MyMediaLite  3.01
Public Member Functions | Properties
ItemRecommender Class Reference

Abstract item recommender class that loads the (positive-only implicit feedback) training data into memory and provides flexible access to it. More...

Inheritance diagram for ItemRecommender:
IRecommender BPRLinear IncrementalItemRecommender ItemAttributeSVM KNN MostPopularByAttributes Random Zero MF MostPopular ItemKNN UserKNN BPRMF WRMF ItemAttributeKNN WeightedItemKNN UserAttributeKNN WeightedUserKNN BPRMF_Mapping BPRMF_Mapping MultiCoreBPRMF SoftMarginRankingMF WeightedBPRMF BPRMF_ItemMapping BPRMF_UserMapping BPRMF_ItemMapping_Optimal BPRMF_ItemMappingKNN BPRMF_ItemMappingSVR BPRMF_UserMapping_Optimal

List of all members.

Public Member Functions

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.
Object Clone ()
 create a shallow copy of the object
abstract void LoadModel (string filename)
 Get the model parameters from a file.
abstract float Predict (int user_id, int item_id)
 Predict rating or score for a given user-item combination.
abstract void SaveModel (string filename)
 Save the model parameters to a file.
override string ToString ()
 Return a string representation of the recommender.
abstract void Train ()
 Learn the model parameters of the recommender from the training data.

Properties

virtual IPosOnlyFeedback Feedback [get, set]
 the feedback data to be used for training
int MaxItemID [get, set]
 Maximum item ID.
int MaxUserID [get, set]
 Maximum user ID.

Detailed Description

Abstract item recommender class that loads the (positive-only implicit feedback) training data into memory and provides flexible access to it.

The data is stored in two sparse matrices: one user-wise (in the rows) and one item-wise.

Positive-only means we only which items a user has accessed/liked, but not which items a user does not like. If there is not data for a specific item, we do not know whether the user has just not yet accessed the item, or whether they really dislike it.

See http://recsyswiki/wiki/Item_recommendation and http://recsyswiki/wiki/Implicit_feedback


Member Function Documentation

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

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.

Object Clone ( ) [inline]

create a shallow copy of the object

abstract void LoadModel ( string  filename) [pure virtual]

Get the model parameters from a file.

Parameters:
filenamethe name of the file to read from

Implements IRecommender.

Implemented in BPRMF, BPRLinear, ItemAttributeSVM, MF, MostPopularByAttributes, MostPopular, KNN, Random, and Zero.

abstract float Predict ( int  user_id,
int  item_id 
) [pure virtual]

Predict rating or score for a given user-item combination.

Parameters:
user_idthe user ID
item_idthe item ID
Returns:
the predicted score/rating for the given user-item combination

Implements IRecommender.

Implemented in BPRMF, BPRMF_ItemMapping, BPRLinear, BPRMF_UserMapping, ItemAttributeSVM, MF, MostPopularByAttributes, MostPopular, UserKNN, ItemKNN, WeightedItemKNN, Random, WeightedUserKNN, and Zero.

abstract void SaveModel ( string  filename) [pure virtual]

Save the model parameters to a file.

Parameters:
filenamethe name of the file to write to

Implements IRecommender.

Implemented in BPRMF, BPRLinear, ItemAttributeSVM, MostPopularByAttributes, MF, MostPopular, KNN, Random, and Zero.

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.

Reimplemented in BPRMF, BPRMF_Mapping, BPRLinear, BPRMF_ItemMapping, BPRMF_UserMapping, WRMF, MultiCoreBPRMF, BPRMF_ItemMapping_Optimal, BPRMF_ItemMappingSVR, SoftMarginRankingMF, ItemAttributeSVM, BPRMF_UserMapping_Optimal, BPRMF_ItemMappingKNN, WeightedBPRMF, ItemKNN, UserKNN, ItemAttributeKNN, UserAttributeKNN, WeightedItemKNN, and WeightedUserKNN.


Property Documentation

virtual IPosOnlyFeedback Feedback [get, set]

the feedback data to be used for training

int MaxItemID [get, set]

Maximum item ID.

int MaxUserID [get, set]

Maximum user ID.


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