Modifier and Type | Method and Description |
---|---|
DataModel |
DataModelBuilder.buildDataModel(FastByIDMap<PreferenceArray> trainingData)
Builds a
DataModel implementation to be used in an evaluation, given training data. |
void |
RelevantItemsDataSplitter.processOtherUser(long userID,
FastIDSet relevantItemIDs,
FastByIDMap<PreferenceArray> trainingUsers,
long otherUserID,
DataModel dataModel)
Adds a single user and all their preferences to the training model.
|
Modifier and Type | Method and Description |
---|---|
void |
GenericRelevantItemsDataSplitter.processOtherUser(long userID,
FastIDSet relevantItemIDs,
FastByIDMap<PreferenceArray> trainingUsers,
long otherUserID,
DataModel dataModel) |
Constructor and Description |
---|
PreferenceEstimateCallable(Recommender recommender,
long testUserID,
PreferenceArray prefs,
AtomicInteger noEstimateCounter) |
Modifier and Type | Class and Description |
---|---|
class |
BooleanItemPreferenceArray
Like
BooleanUserPreferenceArray but stores preferences for one item (all item IDs the same) rather
than one user. |
class |
BooleanUserPreferenceArray
Like
GenericUserPreferenceArray but stores, conceptually, BooleanPreference objects which
have no associated preference value. |
class |
GenericItemPreferenceArray
Like
GenericUserPreferenceArray but stores preferences for one item (all item IDs the same) rather
than one user. |
class |
GenericUserPreferenceArray
Like
GenericItemPreferenceArray but stores preferences for one user (all user IDs the same) rather
than one item. |
Modifier and Type | Method and Description |
---|---|
PreferenceArray |
PlusAnonymousUserDataModel.getPreferencesForItem(long itemID) |
PreferenceArray |
GenericDataModel.getPreferencesForItem(long itemID) |
PreferenceArray |
PlusAnonymousConcurrentUserDataModel.getPreferencesForItem(long itemID) |
PreferenceArray |
GenericBooleanPrefDataModel.getPreferencesForItem(long itemID) |
PreferenceArray |
PlusAnonymousUserDataModel.getPreferencesFromUser(long userID) |
PreferenceArray |
GenericDataModel.getPreferencesFromUser(long userID) |
PreferenceArray |
PlusAnonymousConcurrentUserDataModel.getPreferencesFromUser(long userID) |
PreferenceArray |
GenericBooleanPrefDataModel.getPreferencesFromUser(long userID) |
Modifier and Type | Method and Description |
---|---|
FastByIDMap<PreferenceArray> |
GenericDataModel.getRawItemData()
This is used mostly internally to the framework, and shouldn't be relied upon otherwise.
|
FastByIDMap<PreferenceArray> |
GenericDataModel.getRawUserData()
This is used mostly internally to the framework, and shouldn't be relied upon otherwise.
|
static FastByIDMap<PreferenceArray> |
GenericDataModel.toDataMap(DataModel dataModel)
Exports the simple user IDs and preferences in the data model.
|
static FastByIDMap<PreferenceArray> |
GenericDataModel.toDataMap(FastByIDMap<Collection<Preference>> data,
boolean byUser)
|
Modifier and Type | Method and Description |
---|---|
void |
PlusAnonymousUserDataModel.setTempPrefs(PreferenceArray prefs) |
void |
PlusAnonymousConcurrentUserDataModel.setTempPrefs(PreferenceArray prefs,
long anonymousUserID)
Sets temporary preferences for a given anonymous user.
|
Modifier and Type | Method and Description |
---|---|
static FastByIDMap<FastIDSet> |
GenericBooleanPrefDataModel.toDataMap(FastByIDMap<PreferenceArray> data) |
Constructor and Description |
---|
GenericDataModel(FastByIDMap<PreferenceArray> userData)
Creates a new
GenericDataModel from the given users (and their preferences). |
GenericDataModel(FastByIDMap<PreferenceArray> userData,
FastByIDMap<FastByIDMap<Long>> timestamps)
Creates a new
GenericDataModel from the given users (and their preferences). |
Modifier and Type | Method and Description |
---|---|
PreferenceArray |
FileDataModel.getPreferencesForItem(long itemID) |
PreferenceArray |
FileDataModel.getPreferencesFromUser(long userID) |
Modifier and Type | Method and Description |
---|---|
protected float |
GenericItemBasedRecommender.doEstimatePreference(long userID,
PreferenceArray preferencesFromUser,
long itemID) |
protected float |
GenericBooleanPrefItemBasedRecommender.doEstimatePreference(long userID,
PreferenceArray preferencesFromUser,
long itemID)
This computation is in a technical sense, wrong, since in the domain of "boolean preference users" where
all preference values are 1, this method should only ever return 1.0 or NaN.
|
protected FastIDSet |
AbstractRecommender.getAllOtherItems(long userID,
PreferenceArray preferencesFromUser,
boolean includeKnownItems) |
FastIDSet |
AbstractCandidateItemsStrategy.getCandidateItems(long userID,
PreferenceArray preferencesFromUser,
DataModel dataModel,
boolean includeKnownItems) |
Modifier and Type | Method and Description |
---|---|
protected static Vector |
ALSWRFactorizer.ratingVector(PreferenceArray prefs) |
protected Vector |
ALSWRFactorizer.sparseItemRatingVector(PreferenceArray prefs) |
protected Vector |
ALSWRFactorizer.sparseUserRatingVector(PreferenceArray prefs) |
Modifier and Type | Method and Description |
---|---|
PreferenceArray |
PreferenceArray.clone() |
PreferenceArray |
DataModel.getPreferencesForItem(long itemID) |
PreferenceArray |
DataModel.getPreferencesFromUser(long userID) |
Modifier and Type | Method and Description |
---|---|
FastByIDMap<PreferenceArray> |
JDBCDataModel.exportWithPrefs()
Hmm, should this exist elsewhere? seems like most relevant for a DB implementation, which is not in
memory, which might want to export to memory.
|
Modifier and Type | Method and Description |
---|---|
FastIDSet |
CandidateItemsStrategy.getCandidateItems(long userID,
PreferenceArray preferencesFromUser,
DataModel dataModel,
boolean includeKnownItems) |
Copyright © 2008–2017 The Apache Software Foundation. All rights reserved.