MyMediaLite
3.04
|
Fold-in evaluation. More...
Static Public Member Functions | |
static RatingPredictionEvaluationResults | EvaluateFoldIn (this IFoldInRatingPredictor recommender, IRatings update_data, IRatings eval_data) |
Performs user-wise fold-in evaluation. | |
static RatingPredictionEvaluationResults | EvaluateFoldInCompleteRetraining (this RatingPredictor recommender, IRatings update_data, IRatings eval_data) |
Performs user-wise fold-in evaluation, but instead of folding in perform a complete re-training with the new data. | |
static RatingPredictionEvaluationResults | EvaluateFoldInIncrementalTraining (this IncrementalRatingPredictor recommender, IRatings update_data, IRatings eval_data) |
Performs user-wise fold-in evaluation, but instead of folding in perform incremental training with the new data. |
Fold-in evaluation.
static RatingPredictionEvaluationResults EvaluateFoldIn | ( | this IFoldInRatingPredictor | recommender, |
IRatings | update_data, | ||
IRatings | eval_data | ||
) | [inline, static] |
Performs user-wise fold-in evaluation.
recommender | a rating predictor capable of performing a user fold-in |
update_data | the rating data used to represent the users |
eval_data | the evaluation data |
static RatingPredictionEvaluationResults EvaluateFoldInCompleteRetraining | ( | this RatingPredictor | recommender, |
IRatings | update_data, | ||
IRatings | eval_data | ||
) | [inline, static] |
Performs user-wise fold-in evaluation, but instead of folding in perform a complete re-training with the new data.
This method can be quite slow.
recommender | a rating predictor capable of performing a user fold-in |
update_data | the rating data used to represent the users |
eval_data | the evaluation data |
static RatingPredictionEvaluationResults EvaluateFoldInIncrementalTraining | ( | this IncrementalRatingPredictor | recommender, |
IRatings | update_data, | ||
IRatings | eval_data | ||
) | [inline, static] |
Performs user-wise fold-in evaluation, but instead of folding in perform incremental training with the new data.
recommender | a rating predictor capable of performing a user fold-in |
update_data | the rating data used to represent the users |
eval_data | the evaluation data |