MyMediaLite  3.07
Public Member Functions | Properties
RatingsPerUserChronologicalSplit Class Reference

per-user chronological split for rating prediction More...

Inheritance diagram for RatingsPerUserChronologicalSplit:
ISplit< T >

List of all members.

Public Member Functions

 RatingsPerUserChronologicalSplit (ITimedRatings ratings, double ratio)
 Create a chronological split of rating prediction data.
 RatingsPerUserChronologicalSplit (ITimedRatings ratings, int num_test_ratings_per_user)
 Create a chronological split of rating prediction data.

Properties

uint NumberOfFolds [get]
 The number of folds in this split.
IList< ITimedRatingsTest [get, set]
 Test data for the different folds.
IList< ITimedRatingsTrain [get, set]
 Training data for the different folds.

Detailed Description

per-user chronological split for rating prediction

Chronological splits (splits according to the time of the rating) treat all ratings before a certain time as training ratings, and the ones after that time as test/validation ratings.

Here, the split date may differ from user to user. In the constructor, you can either specify which part (ratio) or how many of a user's rating are supposed to be used for validation.

The dataset must not be modified after the split - this would lead to undefined behavior.


Constructor & Destructor Documentation

RatingsPerUserChronologicalSplit ( ITimedRatings  ratings,
double  ratio 
) [inline]

Create a chronological split of rating prediction data.

If ratings have exactly the same date and time, and they are close to the threshold between train and test, there is no guaranteed order between them (ties are broken according to how the sorting procedure sorts the ratings).

Parameters:
ratingsthe dataset
ratiothe ratio of ratings to use for validation (per user)
RatingsPerUserChronologicalSplit ( ITimedRatings  ratings,
int  num_test_ratings_per_user 
) [inline]

Create a chronological split of rating prediction data.

If ratings have exactly the same date and time, and they are close to the threshold between train and test, there is no guaranteed order between them (ties are broken according to how the sorting procedure sorts the ratings).

Parameters:
ratingsthe dataset
num_test_ratings_per_userthe number of test ratings (per user)

Property Documentation

uint NumberOfFolds [get]

The number of folds in this split.

The number of folds in this split

Implements ISplit< T >.

IList<ITimedRatings> Test [get, set]

Test data for the different folds.

A list of T

Implements ISplit< T >.

IList<ITimedRatings> Train [get, set]

Training data for the different folds.

A list of T

Implements ISplit< T >.


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