public virtual long[] AllSimilarItemIDs(long itemID) {
FastIDSet allSimilarItemIDs = new FastIDSet();
var allItemIDs = dataModel.GetItemIDs();
while (allItemIDs.MoveNext()) {
long possiblySimilarItemID = allItemIDs.Current;
if (!Double.IsNaN(ItemSimilarity(itemID, possiblySimilarItemID))) {
allSimilarItemIDs.Add(possiblySimilarItemID);
}
}
return allSimilarItemIDs.ToArray();
}
public virtual long[] AllSimilarItemIDs(long itemID)
{
FastIDSet allSimilarItemIDs = new FastIDSet();
var allItemIDs = dataModel.GetItemIDs();
while (allItemIDs.MoveNext())
{
long possiblySimilarItemID = allItemIDs.Current;
if (!Double.IsNaN(ItemSimilarity(itemID, possiblySimilarItemID)))
{
allSimilarItemIDs.Add(possiblySimilarItemID);
}
}
return(allSimilarItemIDs.ToArray());
}
/// <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 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());
}
/// <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;
}
/// <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;
}
/// <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 long[] AllSimilarItemIDs(long itemID)
{
FastIDSet similarItemIDs = similarItemIDsIndex.Get(itemID);
return(similarItemIDs != null?similarItemIDs.ToArray() : NO_IDS);
}
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();
}
