MF Class Reference

Abstract class for matrix factorization based item predictors. More...

Inheritance diagram for MF:
ItemRecommender IIterativeModel IItemRecommender IRecommender IRecommender BPRMF WRMF

List of all members.

Public Member Functions

virtual void AddFeedback (int user_id, int item_id)
virtual void AddItem (int item_id)
virtual void AddUser (int user_id)
virtual bool CanPredict (int user_id, int item_id)
 Check whether a useful prediction can be made for a given user-item combination.
Object Clone ()
 create a shallow copy of the object
abstract double ComputeFit ()
 Computes the fit (optimization criterion) on the training data.
abstract void Iterate ()
 Iterate once over the data.
override void LoadModel (string file)
 Get the model parameters from a file.
 MF ()
 Default constructor.
override double Predict (int user_id, int item_id)
 Predict the weight for a given user-item combination.
virtual void RemoveFeedback (int user_id, int item_id)
virtual void RemoveItem (int item_id)
virtual void RemoveUser (int user_id)
override void SaveModel (string file)
 Save the model parameters to a file.
string ToString ()
 Return a string representation of the recommender.
override void Train ()
 Learn the model parameters of the recommender from the training data.

Protected Member Functions

virtual void InitModel ()

Protected Attributes

Matrix< double > item_factors
 Latent item factor matrix.
int num_factors = 10
 Number of latent factors per user/item.
Matrix< double > user_factors
 Latent user factor matrix.

Properties

virtual PosOnlyFeedback Feedback [get, set]
 the feedback data to be used for training
double InitMean [get, set]
 Mean of the normal distribution used to initialize the latent factors.
double InitStdev [get, set]
 Standard deviation of the normal distribution used to initialize the latent factors.
int MaxItemID [get, set]
 Maximum item ID.
int MaxUserID [get, set]
 Maximum user ID.
int NumFactors [get, set]
 Number of latent factors per user/item.
int NumIter [get, set]
 Number of iterations over the training data.

Detailed Description

Abstract class for matrix factorization based item predictors.


Constructor & Destructor Documentation

MF (  ) 

Default constructor.


Member Function Documentation

virtual bool CanPredict ( int  user_id,
int  item_id 
) [virtual, inherited]

Check whether a useful prediction can be made for a given user-item combination.

Parameters:
user_id the user ID
item_id the item ID
Returns:
true if a useful prediction can be made, false otherwise

Implements IRecommender.

Object Clone (  )  [inherited]

create a shallow copy of the object

abstract double ComputeFit (  )  [pure virtual]

Computes the fit (optimization criterion) on the training data.

Returns:
a double representing the fit, lower is better

Implements IIterativeModel.

Implemented in BPRMF, and WRMF.

abstract void Iterate (  )  [pure virtual]

Iterate once over the data.

Implements IIterativeModel.

Implemented in BPRMF, and WRMF.

override void LoadModel ( string  filename  )  [virtual]

Get the model parameters from a file.

Parameters:
filename the name of the file to read from

Implements ItemRecommender.

Reimplemented in BPRMF.

override double Predict ( int  user_id,
int  item_id 
) [virtual]

Predict the weight for a given user-item combination.

If the user or the item are not known to the engine, zero is returned. To avoid this behavior for unknown entities, use CanPredict() to check before.

Parameters:
user_id the user ID
item_id the item ID
Returns:
the predicted weight

Implements ItemRecommender.

Reimplemented in BPRMF.

override void SaveModel ( string  filename  )  [virtual]

Save the model parameters to a file.

Parameters:
filename the name of the file to write to

Implements ItemRecommender.

Reimplemented in BPRMF.

string ToString (  )  [inherited]

Return a string representation of the recommender.

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

Implemented in BPR_Linear, BPRMF, ItemAttributeKNN, ItemKNN, MostPopular, Random, UserAttributeKNN, UserKNN, WeightedItemKNN, WeightedUserKNN, WRMF, Zero, BiasedMatrixFactorization, BiPolarSlopeOne, GlobalAverage, ItemAttributeKNN, ItemAverage, ItemKNNCosine, ItemKNNPearson, MatrixFactorization, SlopeOne, UserAttributeKNN, UserAverage, UserItemBaseline, UserKNNCosine, and UserKNNPearson.


Member Data Documentation

Matrix<double> item_factors [protected]

Latent item factor matrix.

int num_factors = 10 [protected]

Number of latent factors per user/item.

Matrix<double> user_factors [protected]

Latent user factor matrix.


Property Documentation

virtual PosOnlyFeedback Feedback [get, set, inherited]

the feedback data to be used for training

double InitMean [get, set]

Mean of the normal distribution used to initialize the latent factors.

double InitStdev [get, set]

Standard deviation of the normal distribution used to initialize the latent factors.

int MaxItemID [get, set, inherited]

Maximum item ID.

int MaxUserID [get, set, inherited]

Maximum user ID.

int NumFactors [get, set]

Number of latent factors per user/item.

int NumIter [get, set]

Number of iterations over the training data.

Implements IIterativeModel.


The documentation for this class was generated from the following file:
Generated on Tue May 24 12:44:18 2011 for MyMediaLite by  doxygen 1.6.3