Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions R/adversarial_rf.R
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
#' @param early_stop Terminate loop if performance fails to improve from one
#' round to the next?
#' @param prune Impose \code{min_node_size} by pruning?
#' @param verbose Print discriminator accuracy after each round?
#' @param verbose Print discriminator accuracy after each round? Will also show additional warnings.
#' @param parallel Compute in parallel? Must register backend beforehand, e.g.
#' via \code{doParallel} or \code{doFuture}; see examples.
#' @param ... Extra parameters to be passed to \code{ranger}.
Expand Down Expand Up @@ -118,7 +118,7 @@ adversarial_rf <- function(
i <- b <- cnt <- obs <- tree <- leaf <- N <- . <- NULL

# Prep data
x_real <- prep_x(x)
x_real <- prep_x(x, verbose)
n <- nrow(x_real)
d <- ncol(x_real)
factor_cols <- sapply(x_real, is.factor)
Expand Down
11 changes: 8 additions & 3 deletions R/utils.R
Original file line number Diff line number Diff line change
Expand Up @@ -82,9 +82,10 @@ which.max.random <- function(x) {
#' This function prepares input data for ARFs.
#'
#' @param x Input data.frame.
#' @param verbose Show warning if recoding integers?
#' @keywords internal

prep_x <- function(x) {
prep_x <- function(x, verbose = TRUE) {
# Reclass all non-numeric features as factors
x <- as.data.frame(x)
idx_char <- sapply(x, is.character)
Expand All @@ -102,16 +103,20 @@ prep_x <- function(x) {
idx_integer[j] & length(unique(x[[j]])) > 5
})
if (any(to_numeric)) {
warning('Recoding integers with more than 5 unique values as numeric. ',
if (verbose) {
warning('Recoding integers with more than 5 unique values as numeric. ',
'To override this behavior, explicitly code these variables as factors.')
}
x[, to_numeric] <- lapply(x[, to_numeric, drop = FALSE], as.numeric)
}
to_factor <- sapply(seq_len(ncol(x)), function(j) {
idx_integer[j] & length(unique(x[[j]])) < 6
})
if (any(to_factor)) {
warning('Recoding integers with fewer than 6 unique values as ordered factors. ',
if (verbose) {
warning('Recoding integers with fewer than 6 unique values as ordered factors. ',
'To override this behavior, explicitly code these variables as numeric.')
}
x[, to_factor] <- lapply(which(to_factor), function(j) {
lvls <- sort(unique(x[[j]]))
factor(x[[j]], levels = lvls, ordered = TRUE)
Expand Down
2 changes: 1 addition & 1 deletion man/adversarial_rf.Rd

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 3 additions & 1 deletion man/prep_x.Rd

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion tests/testthat/test-return_types.R
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ test_that("FORGE returns correct column types", {
factor = factor(sample(letters[1:5], n, replace = TRUE)),
logical = (sample(0:1, n, replace = TRUE) == 1))

expect_warning(arf <- adversarial_rf(dat, num_trees = 2, verbose = FALSE, parallel = FALSE))
arf <- adversarial_rf(dat, num_trees = 2, verbose = FALSE, parallel = FALSE)
psi <- forde(arf, dat, parallel = FALSE)

# with round = TRUE
Expand Down
Loading