This function generates predictions by creating a dataset with single and combined predictors based on the filtering results of a multiDEGGs_filter model.
# S3 method for multiDEGGs_filter
predict(object, newdata, interaction.type = "ratio", sep = ":", ...)A data frame containing:
Single predictors (if any are specified in object$keep)
Combined predictors based on variable pairs and interaction type
A fitted object of class multiDEGGs_filter containing
filtering results with:
Character vector of variable names to keep as single predictors
Data frame or matrix with two columns specifying pairs of variables to combine
A data frame containing the new data for prediction.
Must contain all variables specified in object$keep and
object$pairs.
Character string specifying how to combine the paired predictors. Options are:
Combine paired predictors by dividing the first variable by the second (a/b)
Combine paired predictors by multiplying the variables (a*b)
Default is "ratio".
Character string used as separator when creating column names for combined predictors. Default is ":".
Additional arguments passed to the generic function.
The function processes the filtering results in two steps:
Selects single predictors from newdata based on variables
listed in object$keep
Adds combined predictors from paired variables in
object$pairs