IIterativeModel Interface Reference

Interface representing iteratively trained models. More...

Inheritance diagram for IIterativeModel:
BPR_Linear MF FactorWiseMatrixFactorization MatrixFactorization TimeAwareBaseline UserItemBaseline BPRMF WRMF BiasedMatrixFactorization TimeAwareBaselineWithFrequencies KNN ItemKNN UserKNN ItemAttributeKNN ItemKNNCosine ItemKNNPearson UserAttributeKNN UserKNNCosine UserKNNPearson

List of all members.

Public Member Functions

double ComputeFit ()
 Compute the fit (e.g. RMSE for rating prediction or AUC for item prediction/ranking) on the training data.
void Iterate ()
 Run one iteration (= pass over the training data).

Properties

uint NumIter [get, set]
 Number of iterations to run the training.

Detailed Description

Interface representing iteratively trained models.


Member Function Documentation

double ComputeFit (  ) 

Compute the fit (e.g. RMSE for rating prediction or AUC for item prediction/ranking) on the training data.

Returns:
the fit on the training data according to the optimization criterion; -1 if not implemented

Implemented in BPR_Linear, BPRMF, MF, WRMF, FactorWiseMatrixFactorization, MatrixFactorization, TimeAwareBaseline, TimeAwareBaselineWithFrequencies, and UserItemBaseline.

void Iterate (  ) 

Run one iteration (= pass over the training data).

Implemented in BPR_Linear, BPRMF, MF, WRMF, BiasedMatrixFactorization, FactorWiseMatrixFactorization, MatrixFactorization, TimeAwareBaseline, and UserItemBaseline.


Property Documentation

uint NumIter [get, set]

Number of iterations to run the training.

Implemented in BPR_Linear, MF, FactorWiseMatrixFactorization, MatrixFactorization, TimeAwareBaseline, and UserItemBaseline.


The documentation for this interface was generated from the following file:
Generated on Sun Nov 13 20:32:46 2011 for MyMediaLite by  doxygen 1.6.3