MyMediaLite  3.11
Public Member Functions | Protected Member Functions | Protected Attributes | Properties | List of all members
KNN Class Referenceabstract

Base class for rating predictors that use some kind of kNN More...

Inheritance diagram for KNN:
IncrementalRatingPredictor RatingPredictor IIncrementalRatingPredictor Recommender IRatingPredictor IRatingPredictor IIncrementalRecommender IRecommender IRecommender IRecommender ItemKNN UserKNN ItemAttributeKNN UserAttributeKNN

Public Member Functions

virtual void AddRatings (IRatings new_ratings)
 Add new ratings and perform incremental training More...
 
virtual bool CanPredict (int user_id, int item_id)
 Check whether a useful prediction (i.e. not using a fallback/default answer) can be made for a given user-item combination More...
 
Object Clone ()
 create a shallow copy of the object More...
 
override void LoadModel (string filename)
 Get the model parameters from a file More...
 
abstract float Predict (int user_id, int item_id)
 Predict rating or score for a given user-item combination More...
 
IList< Tuple< int, float > > Recommend (int user_id, int n=-1, ICollection< int > ignore_items=null, ICollection< int > candidate_items=null)
 Recommend items for a given user More...
 
virtual System.Collections.Generic.IList< Tuple< int, float > > Recommend (int user_id, int n=-1, System.Collections.Generic.ICollection< int > ignore_items=null, System.Collections.Generic.ICollection< int > candidate_items=null)
 
virtual void RemoveItem (int item_id)
 Remove all feedback by one item More...
 
virtual void RemoveRatings (IDataSet ratings_to_delete)
 Remove existing ratings and perform "incremental" training More...
 
virtual void RemoveUser (int user_id)
 Remove all feedback by one user More...
 
override void SaveModel (string filename)
 Save the model parameters to a file More...
 
override string ToString ()
 Return a string representation of the recommender More...
 
override void Train ()
 Learn the model parameters of the recommender from the training data More...
 
virtual void UpdateRatings (IRatings new_ratings)
 Update existing ratings and perform incremental training More...
 

Protected Member Functions

virtual void AddItem (int item_id)
 
virtual void AddUser (int user_id)
 

Protected Attributes

UserItemBaseline baseline_predictor = new UserItemBaseline()
 underlying baseline predictor More...
 
ICorrelationMatrix correlation_matrix
 Correlation matrix over some kind of entity More...
 
float max_rating
 Maximum rating value More...
 
float min_rating
 Minimum rating value More...
 
IRatings ratings
 rating data More...
 

Properties

float Alpha [get, set]
 Alpha parameter for BidirectionalConditionalProbability, or shrinkage parameter for Pearson More...
 
abstract IBooleanMatrix BinaryDataMatrix [get]
 Return the data matrix that can be used to compute a correlation based on binary data More...
 
RatingCorrelationType Correlation [get, set]
 The kind of correlation to use More...
 
abstract EntityType Entity [get]
 The entity type of the neighbors used for rating prediction More...
 
uint K [get, set]
 Number of neighbors to take into account for predictions More...
 
int MaxItemID [get, set]
 Maximum item ID More...
 
virtual float MaxRating [get, set]
 Maximum rating value More...
 
int MaxUserID [get, set]
 Maximum user ID More...
 
virtual float MinRating [get, set]
 Minimum rating value More...
 
uint NumIter [get, set]
 number of iterations used for training the underlying baseline predictor More...
 
override IRatings Ratings [set]
 
float RegI [get, set]
 regularization constant for the item bias of the underlying baseline predictor More...
 
float RegU [get, set]
 regularization constant for the user bias of the underlying baseline predictor More...
 
bool UpdateItems [get, set]
 
bool UpdateUsers [get, set]
 
bool WeightedBinary [get, set]
 If set to true, give a lower weight to evidence coming from very frequent entities More...
 

Detailed Description

Base class for rating predictors that use some kind of kNN

The method is described in section 2.2 of the paper below. One difference is that we support several iterations of alternating optimization, instead of just one.

Literature:

See also
MyMediaLite.ItemRecommendation.KNN

Member Function Documentation

virtual void AddRatings ( IRatings  ratings)
inlinevirtualinherited

Add new ratings and perform incremental training

Parameters
ratingsthe ratings

Implements IIncrementalRatingPredictor.

Reimplemented in MatrixFactorization, UserItemBaseline, NaiveBayes, ItemKNN, UserKNN, UserAverage, GlobalAverage, and ItemAverage.

virtual bool CanPredict ( int  user_id,
int  item_id 
)
inlinevirtualinherited

Check whether a useful prediction (i.e. not using a fallback/default answer) can be made for a given user-item combination

It is up to the recommender implementor to decide when a prediction is useful, and to document it accordingly.

Parameters
user_idthe user ID
item_idthe item ID
Returns
true if a useful prediction can be made, false otherwise

Implements IRecommender.

Reimplemented in ExternalItemRecommender, ExternalRatingPredictor, BiPolarSlopeOne, SlopeOne, Constant, GlobalAverage, UserAverage, ItemAverage, and Random.

Object Clone ( )
inlineinherited

create a shallow copy of the object

override void LoadModel ( string  filename)
inlinevirtual

Get the model parameters from a file

Parameters
filenamethe name of the file to read from

Reimplemented from Recommender.

abstract float Predict ( int  user_id,
int  item_id 
)
pure virtualinherited
IList<Tuple<int, float> > Recommend ( int  user_id,
int  n = -1,
ICollection< int >  ignore_items = null,
ICollection< int >  candidate_items = null 
)
inherited

Recommend items for a given user

Parameters
user_idthe user ID
nthe number of items to recommend, -1 for as many as possible
ignore_itemscollection if items that should not be returned; if null, use empty collection
candidate_itemsthe candidate items to choose from; if null, use all items
Returns
a sorted list of (item_id, score) tuples

Implemented in WeightedEnsemble, and Ensemble.

virtual void RemoveItem ( int  item_id)
inlinevirtualinherited

Remove all feedback by one item

Parameters
item_idthe item ID

Implements IIncrementalRecommender.

Reimplemented in BiasedMatrixFactorization, MatrixFactorization, and ItemAverage.

virtual void RemoveRatings ( IDataSet  ratings)
inlinevirtualinherited

Remove existing ratings and perform "incremental" training

Parameters
ratingsthe user and item IDs of the ratings to be removed

Implements IIncrementalRatingPredictor.

Reimplemented in MatrixFactorization, UserItemBaseline, NaiveBayes, ItemKNN, UserKNN, UserAverage, ItemAverage, and GlobalAverage.

virtual void RemoveUser ( int  user_id)
inlinevirtualinherited

Remove all feedback by one user

Parameters
user_idthe user ID

Implements IIncrementalRecommender.

Reimplemented in BiasedMatrixFactorization, MatrixFactorization, and UserAverage.

override void SaveModel ( string  filename)
inlinevirtual

Save the model parameters to a file

Parameters
filenamethe name of the file to write to

Reimplemented from Recommender.

override string ToString ( )
inline

Return a string representation of the recommender

The ToString() method of recommenders should list the class name and all hyperparameters, separated by space characters.

Implements IRecommender.

override void Train ( )
inlinevirtual

Learn the model parameters of the recommender from the training data

Implements Recommender.

virtual void UpdateRatings ( IRatings  ratings)
inlinevirtualinherited

Update existing ratings and perform incremental training

Parameters
ratingsthe ratings

Implements IIncrementalRatingPredictor.

Reimplemented in MatrixFactorization, UserItemBaseline, NaiveBayes, ItemKNN, UserKNN, UserAverage, GlobalAverage, and ItemAverage.

Member Data Documentation

UserItemBaseline baseline_predictor = new UserItemBaseline()
protected

underlying baseline predictor

ICorrelationMatrix correlation_matrix
protected

Correlation matrix over some kind of entity

float max_rating
protectedinherited

Maximum rating value

float min_rating
protectedinherited

Minimum rating value

IRatings ratings
protectedinherited

rating data

Property Documentation

float Alpha
getset

Alpha parameter for BidirectionalConditionalProbability, or shrinkage parameter for Pearson

abstract IBooleanMatrix BinaryDataMatrix
getprotected

Return the data matrix that can be used to compute a correlation based on binary data

If a purely rating-based correlation is used, this property is ignored.

RatingCorrelationType Correlation
getset

The kind of correlation to use

abstract EntityType Entity
getprotected

The entity type of the neighbors used for rating prediction

uint K
getset

Number of neighbors to take into account for predictions

int MaxItemID
getsetinherited

Maximum item ID

virtual float MaxRating
getsetinherited

Maximum rating value

int MaxUserID
getsetinherited

Maximum user ID

virtual float MinRating
getsetinherited

Minimum rating value

uint NumIter
getset

number of iterations used for training the underlying baseline predictor

float RegI
getset

regularization constant for the item bias of the underlying baseline predictor

float RegU
getset

regularization constant for the user bias of the underlying baseline predictor

bool WeightedBinary
getset

If set to true, give a lower weight to evidence coming from very frequent entities


The documentation for this class was generated from the following file: