stan {ARTtransfer} | R Documentation |
stan: Standardize Training, Validation, and Test Datasets
Description
This function standardizes the training, validation, and test datasets by centering and scaling them using the mean and standard deviation from the training set. It ensures that the validation and test sets are transformed using the same parameters derived from the training data.
Usage
stan(train, validation = NULL, test = NULL)
Arguments
train |
A list containing the training set. The list must have a component 'X' for predictors. |
validation |
A list containing the validation set. The list must have a component 'X' for predictors. If 'NULL', the validation set is not standardized. Default is 'NULL'. |
test |
A list containing the test set. The list must have a component 'X' for predictors. If 'NULL', the test set is not standardized. Default is 'NULL'. |
Value
A list with the following components:
train |
The standardized training set, with predictors centered and scaled. |
validation |
The standardized validation set (if provided), standardized using the training set's mean and standard deviation. |
test |
The standardized test set (if provided), standardized using the training set's mean and standard deviation. |
Examples
# Example usage
train_data <- list(X = matrix(rnorm(100), ncol=10))
validation_data <- list(X = matrix(rnorm(50), ncol=10))
test_data <- list(X = matrix(rnorm(50), ncol=10))
standardized <- stan(train = train_data, validation = validation_data, test = test_data)