUserID2();
if (num != num2)
{
long num3;
long num4;
if (num < num2)
{
num3 = num;
num4 = num2;
}
else
{
num3 = num2;
num4 = num;
}
FastByIDMap <double> map = this.similarityMaps.get(num3);
if (map == null)
{
map = new FastByIDMap <double>();
this.similarityMaps.put(num3, map);
}
map.put(num4, current.getValue());
}
}
}
public void persistAndLoad()
{
FastByIDMap <int?> userIDMapping = new FastByIDMap <int?>();
FastByIDMap <int?> itemIDMapping = new FastByIDMap <int?>();
userIDMapping.Put(123, 0);
userIDMapping.Put(456, 1);
itemIDMapping.Put(12, 0);
itemIDMapping.Put(34, 1);
double[][] userFeatures = new double[][] { new double[] { 0.1, 0.2, 0.3 }, new double[] { 0.4, 0.5, 0.6 } };
double[][] itemFeatures = new double[][] { new double[] { 0.7, 0.8, 0.9 }, new double[] { 1.0, 1.1, 1.2 } };
Factorization original = new Factorization(userIDMapping, itemIDMapping, userFeatures, itemFeatures);
var storage = Path.Combine(Path.GetTempPath(), "storage.bin");
try {
IPersistenceStrategy persistenceStrategy = new FilePersistenceStrategy(storage);
Assert.IsNull(persistenceStrategy.Load());
persistenceStrategy.MaybePersist(original);
Factorization clone = persistenceStrategy.Load();
Assert.True(original.Equals(clone));
} finally {
if (File.Exists(storage))
{
try { File.Delete(storage); } catch { }
}
}
}
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 setUpSyntheticData()
{
int numUsers = 2000;
int numItems = 1000;
double sparsity = 0.5;
this.rank = 20;
this.lambda = 0.000000001;
this.numIterations = 100;
var users = randomMatrix(numUsers, rank, 1);
var items = randomMatrix(rank, numItems, 1);
var ratings = times(users, items);
normalize(ratings, 5);
FastByIDMap<IPreferenceArray> userData = new FastByIDMap<IPreferenceArray>();
for (int userIndex = 0; userIndex < numUsers; userIndex++) {
List<IPreference> row= new List<IPreference>();
for (int itemIndex = 0; itemIndex < numItems; itemIndex++) {
if (random.nextDouble() <= sparsity) {
row.Add(new GenericPreference(userIndex, itemIndex, (float) ratings[userIndex, itemIndex]));
}
}
userData.Put(userIndex, new GenericUserPreferenceArray(row));
}
dataModel = new GenericDataModel(userData);
}
private void initSimilarityMaps(IEnumerator <UserUserSimilarity> similarities)
{
while (similarities.MoveNext())
{
UserUserSimilarity uuc = similarities.Current;
long similarityUser1 = uuc.getUserID1();
long similarityUser2 = uuc.getUserID2();
if (similarityUser1 != similarityUser2)
{
// Order them -- first key should be the "smaller" one
long user1;
long user2;
if (similarityUser1 < similarityUser2)
{
user1 = similarityUser1;
user2 = similarityUser2;
}
else
{
user1 = similarityUser2;
user2 = similarityUser1;
}
FastByIDMap <Double> map = similarityMaps.Get(user1);
if (map == null)
{
map = new FastByIDMap <Double>();
similarityMaps.Put(user1, map);
}
map.Put(user2, uuc.getValue());
}
// else similarity between user and itself already assumed to be 1.0
}
}
public double UserSimilarity(long userID1, long userID2)
{
if (userID1 == userID2)
{
return(1.0);
}
long first;
long second;
if (userID1 < userID2)
{
first = userID1;
second = userID2;
}
else
{
first = userID2;
second = userID1;
}
FastByIDMap <Double> nextMap = similarityMaps.Get(first);
if (nextMap == null)
{
return(Double.NaN);
}
Double similarity = nextMap.Get(second);
return(similarity == null ? Double.NaN : similarity);
}
public Factorization(FastByIDMap <int?> userIDMapping, FastByIDMap <int?> itemIDMapping, double[][] userFeatures,
double[][] itemFeatures)
{
this.userIDMapping = userIDMapping; //Preconditions.checkNotNull(
this.itemIDMapping = itemIDMapping; //Preconditions.checkNotNull();
this.userFeatures = userFeatures;
this.itemFeatures = itemFeatures;
}
public GenericUserSimilarity(UserSimilarity otherSimilarity, DataModel dataModel, int maxToKeep)
{
this.similarityMaps = new FastByIDMap <FastByIDMap <double> >();
long[] itemIDs = longIteratorToList(dataModel.getUserIDs());
IEnumerator <UserUserSimilarity> allSimilarities = new DataModelSimilaritiesIterator(otherSimilarity, itemIDs);
this.initSimilarityMaps(TopItems.getTopUserUserSimilarities(maxToKeep, allSimilarities).GetEnumerator());
}
private static FastByIDMap<int?> createIDMapping(int size, IEnumerator<long> idIterator) {
var mapping = new FastByIDMap<int?>(size);
int index = 0;
while (idIterator.MoveNext()) {
mapping.Put(idIterator.Current, index++);
}
return mapping;
}
public void testGrow()
{
FastByIDMap<String> map = new FastByIDMap<String>(1,1);
map.Put(500000L, "alpha");
map.Put(47L, "bang");
Assert.IsNull(map.Get(500000L));
Assert.AreEqual("bang", map.Get(47L));
}
/// <summary>
/// Creates a new <see cref="GenericDataModel"/> from the given users (and their preferences). This
/// <see cref="IDataModel"/> retains all this information in memory and is effectively immutable.
/// </summary>
/// <param name="userData">users to include; (see also <see cref="GenericDataModel.ToDataMap(FastByIDMap, bool)"/>)</param>
/// <param name="timestamps">timestamps optionally, provided timestamps of preferences as milliseconds since the epoch. User IDs are mapped to maps of item IDs to long timestamps.</param>
public GenericDataModel(FastByIDMap<IPreferenceArray> userData, FastByIDMap<FastByIDMap<DateTime?>> timestamps)
{
//Preconditions.checkArgument(userData != null, "userData is null");
this.preferenceFromUsers = userData;
FastByIDMap<IList<IPreference>> prefsForItems = new FastByIDMap<IList<IPreference>>();
FastIDSet itemIDSet = new FastIDSet();
int currentCount = 0;
float maxPrefValue = float.NegativeInfinity;
float minPrefValue = float.PositiveInfinity;
foreach (var entry in preferenceFromUsers.EntrySet()) {
IPreferenceArray prefs = entry.Value;
prefs.SortByItem();
foreach (IPreference preference in prefs) {
long itemID = preference.GetItemID();
itemIDSet.Add(itemID);
var prefsForItem = prefsForItems.Get(itemID);
if (prefsForItem == null) {
prefsForItem = new List<IPreference>(2);
prefsForItems.Put(itemID, prefsForItem);
}
prefsForItem.Add(preference);
float value = preference.GetValue();
if (value > maxPrefValue) {
maxPrefValue = value;
}
if (value < minPrefValue) {
minPrefValue = value;
}
}
if (++currentCount % 10000 == 0) {
log.Info("Processed {0} users", currentCount);
}
}
log.Info("Processed {0} users", currentCount);
setMinPreference(minPrefValue);
setMaxPreference(maxPrefValue);
this.itemIDs = itemIDSet.ToArray();
itemIDSet = null; // Might help GC -- this is big
Array.Sort(itemIDs);
this.preferenceForItems = ToDataMap(prefsForItems, false);
foreach (var entry in preferenceForItems.EntrySet()) {
entry.Value.SortByUser();
}
this.userIDs = new long[userData.Count()];
int i = 0;
foreach (var v in userData.Keys) {
userIDs[i++] = v;
}
Array.Sort(userIDs);
this.timestamps = timestamps;
}
public ItemAverageRecommender(IDataModel dataModel) : base(dataModel)
{
this.itemAverages = new FastByIDMap <IRunningAverage>();
this.refreshHelper = new RefreshHelper(() => {
buildAverageDiffs();
});
refreshHelper.AddDependency(dataModel);
buildAverageDiffs();
}
private static void removeTimestamp(long userID, long itemID, FastByIDMap <FastByIDMap <DateTime?> > timestamps)
{
FastByIDMap <DateTime?> map = timestamps.get(userID);
if (map != null)
{
map.remove(itemID);
}
}
public GenericItemSimilarity(ItemSimilarity otherSimilarity, DataModel dataModel, int maxToKeep)
{
this.similarityMaps = new FastByIDMap <FastByIDMap <double?> >();
this.similarItemIDsIndex = new FastByIDMap <FastIDSet>();
long[] itemIDs = GenericUserSimilarity.longIteratorToList(dataModel.getItemIDs());
DataModelSimilaritiesIterator allSimilarities = new DataModelSimilaritiesIterator(otherSimilarity, itemIDs);
this.initSimilarityMaps(TopItems.getTopItemItemSimilarities(maxToKeep, allSimilarities).GetEnumerator());
}
private long processLine(String line, long averageCount)
{
if (string.IsNullOrEmpty(line) || line[0] == COMMENT_CHAR)
{
return(averageCount);
}
String[] tokens = SEPARATOR.Split(line);
//Preconditions.checkArgument(tokens.length >= 3 && tokens.length != 5, "Bad line: %s", line);
long itemID1 = long.Parse(tokens[0]);
long itemID2 = long.Parse(tokens[1]);
double diff = double.Parse(tokens[2]);
int count = tokens.Length >= 4 ? int.Parse(tokens[3]) : 1;
bool hasMkSk = tokens.Length >= 5;
if (itemID1 > itemID2)
{
long temp = itemID1;
itemID1 = itemID2;
itemID2 = temp;
}
FastByIDMap <RunningAverage> level1Map = averageDiffs.get(itemID1);
if (level1Map == null)
{
level1Map = new FastByIDMap <RunningAverage>();
averageDiffs.put(itemID1, level1Map);
}
RunningAverage average = level1Map.get(itemID2);
if (average != null)
{
throw new Exception("Duplicated line for item-item pair " + itemID1 + " / " + itemID2);
}
if (averageCount < maxEntries)
{
if (hasMkSk)
{
double mk = Double.Parse(tokens[4]);
double sk = Double.Parse(tokens[5]);
average = new FullRunningAverageAndStdDev(count, diff, mk, sk);
}
else
{
average = new FullRunningAverage(count, diff);
}
level1Map.put(itemID2, average);
averageCount++;
}
allRecommendableItemIDs.add(itemID1);
allRecommendableItemIDs.add(itemID2);
return(averageCount);
}
public void testClear()
{
FastByIDMap<long?> map = new FastByIDMap<long?>();
map.Put(500000L, 2L);
map.Clear();
Assert.AreEqual(0, map.Count());
Assert.True(map.IsEmpty());
Assert.IsNull(map.Get(500000L));
}
private void reload() {
if (reloadLock.tryLock()) {
try {
longToString = buildMapping();
} catch (IOException ioe) {
throw new InvalidOperationException(ioe);
} finally {
reloadLock.unlock();
}
}
}
private static void addDatumAndCreateIfNeeded(long itemID, float value, FastByIDMap <IRunningAverage> averages)
{
IRunningAverage itemAverage = averages.Get(itemID);
if (itemAverage == null)
{
itemAverage = new FullRunningAverage();
averages.Put(itemID, itemAverage);
}
itemAverage.AddDatum(value);
}
public void testMaxSize()
{
FastByIDMap<String> map = new FastByIDMap<String>();
map.Put(4, "bang");
Assert.AreEqual(1, map.Count());
map.Put(47L, "bang");
Assert.AreEqual(2, map.Count());
Assert.IsNull(map.Get(500000L));
map.Put(47L, "buzz");
Assert.AreEqual(2, map.Count());
Assert.AreEqual("buzz", map.Get(47L));
}
public FileIDMigrator(File dataFile, long minReloadIntervalMS) {
longToString = new FastByIDMap<String>(100);
this.dataFile = Preconditions.checkNotNull(dataFile);
if (!dataFile.exists() || dataFile.isDirectory()) {
throw new FileNotFoundException(dataFile.toString());
}
log.info("Creating FileReadonlyIDMigrator for file {}", dataFile);
this.reloadLock = new ReentrantLock();
this.lastModified = dataFile.lastModified();
this.minReloadIntervalMS = minReloadIntervalMS;
reload();
}
public void testGetNumUsersWithDelegateUsersOnly()
{
IPreferenceArray prefs = new GenericUserPreferenceArray(1);
long sampleUserID = 1;
prefs.SetUserID(0, sampleUserID);
long sampleItemID = 11;
prefs.SetItemID(0, sampleItemID);
FastByIDMap<IPreferenceArray> delegatePreferences = new FastByIDMap<IPreferenceArray>();
delegatePreferences.Put(sampleUserID, prefs);
PlusAnonymousConcurrentUserDataModel instance = getTestableWithDelegateData(10, delegatePreferences);
Assert.AreEqual(1, instance.GetNumUsers());
}
public static IDataModel getDataModel(long[] userIDs, double?[][] prefValues)
{
FastByIDMap<IPreferenceArray> result = new FastByIDMap<IPreferenceArray>();
for (int i = 0; i < userIDs.Length; i++) {
List<IPreference> prefsList = new List<IPreference>();
for (int j = 0; j < prefValues[i].Length; j++) {
if (prefValues[i][j].HasValue) {
prefsList.Add(new GenericPreference(userIDs[i], j, (float) prefValues[i][j].Value ));
}
}
if (prefsList.Count>0) {
result.Put(userIDs[i], new GenericUserPreferenceArray(prefsList));
}
}
return new GenericDataModel(result);
}
public static IDataModel getBooleanDataModel(long[] userIDs, bool[][] prefs)
{
FastByIDMap<FastIDSet> result = new FastByIDMap<FastIDSet>();
for (int i = 0; i < userIDs.Length; i++) {
FastIDSet prefsSet = new FastIDSet();
for (int j = 0; j < prefs[i].Length; j++) {
if (prefs[i][j]) {
prefsSet.Add(j);
}
}
if (!prefsSet.IsEmpty()) {
result.Put(userIDs[i], prefsSet);
}
}
return new GenericBooleanPrefDataModel(result);
}
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);
}
}
/// <p>
/// Creates a new {@link GenericDataModel} from the given users (and their preferences). This
/// {@link DataModel} retains all this information in memory and is effectively immutable.
/// </p>
///
/// @param userData users to include
/// @param timestamps optionally, provided timestamps of preferences as milliseconds since the epoch.
/// User IDs are mapped to maps of item IDs to long timestamps.
public GenericBooleanPrefDataModel(FastByIDMap<FastIDSet> userData, FastByIDMap<FastByIDMap<DateTime?>> timestamps) {
//Preconditions.checkArgument(userData != null, "userData is null");
this.preferenceFromUsers = userData;
this.preferenceForItems = new FastByIDMap<FastIDSet>();
FastIDSet itemIDSet = new FastIDSet();
foreach (var entry in preferenceFromUsers.EntrySet()) {
long userID = entry.Key;
FastIDSet itemIDs1 = entry.Value;
itemIDSet.AddAll(itemIDs1);
var it = itemIDs1.GetEnumerator();
while (it.MoveNext()) {
long itemID = it.Current;
FastIDSet userIDs1 = preferenceForItems.Get(itemID);
if (userIDs1 == null) {
userIDs1 = new FastIDSet(2);
preferenceForItems.Put(itemID, userIDs1);
}
userIDs1.Add(userID);
}
}
this.itemIDs = itemIDSet.ToArray();
itemIDSet = null; // Might help GC -- this is big
Array.Sort(itemIDs);
this.userIDs = new long[userData.Count()];
int i = 0;
var it1 = userData.Keys.GetEnumerator();
while (it1.MoveNext()) {
userIDs[i++] = it1.Current;
}
Array.Sort(userIDs);
this.timestamps = timestamps;
}
public IDataModel BuildDataModel(FastByIDMap<IPreferenceArray> trainingData)
{
return new GenericBooleanPrefDataModel(GenericBooleanPrefDataModel.toDataMap(trainingData));
}
public static FastByIDMap<FastIDSet> toDataMap(FastByIDMap<IPreferenceArray> data) {
var res = new FastByIDMap<FastIDSet>( data.Count() );
foreach (var entry in data.EntrySet()) {
IPreferenceArray prefArray = entry.Value;
int size = prefArray.Length();
FastIDSet itemIDs = new FastIDSet(size);
for (int i = 0; i < size; i++) {
itemIDs.Add(prefArray.GetItemID(i));
}
res.Put( entry.Key, itemIDs );
}
return res;
}
/// <summary>
/// Creates a new <see cref="GenericBooleanPrefDataModel"/> from the given users (and their preferences). This
/// <see cref="IDataModel"/> retains all this information in memory and is effectively immutable.
/// </summary>
public GenericBooleanPrefDataModel(FastByIDMap<FastIDSet> userData)
: this(userData, null) {
}
public override void SetUp()
{
base.SetUp();
FastByIDMap<IPreferenceArray> userData = new FastByIDMap<IPreferenceArray>();
userData.Put(1L, new GenericUserPreferenceArray( new List<IPreference>() {new GenericPreference(1L, 1L, 5.0f),
new GenericPreference(1L, 2L, 5.0f),
new GenericPreference(1L, 3L, 2.0f) } ));
userData.Put(2L, new GenericUserPreferenceArray( new List<IPreference>() {new GenericPreference(2L, 1L, 2.0f),
new GenericPreference(2L, 3L, 3.0f),
new GenericPreference(2L, 4L, 5.0f) } ));
userData.Put(3L, new GenericUserPreferenceArray( new List<IPreference>() {new GenericPreference(3L, 2L, 5.0f),
new GenericPreference(3L, 4L, 3.0f) } ));
userData.Put(4L, new GenericUserPreferenceArray(new List<IPreference>() {new GenericPreference(4L, 1L, 3.0f),
new GenericPreference(4L, 4L, 5.0f)}));
dataModel = new GenericDataModel(userData);
factorizer = new ALSWRFactorizer(dataModel, 3, 0.065, 10);
}
private FastByIDMap<String> buildMapping() {
FastByIDMap<String> mapping = new FastByIDMap<String>();
for (String line : new FileLineIterable(dataFile)) {
mapping.put(tolongID(line), line);
}
lastModified = dataFile.lastModified();
return mapping;
}
private static FastByIDMap<String> buildTestFastMap()
{
FastByIDMap<String> map = new FastByIDMap<String>();
map.Put(500000L, "alpha");
map.Put(47L, "bang");
map.Put(2L, "beta");
return map;
}
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;
}
private double getEvaluation(FastByIDMap<IPreferenceArray> testPrefs, IRecommender recommender)
{
reset();
var estimateCallables = new List<Action>();
AtomicInteger noEstimateCounter = new AtomicInteger();
foreach (var entry in testPrefs.EntrySet()) {
estimateCallables.Add( () => {
var testUserID = entry.Key;
var prefs = entry.Value;
foreach (IPreference realPref in prefs) {
float estimatedPreference = float.NaN;
try {
estimatedPreference = recommender.EstimatePreference(testUserID, realPref.GetItemID());
} catch (NoSuchUserException nsue) {
// 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("User exists in test data but not training data: {}", testUserID);
} catch (NoSuchItemException nsie) {
log.Info("Item exists in test data but not training data: {}", realPref.GetItemID());
}
if (float.IsNaN(estimatedPreference)) {
noEstimateCounter.incrementAndGet();
} else {
estimatedPreference = capEstimatedPreference(estimatedPreference);
processOneEstimate(estimatedPreference, realPref);
}
}
});
// new PreferenceEstimateCallable(recommender, entry.Key, entry.Value, noEstimateCounter));
}
log.Info("Beginning evaluation of {} users", estimateCallables.Count);
IRunningAverageAndStdDev timing = new FullRunningAverageAndStdDev();
execute(estimateCallables, noEstimateCounter, timing);
return computeFinalEvaluation();
}
private void splitOneUsersPrefs(double trainingPercentage,
FastByIDMap<IPreferenceArray> trainingPrefs,
FastByIDMap<IPreferenceArray> testPrefs,
long userID,
IDataModel dataModel) {
List<IPreference> oneUserTrainingPrefs = null;
List<IPreference> oneUserTestPrefs = null;
IPreferenceArray prefs = dataModel.GetPreferencesFromUser(userID);
int size = prefs.Length();
for (int i = 0; i < size; i++) {
IPreference newPref = new GenericPreference(userID, prefs.GetItemID(i), prefs.GetValue(i));
if (random.nextDouble() < trainingPercentage) {
if (oneUserTrainingPrefs == null) {
oneUserTrainingPrefs = new List<IPreference>(3);
}
oneUserTrainingPrefs.Add(newPref);
} else {
if (oneUserTestPrefs == null) {
oneUserTestPrefs = new List<IPreference>(3);
}
oneUserTestPrefs.Add(newPref);
}
}
if (oneUserTrainingPrefs != null) {
trainingPrefs.Put(userID, new GenericUserPreferenceArray(oneUserTrainingPrefs));
if (oneUserTestPrefs != null) {
testPrefs.Put(userID, new GenericUserPreferenceArray(oneUserTestPrefs));
}
}
}
public void testSizeEmpty()
{
FastByIDMap<long> map = new FastByIDMap<long>();
Assert.AreEqual(0, map.Count());
Assert.True(map.IsEmpty());
map.Put(500000L, 2L);
Assert.AreEqual(1, map.Count());
Assert.False(map.IsEmpty());
map.Remove(500000L);
Assert.AreEqual(0, map.Count());
Assert.True(map.IsEmpty());
}
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 testPutAndGet()
{
FastByIDMap<long?> map = new FastByIDMap<long?>();
Assert.IsNull(map.Get(500000L));
map.Put(500000L, 2L);
Assert.AreEqual(2L, (long) map.Get(500000L));
}
public MemoryIDMigrator() {
this.longToString = new FastByIDMap<String>(100);
}
public void testVersusHashMap()
{
FastByIDMap<String> actual = new FastByIDMap<String>();
IDictionary<long, string> expected = new Dictionary<long,string>(1000000);
var r = RandomUtils.getRandom();
for (int i = 0; i < 1000000; i++) {
double d = r.nextDouble();
long key = (long) r.nextInt(100);
if (d < 0.4) {
Assert.AreEqual( expected.ContainsKey(key)?expected[key]:null, actual.Get(key));
} else {
if (d < 0.7) {
var expectedOldVal = expected.ContainsKey(key) ? expected[key] : null;
expected[key] = "bang";
Assert.AreEqual(expectedOldVal, actual.Put(key, "bang"));
} else {
var expectedOldVal = expected.ContainsKey(key) ? expected[key] : null;
expected.Remove(key);
Assert.AreEqual(expectedOldVal, actual.Remove(key));
}
Assert.AreEqual(expected.Count, actual.Count());
Assert.AreEqual(expected.Count==0, actual.IsEmpty());
}
}
}
