recommenderlab (version 0.1-5)

evaluationScheme: Creator Function for evaluationScheme

Description

Creates an evaluationScheme object from a data set. The scheme can be a simple split into training and test data, k-fold cross-evaluation or using k independent bootstrap samples.

Usage

evaluationScheme(data, ...)
## S3 method for class 'ratingMatrix':
evaluationScheme(data, method="split", 
    train=0.9, k=NULL, given, goodRating = NA)

Arguments

data

data set as a ratingMatrix.

method

a character string defining the evaluation method to use (see details).

train

fraction of the data set used for training.

k

number of folds/times to run the evaluation (defaults to 10 for cross-validation and bootstrap and 1 for split).

given

single number of items given for evaluation or a vector of length of data giving the number of items given for each observation.

goodRating

numeric; threshold at which ratings are considered good for evaluation. E.g., with goodRating=3 all items with actual user rating of greater or equal 3 are considered positives in the evaluation process. Note that this argument is onl

...

further arguments.

Value

• Returns an object of class "evaluationScheme".

Details

evaluationScheme creates an evaluation scheme (training and test data) with k runs and one of the given methods:

"split" randomly assigns the proportion of objects given by train to the training set and the rest is used for the test set.

"cross-validation" creates a k-fold cross-validation scheme. The data is randomly split into k parts and in each run k-1 parts are used for training and the remaining part is used for testing. After all k runs each part was used as the test set exactly once.

"bootstrap" creates the training set by taking a bootstrap sample (sampling with replacement) of size train times number of users in the data set. All objects not in the training set are used for testing.

For evaluation, the scheme chooses from the test data for each user given items are randomly as "known" items, the remaining items are "unknown." The known items are used to create a prediction and it is evaluated how well the algorithm predicts the unknown items.

References

Kohavi, Ron (1995). "A study of cross-validation and bootstrap for accuracy estimation and model selection". Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, pp. 1137-1143.

See Also

getData, evaluationScheme, ratingMatrix.

Examples

data("MSWeb")

MSWeb10 <- sample(MSWeb[rowCounts(MSWeb) >10,], 50)
MSWeb10 

esSplit <- evaluationScheme(MSWeb10, method="split",
        train = 0.9, k=1, given=3)
esSplit

esCross <- evaluationScheme(MSWeb10, method="cross-validation",
        k=4, given=3)
esCross