C# Class MyMediaLite.ItemRecommendation.MF

Abstract class for matrix factorization based item predictors
Inheritance: MyMediaLite.ItemRecommendation.IncrementalItemRecommender, IIterativeModel
Afficher le fichier Open project: zenogantner/MML-KDD

Protected Properties

Свойство Type Description
item_factors Matrix
num_factors int
user_factors Matrix

Méthodes publiques

Méthode Description
ComputeFit ( ) : double

Computes the fit (optimization criterion) on the training data
Iterate ( ) : void

Iterate once over the data
LoadModel ( string file ) : void
MF ( ) : System

Default constructor
Predict ( int user_id, int item_id ) : double

Predict the weight for a given user-item combination

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

SaveModel ( string file ) : void
Train ( ) : void

Méthodes protégées

Méthode Description
InitModel ( ) : void

Method Details

ComputeFit() public abstract méthode

Computes the fit (optimization criterion) on the training data
public abstract ComputeFit ( ) : double
Résultat double

InitModel() protected méthode

protected InitModel ( ) : void
Résultat void

Iterate() public abstract méthode

Iterate once over the data
public abstract Iterate ( ) : void
Résultat void

LoadModel() public méthode

public LoadModel ( string file ) : void
file string
Résultat void

MF() public méthode

Default constructor
public MF ( ) : System
Résultat System

Predict() public méthode

Predict the weight for a given user-item combination
If the user or the item are not known to the recommender, zero is returned. To avoid this behavior for unknown entities, use CanPredict() to check before.
public Predict ( int user_id, int item_id ) : double
user_id int the user ID
item_id int the item ID
Résultat double

SaveModel() public méthode

public SaveModel ( string file ) : void
file string
Résultat void

Train() public méthode

public Train ( ) : void
Résultat void

Property Details

item_factors protected_oe property

Latent item factor matrix
protected Matrix item_factors
Résultat Matrix

num_factors protected_oe property

Number of latent factors per user/item
protected int num_factors
Résultat int

user_factors protected_oe property

Latent user factor matrix
protected Matrix user_factors
Résultat Matrix