Merge 62cc1b3 into e887629

insightsengineering · Oct 14, 2022 · 237b0fd · 237b0fd
2 parents e887629 + 62cc1b3
commit 237b0fd
Show file tree

Hide file tree

Showing 95 changed files with 484 additions and 523 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: tern
 Title: Create Common TLGs Used in Clinical Trials
-Version: 0.7.10
+Version: 0.7.10.9000
 Date: 2022-10-14
 Authors@R: c(
     person("Joe", "Zhu", , "[email protected]", role = c("aut", "cre")),

diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,9 @@
+# tern 0.7.10.9000
+
+### Enhancements
+* Replaced `synthetic_cdisc_data` with refactored `synthetic_cdisc_dataset` function to speed up dataset loading in tests/examples.
+* Updated all tests to use `rcd_2022_06_27` version of cached data.
+
 # tern 0.7.10
 
 ### New Features

diff --git a/R/abnormal_by_worst_grade.R b/R/abnormal_by_worst_grade.R
@@ -36,8 +36,7 @@ NULL
 #' library(scda)
 #' library(dplyr)
 #' library(forcats)
-#'
-#' adlb <- synthetic_cdisc_data("latest")$adlb
+#' adlb <- synthetic_cdisc_dataset("latest", "adlb")
 #'
 #' # Data is modified in order to have some parameters with grades only in one direction
 #' # and simulate the real data.

diff --git a/R/abnormal_by_worst_grade_worsen.R b/R/abnormal_by_worst_grade_worsen.R
@@ -33,11 +33,10 @@ NULL
 #' for the high direction.
 #'
 #' @examples
-#'
 #' library(scda)
 #' library(dplyr)
-#' adlb <- synthetic_cdisc_data("latest")$adlb
-#' adsl <- synthetic_cdisc_data("latest")$adsl
+#' adsl <- synthetic_cdisc_dataset("latest", "adsl")
+#' adlb <- synthetic_cdisc_dataset("latest", "adlb")
 #'
 #' # The direction variable, GRADDR, is based on metadata
 #' adlb <- adlb %>%

diff --git a/R/count_cumulative.R b/R/count_cumulative.R
@@ -46,13 +46,13 @@ h_count_cumulative <- function(x,
   checkmate::assert_flag(na.rm)
 
   is_keep <- if (na.rm) !is.na(x) else rep(TRUE, length(x))
-  count <- if (lower_tail & include_eq) {
+  count <- if (lower_tail && include_eq) {
     length(x[is_keep & x <= threshold])
-  } else if (lower_tail & !include_eq) {
+  } else if (lower_tail && !include_eq) {
     length(x[is_keep & x < threshold])
-  } else if (!lower_tail & include_eq) {
+  } else if (!lower_tail && include_eq) {
     length(x[is_keep & x >= threshold])
-  } else if (!lower_tail & !include_eq) {
+  } else if (!lower_tail && !include_eq) {
     length(x[is_keep & x > threshold])
   }
 
@@ -137,7 +137,8 @@ a_count_cumulative <- make_afun(
 #' @export
 #' @examples
 #' library(scda)
-#' ADSL <- synthetic_cdisc_data("latest")$adsl
+#' ADSL <- synthetic_cdisc_dataset("latest", "adsl")
+#'
 #' basic_table() %>%
 #'   split_cols_by("ARM") %>%
 #'   add_colcounts() %>%
@@ -146,6 +147,7 @@ a_count_cumulative <- make_afun(
 #'     thresholds = c(40, 60)
 #'   ) %>%
 #'   build_table(ADSL)
+#'
 count_cumulative <- function(lyt,
                              vars,
                              var_labels = vars,

diff --git a/R/count_missed_doses.R b/R/count_missed_doses.R
@@ -92,8 +92,9 @@ a_count_missed_doses <- make_afun(
 #' @examples
 #' library(dplyr)
 #' library(scda)
-#' adex <- synthetic_cdisc_data("latest")$adex
-#' adsl <- synthetic_cdisc_data("latest")$adsl
+#' adex <- synthetic_cdisc_dataset("latest", "adex")
+#' adsl <- synthetic_cdisc_dataset("latest", "adsl")
+#'
 #' anl <- adex %>%
 #'   distinct(STUDYID, USUBJID, ARM) %>%
 #'   mutate(

diff --git a/R/count_patients_with_event.R b/R/count_patients_with_event.R
@@ -26,12 +26,10 @@ NULL
 #' @export
 #'
 #' @examples
-#'
-#'
 #' library(dplyr)
 #' library(scda)
-#' adae <- synthetic_cdisc_data("latest")$adae
-#' adsl <- synthetic_cdisc_data("latest")$adsl
+#' adae <- synthetic_cdisc_dataset("latest", "adae")
+#' adsl <- synthetic_cdisc_dataset("latest", "adsl")
 #'
 #' # `s_count_patients_with_event()`
 #'

diff --git a/R/coxph.R b/R/coxph.R
@@ -91,18 +91,18 @@ rht <- function(x) {
 #' library(scda)
 #' library(survival)
 #'
-#' ADSL <- synthetic_cdisc_data("latest")$adsl
+#' ADSL <- synthetic_cdisc_dataset("latest", "adsl")
 #' ADSL <- ADSL %>%
 #'   filter(SEX %in% c("F", "M"))
 #'
-#' ADTTE <- synthetic_cdisc_data("latest")$adtte %>%
+#' adtte <- synthetic_cdisc_dataset("latest", "adtte") %>%
 #'   filter(PARAMCD == "PFS")
-#' ADTTE$ARMCD <- droplevels(ADTTE$ARMCD)
-#' ADTTE$SEX <- droplevels(ADTTE$SEX)
+#' adtte$ARMCD <- droplevels(adtte$ARMCD)
+#' adtte$SEX <- droplevels(adtte$SEX)
 #'
 #' mod <- coxph(
 #'   formula = Surv(time = AVAL, event = 1 - CNSR) ~ (SEX + ARMCD)^2,
-#'   data = ADTTE
+#'   data = adtte
 #' )
 #'
 #' mmat <- stats::model.matrix(mod)[1, ]
@@ -299,7 +299,7 @@ check_formula <- function(formula) {
 
 
 check_covariate_formulas <- function(covariates) {
-  if (!all(vapply(X = covariates, FUN = inherits, what = "formula", FUN.VALUE = TRUE)) | is.null(covariates)) {
+  if (!all(vapply(X = covariates, FUN = inherits, what = "formula", FUN.VALUE = TRUE)) || is.null(covariates)) {
     stop("Check `covariates`, it should be a list of right-hand-term formulas, e.g. list(Age = ~AGE).")
   }
 
@@ -363,21 +363,21 @@ check_increments <- function(increments, covariates) {
 #' library(scda)
 #' library(dplyr)
 #'
-#' ADTTE <- synthetic_cdisc_data("latest")$adtte
-#' ADTTE_f <- subset(ADTTE, PARAMCD == "OS") # _f: filtered
-#' ADTTE_f <- filter(
-#'   ADTTE_f,
+#' adtte <- synthetic_cdisc_dataset("latest", "adtte")
+#' adtte_f <- subset(adtte, PARAMCD == "OS") # _f: filtered
+#' adtte_f <- filter(
+#'   adtte_f,
 #'   PARAMCD == "OS" &
 #'     SEX %in% c("F", "M") &
 #'     RACE %in% c("ASIAN", "BLACK OR AFRICAN AMERICAN", "WHITE")
 #' )
-#' ADTTE_f$SEX <- droplevels(ADTTE_f$SEX)
-#' ADTTE_f$RACE <- droplevels(ADTTE_f$RACE)
+#' adtte_f$SEX <- droplevels(adtte_f$SEX)
+#' adtte_f$RACE <- droplevels(adtte_f$RACE)
 #'
 #' # Internal function - s_cox_multivariate
 #' \dontrun{
 #' s_cox_multivariate(
-#'   formula = Surv(time = AVAL, event = 1 - CNSR) ~ (ARMCD + RACE + AGE)^2, data = ADTTE_f
+#'   formula = Surv(time = AVAL, event = 1 - CNSR) ~ (ARMCD + RACE + AGE)^2, data = adtte_f
 #' )
 #' }
 #'

diff --git a/R/fit_rsp_step.R b/R/fit_rsp_step.R
@@ -26,13 +26,12 @@
 #'   customization options.
 #' @export
 #' @examples
-#'
 #' # Testing dataset with just two treatment arms.
 #' library(survival)
 #' library(dplyr)
 #' library(scda)
 #'
-#' adrs <- synthetic_cdisc_data("latest")$adrs
+#' adrs <- synthetic_cdisc_dataset("latest", "adrs")
 #' adrs_f <- adrs %>%
 #'   filter(
 #'     PARAMCD == "BESRSPI",

diff --git a/R/fit_survival_step.R b/R/fit_survival_step.R
@@ -21,13 +21,12 @@
 #' @seealso [control_step()] and [control_coxph()] for the available customization options.
 #' @export
 #' @examples
-#'
 #' # Testing dataset with just two treatment arms.
 #' library(scda)
 #' library(dplyr)
 #' library(rtables)
 #'
-#' adtte <- synthetic_cdisc_data("latest")$adtte
+#' adtte <- synthetic_cdisc_dataset("latest", "adtte")
 #'
 #' adtte_f <- adtte %>%
 #'   filter(

diff --git a/R/g_forest.R b/R/g_forest.R
@@ -43,7 +43,8 @@
 #' library(forcats)
 #' library(rtables)
 #' library(nestcolor)
-#' adrs <- synthetic_cdisc_data("latest")$adrs
+#'
+#' adrs <- synthetic_cdisc_dataset("latest", "adrs")
 #' n_records <- 20
 #' adrs_labels <- formatters::var_labels(adrs, fill = TRUE)
 #' adrs <- adrs %>%
@@ -82,7 +83,7 @@
 #' draw_grob(p)
 #'
 #' # Survival forest plot example.
-#' adtte <- synthetic_cdisc_data("latest")$adtte
+#' adtte <- synthetic_cdisc_dataset("latest", "adtte")
 #' # Save variable labels before data processing steps.
 #' adtte_labels <- formatters::var_labels(adtte, fill = TRUE)
 #' adtte_f <- adtte %>%

diff --git a/R/g_lineplot.R b/R/g_lineplot.R
@@ -79,11 +79,11 @@
 #' @export
 #'
 #' @examples
+#' library(scda)
 #' library(nestcolor)
 #'
-#' cached_data <- scda::synthetic_cdisc_data("latest")
-#' adsl <- cached_data$adsl
-#' adlb <- cached_data$adlb
+#' adsl <- synthetic_cdisc_dataset("latest", "adsl")
+#' adlb <- synthetic_cdisc_dataset("latest", "adlb")
 #' adlb <- dplyr::filter(adlb, ANL01FL == "Y", PARAMCD == "ALT", AVISIT != "SCREENING")
 #' adlb$AVISIT <- droplevels(adlb$AVISIT)
 #' adlb <- dplyr::mutate(adlb, AVISIT = forcats::fct_reorder(AVISIT, AVISITN, min))

diff --git a/R/g_waterfall.R b/R/g_waterfall.R
@@ -40,11 +40,11 @@
 #' library(scda)
 #' library(dplyr)
 #'
-#' ADSL <- synthetic_cdisc_data("latest")$adsl
+#' ADSL <- synthetic_cdisc_dataset("latest", "adsl")
 #' ADSL_f <- ADSL %>%
 #'   select(USUBJID, STUDYID, ARM, ARMCD, SEX)
 #'
-#' ADRS <- synthetic_cdisc_data("latest")$adrs
+#' ADRS <- synthetic_cdisc_dataset("latest", "adrs")
 #' ADRS_f <- ADRS %>%
 #'   filter(PARAMCD == "OVRINV") %>%
 #'   mutate(pchg = rnorm(n(), 10, 50))

diff --git a/R/h_adsl_adlb_merge_using_worst_flag.R b/R/h_adsl_adlb_merge_using_worst_flag.R
@@ -28,8 +28,8 @@
 #'
 #' @examples
 #' library(scda)
-#' adlb <- synthetic_cdisc_data("latest")$adlb
-#' adsl <- synthetic_cdisc_data("latest")$adsl
+#' adlb <- synthetic_cdisc_dataset("latest", "adlb")
+#' adsl <- synthetic_cdisc_dataset("latest", "adsl")
 #'
 #' # `h_adsl_adlb_merge_using_worst_flag`
 #' adlb_out <- h_adsl_adlb_merge_using_worst_flag(adsl, adlb, worst_flag = c("WGRHIFL" = "Y"))

diff --git a/R/h_map_for_count_abnormal.R b/R/h_map_for_count_abnormal.R
@@ -19,7 +19,7 @@
 #'
 #' @examples
 #' library(scda)
-#' adlb <- synthetic_cdisc_data("latest")$adlb
+#' adlb <- synthetic_cdisc_dataset("latest", "adlb")
 #' adlb <- df_explicit_na(adlb)
 #'
 #' h_map_for_count_abnormal(

diff --git a/R/h_pkparam_sort.R b/R/h_pkparam_sort.R
@@ -11,7 +11,7 @@
 #' library(scda)
 #' library(dplyr)
 #'
-#' adpp <- synthetic_cdisc_data("latest")$adpp
+#' adpp <- synthetic_cdisc_dataset("latest", "adpp")
 #' adpp <- adpp %>% mutate(PKPARAM = factor(paste0(PARAM, " (", AVALU, ")")))
 #'
 #' pk_ordered_data <- h_pkparam_sort(adpp)

diff --git a/R/h_response_biomarkers_subgroups.R b/R/h_response_biomarkers_subgroups.R
@@ -16,7 +16,7 @@
 #' library(forcats)
 #' library(rtables)
 #'
-#' adrs <- synthetic_cdisc_data("latest")$adrs
+#' adrs <- synthetic_cdisc_dataset("latest", "adrs")
 #' adrs_labels <- formatters::var_labels(adrs)
 #'
 #' adrs_f <- adrs %>%

diff --git a/R/h_response_subgroups.R b/R/h_response_subgroups.R
@@ -19,7 +19,7 @@
 #' library(forcats)
 #' library(rtables)
 #'
-#' adrs <- synthetic_cdisc_data("latest")$adrs
+#' adrs <- synthetic_cdisc_dataset("latest", "adrs")
 #' adrs_labels <- formatters::var_labels(adrs)
 #'
 #' adrs_f <- adrs %>%

diff --git a/R/h_stack_by_baskets.R b/R/h_stack_by_baskets.R
@@ -24,7 +24,7 @@
 #' @examples
 #' library(scda)
 #'
-#' adae <- synthetic_cdisc_data("latest")$adae[1:20, ] %>% df_explicit_na()
+#' adae <- synthetic_cdisc_dataset("latest", "adae")[1:20, ] %>% df_explicit_na()
 #' h_stack_by_baskets(df = adae)
 #'
 #' aag <- data.frame(

diff --git a/R/h_survival_biomarkers_subgroups.R b/R/h_survival_biomarkers_subgroups.R
@@ -18,7 +18,7 @@
 #' library(forcats)
 #' library(rtables)
 #'
-#' adtte <- synthetic_cdisc_data("latest")$adtte
+#' adtte <- synthetic_cdisc_dataset("latest", "adtte")
 #'
 #' # Save variable labels before data processing steps.
 #' adtte_labels <- formatters::var_labels(adtte, fill = FALSE)

diff --git a/R/h_survival_duration_subgroups.R b/R/h_survival_duration_subgroups.R
@@ -21,7 +21,7 @@
 #' library(forcats)
 #' library(rtables)
 #'
-#' adtte <- synthetic_cdisc_data("latest")$adtte
+#' adtte <- synthetic_cdisc_dataset("latest", "adtte")
 #'
 #' # Save variable labels before data processing steps.
 #' adtte_labels <- formatters::var_labels(adtte)

diff --git a/R/individual_patient_plot.R b/R/individual_patient_plot.R
@@ -36,13 +36,12 @@ NULL
 #' @inheritParams argument_convention
 #' @export
 #' @examples
-#'
 #' library(scda)
 #' library(dplyr)
 #' library(nestcolor)
 #'
 #' # Select a small sample of data to plot.
-#' adlb <- synthetic_cdisc_data("latest")$adlb %>%
+#' adlb <- synthetic_cdisc_dataset("latest", "adlb") %>%
 #'   filter(PARAMCD == "ALT", !(AVISIT %in% c("SCREENING", "BASELINE"))) %>%
 #'   slice(1:36)
 #'