Rating predictor that allows folding in new users. More...
Public Member Functions | |
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. | |
void | LoadModel (string filename) |
Get the model parameters from a file. | |
float | Predict (int user_id, int item_id) |
Predict rating or score for a given user-item combination. | |
void | SaveModel (string filename) |
Save the model parameters to a file. | |
IList< Pair< int, float > > | ScoreItems (IList< Pair< int, float >> rated_items, IList< int > candidate_items) |
Rate a list of items given a list of ratings that represent a new user. | |
string | ToString () |
Return a string representation of the recommender. | |
void | Train () |
Learn the model parameters of the recommender from the training data. | |
Properties | |
float | MaxRating [get, set] |
Gets or sets the maximum rating. | |
float | MinRating [get, set] |
Gets or sets the minimum rating. |
Rating predictor that allows folding in new users.
The process of folding in is computing a predictive model for a new user based on their ratings and the existing recommender, without modifying the parameters of the existing recommender.
Literature:
bool CanPredict | ( | int | user_id, | |
int | item_id | |||
) | [inherited] |
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.
user_id | the user ID | |
item_id | the item ID |
Implemented in Ensemble, ItemRecommender, BiPolarSlopeOne, Constant, GlobalAverage, ItemAverage, Random, RatingPredictor, SlopeOne, and UserAverage.
void LoadModel | ( | string | filename | ) | [inherited] |
Get the model parameters from a file.
filename | the name of the file to read from |
Implemented in Ensemble, WeightedEnsemble, BPRLinear, BPRMF, ItemAttributeSVM, ItemRecommender, KNN, MF, MostPopular, Random, Zero, BiasedMatrixFactorization, BiPolarSlopeOne, CoClustering, Constant, EntityAverage, FactorWiseMatrixFactorization, GlobalAverage, ItemKNN, KNN, MatrixFactorization, Random, RatingPredictor, SigmoidItemAsymmetricFactorModel, SigmoidSVDPlusPlus, SlopeOne, SVDPlusPlus, and UserItemBaseline.
float Predict | ( | int | user_id, | |
int | item_id | |||
) | [inherited] |
Predict rating or score for a given user-item combination.
user_id | the user ID | |
item_id | the item ID |
Implemented in BPRMF_ItemMapping, BPRMF_UserMapping, Ensemble, WeightedEnsemble, BPRLinear, BPRMF, ItemAttributeSVM, ItemKNN, ItemRecommender, MF, MostPopular, Random, UserKNN, WeightedItemKNN, WeightedUserKNN, Zero, BiasedMatrixFactorization, BiPolarSlopeOne, CoClustering, Constant, FactorWiseMatrixFactorization, GlobalAverage, ItemAverage, ItemKNN, LatentFeatureLogLinearModel, MatrixFactorization, Random, RatingPredictor, SigmoidItemAsymmetricFactorModel, SigmoidSVDPlusPlus, SlopeOne, SVDPlusPlus, TimeAwareBaseline, UserAverage, UserItemBaseline, and UserKNN.
void SaveModel | ( | string | filename | ) | [inherited] |
Save the model parameters to a file.
filename | the name of the file to write to |
Implemented in Ensemble, WeightedEnsemble, BPRLinear, BPRMF, ItemAttributeSVM, ItemRecommender, KNN, MF, MostPopular, Random, Zero, BiasedMatrixFactorization, BiPolarSlopeOne, CoClustering, Constant, EntityAverage, FactorWiseMatrixFactorization, GlobalAverage, KNN, MatrixFactorization, Random, RatingPredictor, SigmoidItemAsymmetricFactorModel, SlopeOne, SVDPlusPlus, and UserItemBaseline.
IList<Pair<int, float> > ScoreItems | ( | IList< Pair< int, float >> | rated_items, | |
IList< int > | candidate_items | |||
) |
Rate a list of items given a list of ratings that represent a new user.
rated_items | the ratings (item IDs and rating values) representing the new user | |
candidate_items | the items to be rated |
Implemented in MatrixFactorization, UserAverage, and UserKNN.
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 BPRMF_ItemMapping, BPRMF_ItemMapping_Optimal, BPRMF_ItemMappingKNN, BPRMF_ItemMappingSVR, BPRMF_UserMapping, BPRMF_UserMapping_Optimal, BPRLinear, BPRMF, ItemAttributeKNN, ItemAttributeSVM, ItemKNN, ItemRecommender, MultiCoreBPRMF, SoftMarginRankingMF, UserAttributeKNN, UserKNN, WeightedBPRMF, WeightedItemKNN, WeightedUserKNN, WRMF, BiasedMatrixFactorization, CoClustering, Constant, FactorWiseMatrixFactorization, ItemAttributeKNN, ItemKNNCosine, ItemKNNPearson, LatentFeatureLogLinearModel, MatrixFactorization, RatingPredictor, SigmoidItemAsymmetricFactorModel, SigmoidSVDPlusPlus, SocialMF, SVDPlusPlus, TimeAwareBaseline, TimeAwareBaselineWithFrequencies, UserAttributeKNN, UserItemBaseline, UserKNNCosine, and UserKNNPearson.
float MaxRating [get, set, inherited] |
float MinRating [get, set, inherited] |