Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

720 Remove replace_emptys_with_na #768

Merged
merged 6 commits into from
Dec 9, 2022
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
2 changes: 0 additions & 2 deletions R/df_explicit_na.R
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,6 @@
#' # Encode missing values in a subset of columns.
#' df_explicit_na(my_data, omit_columns = c("x", "y"))
#'
#' @seealso [replace_emptys_with_na()]
df_explicit_na <- function(data,
omit_columns = NULL,
char_as_factor = TRUE,
Expand Down Expand Up @@ -86,7 +85,6 @@ df_explicit_na <- function(data,
}

if (is.factor(xi) || is.character(xi)) {

# Handle empty strings and NA values.
xi <- explicit_na(sas_na(xi), label = na_level)

Expand Down
6 changes: 2 additions & 4 deletions R/logistic_regression.R
Original file line number Diff line number Diff line change
Expand Up @@ -904,11 +904,10 @@ logistic_summary_by_flag <- function(flag_var) {
#' @param drop_and_remove_str string to be dropped and removed
#'
#' @examples
#' # Internal function - replace_emptys_with_na
#' \dontrun{
#' # flagging empty strings with "_"
#' df <- replace_emptys_with_na(df, rep_str = "_")
#' df2 <- replace_emptys_with_na(df2, rep_str = "_")
#' df <- df_explicit_na(df, na_level = "_")
#' df2 <- df_explicit_na(df2, na_level = "_")
#'
#' result1 <- basic_table() %>%
#' summarize_logistic(
Expand All @@ -931,7 +930,6 @@ logistic_summary_by_flag <- function(flag_var) {
summarize_logistic <- function(lyt,
conf_level,
drop_and_remove_str = "") {

# checks
checkmate::assert_string(drop_and_remove_str)

Expand Down
39 changes: 0 additions & 39 deletions R/utils_factor.R
Original file line number Diff line number Diff line change
Expand Up @@ -285,42 +285,3 @@ fct_collapse_only <- function(.f, ..., .na_level = "<Missing>") {
x <- forcats::fct_collapse(.f, ..., other_level = .na_level)
do.call(forcats::fct_relevel, args = c(list(.f = x), as.list(new_lvls)))
}

#' Replace all empty string values in data frame
#'
#' @description
#' Function used to fix for update in `Rtables issue` `tern#593` (`NA` alternative -> `" "`)
#' This function is similar in scope as `df_explicit_na()`. In the future a merge
#' is to be expected.
#'
#' @param df `data.frame` table to act upon
#' @param rep_str replacement string for empty strings
#'
#' @details this functions relies onto `for` loop, `levels`, and `nchar`. It can
#' easily be optimized for different cases. For the moment, this fits the purpose
#' to fix issue `tern#593`
#'
#' @seealso [df_explicit_na()]
#'
#' @keywords internal
replace_emptys_with_na <- function(df, rep_str = "NA") {

# checks
checkmate::assert_string(rep_str)

# col logical v
where_to_mod <- apply(df, 2, function(x) any(nchar(x) == 0))

# main loop on cols
for (cl_nm in which(where_to_mod)) {
tmp_cl <- df[, cl_nm]
if (is.null(levels(tmp_cl))) {
tmp_cl[sapply(tmp_cl, nchar) == 0] <- rep_str
} else {
levels(tmp_cl)[sapply(levels(tmp_cl), nchar) == 0] <- rep_str
}
df[, cl_nm] <- tmp_cl
}

return(df)
}
2 changes: 0 additions & 2 deletions man/df_explicit_na.Rd

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

5 changes: 2 additions & 3 deletions man/logistic_regression.Rd

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

27 changes: 0 additions & 27 deletions man/replace_emptys_with_na.Rd

This file was deleted.

21 changes: 7 additions & 14 deletions tests/testthat/test-logistic_regression.R
Original file line number Diff line number Diff line change
Expand Up @@ -1022,17 +1022,15 @@ testthat::test_that("summarize_logistic works as expected for interaction model
interaction = "AGE"
)
)
df <- broom::tidy(mod1, conf_level = 0.99)

# fix for update in Rtables tern#593
df2 <- replace_emptys_with_na(df, rep_str = "_") # _ is the flag value
df <- broom::tidy(mod1, conf_level = 0.99) %>%
df_explicit_na(na_level = "_")

result <- basic_table() %>%
summarize_logistic(
conf_level = 0.99,
drop_and_remove_str = "_"
) %>%
build_table(df2)
build_table(df)

result_matrix <- to_string_matrix(result)
expected_matrix <- structure(
Expand Down Expand Up @@ -1072,11 +1070,8 @@ testthat::test_that("summarize_logistic works as expected for interaction model
interaction = "SEX"
)
)

df <- broom::tidy(model, conf_level = 0.99)

# fix for update in Rtables tern#593
df <- replace_emptys_with_na(df, rep_str = "_")
df <- broom::tidy(model, conf_level = 0.99) %>%
df_explicit_na(na_level = "_")

result <- basic_table() %>%
summarize_logistic(
Expand Down Expand Up @@ -1119,10 +1114,8 @@ testthat::test_that("summarize_logistic works as expected for simple model witho
adrs,
variables = list(response = "Response", arm = "ARMCD", covariates = "AGE")
)
df <- broom::tidy(mod1, conf_level = 0.99)

# fix for update in Rtables tern#593
df <- replace_emptys_with_na(df, rep_str = "_")
df <- broom::tidy(mod1, conf_level = 0.99) %>%
df_explicit_na(na_level = "_")

result <- basic_table() %>%
summarize_logistic(
Expand Down
24 changes: 8 additions & 16 deletions tests/testthat/test-table_lgrt02.R
Original file line number Diff line number Diff line change
Expand Up @@ -38,10 +38,8 @@ testthat::test_that("LGRT02 without interaction term is produced correctly", {
variables = list(response = "Response", arm = "ARMCD", covariates = c("SEX", "RACE", "AGE"))
)
conf_level <- 0.95
df <- broom::tidy(model, conf_level = conf_level)

# fix for update in Rtables tern#593
df <- replace_emptys_with_na(df, rep_str = "_")
df <- broom::tidy(model, conf_level = conf_level) %>%
df_explicit_na(na_level = "_")

result <- basic_table() %>%
summarize_logistic(
Expand Down Expand Up @@ -89,10 +87,8 @@ testthat::test_that("LGRT02 with categorical interaction is produced correctly",
)
)
conf_level <- 0.95
df <- broom::tidy(model, conf_level = conf_level)

# fix for update in Rtables tern#593
df <- replace_emptys_with_na(df, rep_str = "_")
df <- broom::tidy(model, conf_level = conf_level) %>%
df_explicit_na(na_level = "_")

result <- basic_table() %>%
summarize_logistic(
Expand Down Expand Up @@ -142,10 +138,8 @@ testthat::test_that("LGRT02 with continuous interaction is produced correctly",
)
)
conf_level <- 0.95
df <- broom::tidy(model, conf_level = conf_level, at = c(18, 65))

# fix for update in Rtables tern#593
df <- replace_emptys_with_na(df, rep_str = "_")
df <- broom::tidy(model, conf_level = conf_level, at = c(18, 65)) %>%
df_explicit_na(na_level = "_")

result <- basic_table() %>%
summarize_logistic(
Expand Down Expand Up @@ -195,10 +189,8 @@ testthat::test_that("LGRT02 with setting values indicating an event and custom a
response_definition = "1 - response"
)
conf_level <- 0.9
df <- broom::tidy(model, conf_level = conf_level)

# fix for update in Rtables tern#593
df <- replace_emptys_with_na(df, rep_str = "_")
df <- broom::tidy(model, conf_level = conf_level) %>%
df_explicit_na(na_level = "_")

result <- basic_table() %>%
summarize_logistic(
Expand Down