C# Class numl.Recommendation.CofiRecommenderModel

Collaborative Filtering Recommender model.
Inheritance: Supervised.Model
Afficher le fichier Open project: sethjuarez/numl

Méthodes publiques

Méthode Description
CofiRecommenderModel ( ) : System

Initializes a new Collaborative Filtering recommender model.
NewEntity ( object item ) : void

Inserts a new learning target entity feature item into the model, i.e. insert a new Movie into the existing model.
NewReference ( object item ) : void

Inserts a new source / reference feature (i.e. User rating items) into the existing model.
Predict ( int referenceId ) : Vector

Predicts all the recommendations of the Items for the supplied reference, i.e. a user.
Predict ( Vector y ) : double

Not implemnted.
PredictRelated ( int itemId, int count = 5, ItemType itemType = ItemType.References ) : Vector

Predicts the related items, given the item index and the type (either References or Entities).

Method Details

CofiRecommenderModel() public méthode

Initializes a new Collaborative Filtering recommender model.
public CofiRecommenderModel ( ) : System
Résultat System

NewEntity() public méthode

Inserts a new learning target entity feature item into the model, i.e. insert a new Movie into the existing model.
public NewEntity ( object item ) : void
item object A source entity object.
Résultat void

NewReference() public méthode

Inserts a new source / reference feature (i.e. User rating items) into the existing model.
public NewReference ( object item ) : void
item object A source feature object.
Résultat void

Predict() public méthode

Predicts all the recommendations of the Items for the supplied reference, i.e. a user.
public Predict ( int referenceId ) : Vector
referenceId int Reference index to use for generating predictions.
Résultat numl.Math.LinearAlgebra.Vector

Predict() public méthode

Not implemnted.
public Predict ( Vector y ) : double
y numl.Math.LinearAlgebra.Vector
Résultat double

PredictRelated() public méthode

Predicts the related items, given the item index and the type (either References or Entities).
public PredictRelated ( int itemId, int count = 5, ItemType itemType = ItemType.References ) : Vector
itemId int The item index in the corresponding feature map column.
count int count
itemType ItemType Type of item to return related items (i.e. References = user ratings OR Entities = books or movies)
Résultat numl.Math.LinearAlgebra.Vector