replace usage of scda and scda.2022 with random.cdisc.data (#250)

closes #242 similar to [this PR](https://github.com/insightsengineering/biomarker-catalog/pull/64/files#diff-9cc358405149db607ff830a16f0b4b21f7366e3c99ec00d52800acebe21b231c) --------- Co-authored-by: github-actions <41898282+github-actions[bot]@users.noreply.github.com>
insightsengineering · May 15, 2024 · 7a3f457 · 7a3f457
1 parent cd2b70d
commit 7a3f457
Show file tree

Hide file tree

Showing 137 changed files with 383 additions and 827 deletions.
diff --git a/book/graphs/efficacy/fstg01.qmd b/book/graphs/efficacy/fstg01.qmd
@@ -13,16 +13,14 @@ subtitle: Subgroup Analysis of Best Overall Response
 ```{r setup, message = FALSE}
 #| code-fold: show
 
-library(scda)
-library(scda.2022)
 library(dplyr)
 library(tern)
 library(nestcolor)
 
-adsl_f <- synthetic_cdisc_dataset("latest", "adsl") %>%
+adsl_f <- random.cdisc.data::cadsl %>%
   select(STUDYID, USUBJID, ARMCD, ARM, SEX, BMRKR2, STRATA1, STRATA2)
 
-adrs_f <- synthetic_cdisc_dataset("latest", "adrs") %>%
+adrs_f <- random.cdisc.data::cadrs %>%
   filter(PARAMCD == "INVET") %>%
   select(STUDYID, USUBJID, PARAMCD, AVISIT, AVALC)
 
@@ -244,11 +242,8 @@ library(teal.modules.clinical)
 ## Data reproducible code
 data <- teal_data()
 data <- within(data, {
-  library(scda)
-  library(scda.2022)
-
-  ADSL <- synthetic_cdisc_dataset("latest", "adsl")
-  ADRS <- synthetic_cdisc_dataset("latest", "adrs")
+  ADSL <- random.cdisc.data::cadsl
+  ADRS <- random.cdisc.data::cadrs
 })
 datanames <- c("ADSL", "ADRS")
 datanames(data) <- datanames

diff --git a/book/graphs/efficacy/fstg02.qmd b/book/graphs/efficacy/fstg02.qmd
@@ -17,8 +17,6 @@ library(tern)
 library(dplyr)
 library(forcats)
 library(nestcolor)
-library(scda)
-library(scda.2022)
 
 preprocess_adtte <- function(adtte) {
   # Save variable labels before data processing steps.
@@ -51,7 +49,7 @@ preprocess_adtte <- function(adtte) {
   adtte
 }
 
-anl <- synthetic_cdisc_dataset("latest", "adtte") %>%
+anl <- random.cdisc.data::cadtte %>%
   preprocess_adtte()
 ```
 
@@ -212,19 +210,17 @@ library(teal.modules.clinical)
 ## Data reproducible code
 data <- teal_data()
 data <- within(data, {
-  library(scda)
-  library(scda.2022)
   library(dplyr)
   library(forcats)
 
-  ADSL <- synthetic_cdisc_dataset("latest", "adsl")
+  ADSL <- random.cdisc.data::cadsl
   ADSL <- ADSL %>%
     filter(ARM %in% c("B: Placebo", "A: Drug X")) %>%
     mutate(ARM = droplevels(fct_relevel(ARM, "B: Placebo"))) %>%
     mutate(ARMCD = droplevels(fct_relevel(ARMCD, "ARM B")))
   ADSL$RACE <- droplevels(ADSL$RACE)
 
-  ADTTE <- synthetic_cdisc_dataset("latest", "adtte")
+  ADTTE <- random.cdisc.data::cadtte
   adtte_labels <- col_labels(ADTTE)
 
   ADTTE <- ADTTE %>%

diff --git a/book/graphs/efficacy/kmg01.qmd b/book/graphs/efficacy/kmg01.qmd
@@ -14,12 +14,10 @@ subtitle: Kaplan-Meier Plot
 #| code-fold: show
 
 library(tern)
-library(scda)
-library(scda.2022)
 library(dplyr)
 library(nestcolor)
 
-adtte <- synthetic_cdisc_dataset("latest", "adtte")
+adtte <- random.cdisc.data::cadtte
 anl <- adtte %>%
   dplyr::filter(PARAMCD == "OS") %>%
   dplyr::mutate(is_event = CNSR == 0)
@@ -183,11 +181,8 @@ library(teal.modules.clinical)
 ## Data reproducible code
 data <- teal_data()
 data <- within(data, {
-  library(scda)
-  library(scda.2022)
-
-  ADSL <- synthetic_cdisc_dataset("latest", "adsl")
-  ADTTE <- synthetic_cdisc_dataset("latest", "adtte")
+  ADSL <- random.cdisc.data::cadsl
+  ADTTE <- random.cdisc.data::cadtte
 })
 datanames <- c("ADSL", "ADTTE")
 datanames(data) <- datanames

diff --git a/book/graphs/efficacy/mmrmg01.qmd b/book/graphs/efficacy/mmrmg01.qmd
@@ -18,12 +18,10 @@ Given an MMRM fitted with `s_mmrm`, `g_mmrm_lsmeans` displays for each visit the
 
 library(dplyr)
 library(tern.mmrm)
-library(scda)
-library(scda.2022)
 library(nestcolor)
 
-adsl <- synthetic_cdisc_dataset("latest", "adsl")
-adqs <- synthetic_cdisc_dataset("latest", "adqs")
+adsl <- random.cdisc.data::cadsl
+adqs <- random.cdisc.data::cadqs
 
 adqs_f <- adqs %>%
   dplyr::filter(PARAMCD == "FKSI-FWB" & !AVISIT %in% c("BASELINE")) %>%
@@ -124,12 +122,10 @@ library(teal.modules.clinical)
 ## Data reproducible code
 data <- teal_data()
 data <- within(data, {
-  library(scda)
-  library(scda.2022)
   library(dplyr)
 
-  ADSL <- synthetic_cdisc_dataset("latest", "adsl")
-  ADQS <- synthetic_cdisc_dataset("latest", "adqs") %>%
+  ADSL <- random.cdisc.data::cadsl
+  ADQS <- random.cdisc.data::cadqs %>%
     filter(ABLFL != "Y" & ABLFL2 != "Y") %>%
     filter(AVISIT %in% c("WEEK 1 DAY 8", "WEEK 2 DAY 15", "WEEK 3 DAY 22")) %>%
     mutate(

diff --git a/book/graphs/efficacy/mmrmg02.qmd b/book/graphs/efficacy/mmrmg02.qmd
@@ -13,14 +13,12 @@ subtitle: Forest Plot for Mixed-Effect Model Repeated Measures
 ```{r setup, message = FALSE}
 #| code-fold: show
 
-library(scda)
-library(scda.2022)
 library(dplyr)
 library(tern.mmrm)
 library(nestcolor)
 
-adsl <- synthetic_cdisc_dataset("latest", "adsl")
-adqs <- synthetic_cdisc_dataset("latest", "adqs")
+adsl <- random.cdisc.data::cadsl
+adqs <- random.cdisc.data::cadqs
 
 adqs_f <- adqs %>%
   dplyr::filter(PARAMCD == "FKSI-FWB" & !AVISIT %in% c("BASELINE")) %>%

diff --git a/book/graphs/other/brg01.qmd b/book/graphs/other/brg01.qmd
@@ -16,13 +16,11 @@ subtitle: Bar Chart
 library(binom)
 library(dplyr)
 library(ggplot2)
-library(scda)
-library(scda.2022)
 library(tidyr)
 library(tern)
 library(nestcolor)
 
-adsl <- synthetic_cdisc_dataset("latest", "adsl")
+adsl <- random.cdisc.data::cadsl
 
 # filtered population
 patpop_df <- adsl %>%
@@ -31,12 +29,12 @@ patpop_df <- adsl %>%
 patpop <- setNames(patpop_df$patpop, patpop_df$STUDYID)
 denom <- patpop_df$patpop
 
-adae <- synthetic_cdisc_dataset("latest", "adae") %>%
+adae <- random.cdisc.data::cadae %>%
   mutate(AETOXGRC = as.character(AETOXGR))
 attributes(adae$AETOXGRC)$label <- "Analysis Toxicity Grade (C)"
 vl_ae <- var_labels(adae)
 
-adlb <- synthetic_cdisc_dataset("latest", "adlb")
+adlb <- random.cdisc.data::cadlb
 vl_lb <- var_labels(adlb)
 ```
 
@@ -153,7 +151,6 @@ plot
 ## {{< fa regular file-lines sm fw >}} Preview
 
 <!-- skip strict because of partial arg match in `bionom` https://github.com/cran/binom/blob/master/R/binom.confint.R#L31 -->
-
 ```{r plot5, test = list(plot_v5 = "plot"), opts.label = "skip_test_strict"}
 anl <- adlb %>%
   filter(PARAMCD == "ALT" & ANRIND == "HIGH")

diff --git a/book/graphs/other/bwg01.qmd b/book/graphs/other/bwg01.qmd
@@ -14,13 +14,11 @@ subtitle: Box Plot
 #| code-fold: show
 
 # generic code for all plots
-library(scda)
-library(scda.2022)
 library(dplyr)
 library(ggplot2)
 library(nestcolor)
 
-adlb <- synthetic_cdisc_dataset("latest", "adlb")
+adlb <- random.cdisc.data::cadlb
 adlb <- adlb %>% filter(PARAMCD == "ALT" & AVISIT == "WEEK 2 DAY 15")
 
 # Definition of boxplot boundaries and whiskers
@@ -244,8 +242,8 @@ plot
 
 <!-- skip strict because of https://github.com/r-lib/gtable/pull/94 -->
 ```{r plot6, test = list(plot_v6 = "plot"), opts.label = "skip_test_strict"}
-adsl <- synthetic_cdisc_dataset("latest", "adsl")
-adlb <- synthetic_cdisc_dataset("latest", "adlb")
+adsl <- random.cdisc.data::cadsl
+adlb <- random.cdisc.data::cadlb
 
 adlb_v <- adlb %>%
   filter(PARAMCD == "ALT" & AVISIT %in% c("WEEK 1 DAY 8", "WEEK 2 DAY 15", "WEEK 3 DAY 22", "WEEK 4 DAY 29"))
@@ -433,12 +431,10 @@ library(teal.modules.general)
 ## Data reproducible code
 data <- teal_data()
 data <- within(data, {
-  library(scda)
-  library(scda.2022)
   library(tern)
 
-  ADSL <- synthetic_cdisc_dataset("latest", "adsl")
-  ADLB <- synthetic_cdisc_dataset("latest", "adlb")
+  ADSL <- random.cdisc.data::cadsl
+  ADLB <- random.cdisc.data::cadlb
 
   # If PARAMCD and AVISIT are not factors, convert to factors
   # Also fill in missing values with "<Missing>"

diff --git a/book/graphs/other/cig01.qmd b/book/graphs/other/cig01.qmd
@@ -16,11 +16,9 @@ subtitle: Confidence Interval Plot
 library(tern)
 library(ggplot2)
 library(dplyr)
-library(scda)
-library(scda.2022)
 library(nestcolor)
 
-adlb <- synthetic_cdisc_dataset("latest", "adlb") %>%
+adlb <- random.cdisc.data::cadlb %>%
   filter(PARAMCD == "ALT", AVISIT == "BASELINE")
 ```
 
@@ -214,11 +212,8 @@ library(teal.modules.clinical)
 ## Data reproducible code
 data <- teal_data()
 data <- within(data, {
-  library(scda)
-  library(scda.2022)
-
-  ADSL <- synthetic_cdisc_dataset("latest", "adsl")
-  ADLB <- synthetic_cdisc_dataset("latest", "adlb")
+  ADSL <- random.cdisc.data::cadsl
+  ADLB <- random.cdisc.data::cadlb
 })
 datanames <- c("ADSL", "ADLB")
 datanames(data) <- datanames

diff --git a/book/graphs/other/ippg01.qmd b/book/graphs/other/ippg01.qmd
@@ -16,15 +16,13 @@ For illustration purposes, we will subset the `adlb` dataset for safety populati
 #| code-fold: show
 
 library(tern)
-library(scda)
-library(scda.2022)
 library(dplyr)
 library(ggplot2)
 library(nestcolor)
 
 # use small sample size
-adsl <- synthetic_cdisc_dataset("latest", "adsl") %>% slice(1:15)
-adlb <- synthetic_cdisc_dataset("latest", "adlb") %>% filter(USUBJID %in% adsl$USUBJID)
+adsl <- random.cdisc.data::cadsl %>% slice(1:15)
+adlb <- random.cdisc.data::cadlb %>% filter(USUBJID %in% adsl$USUBJID)
 
 # Ensure character variables are converted to factors and empty strings and NAs are explicit missing levels.
 adlb <- df_explicit_na(adlb)
@@ -113,13 +111,11 @@ library(teal.modules.clinical)
 ## Data reproducible code
 data <- teal_data()
 data <- within(data, {
-  library(scda)
-  library(scda.2022)
   library(dplyr)
 
   # use small sample size
-  ADSL <- synthetic_cdisc_dataset("latest", "adsl") %>% slice(1:15)
-  ADLB <- synthetic_cdisc_dataset("latest", "adlb") %>% filter(USUBJID %in% ADSL$USUBJID)
+  ADSL <- random.cdisc.data::cadsl %>% slice(1:15)
+  ADLB <- random.cdisc.data::cadlb %>% filter(USUBJID %in% ADSL$USUBJID)
 
   # Ensure character variables are converted to factors and empty strings and NAs are explicit missing levels.
   ADSL <- df_explicit_na(ADSL)

diff --git a/book/graphs/other/ltg01.qmd b/book/graphs/other/ltg01.qmd
@@ -15,17 +15,15 @@ Lattice plots are natively handled by R, the examples below rely mostly on the p
 ```{r setup, message = FALSE}
 #| code-fold: show
 
-library(scda)
-library(scda.2022)
 library(tern)
 library(teal.modules.clinical)
 library(ggplot2)
 library(dplyr)
 library(nestcolor)
 
 # Datasets
-adsl <- synthetic_cdisc_dataset("latest", "adsl") %>% slice(1:8)
-adlb <- synthetic_cdisc_dataset("latest", "adlb") %>% filter(USUBJID %in% adsl$USUBJID)
+adsl <- random.cdisc.data::cadsl %>% slice(1:8)
+adlb <- random.cdisc.data::cadlb %>% filter(USUBJID %in% adsl$USUBJID)
 
 # Pre-processing
 adlb$AVISIT_txt <- adlb$AVISIT
@@ -135,8 +133,8 @@ The example below suggests a larger dataset, where the individual subject legend
 #| code-fold: show
 
 # Datasets
-adsl <- synthetic_cdisc_dataset("latest", "adsl") %>% slice(1:40)
-adlb <- synthetic_cdisc_dataset("latest", "adlb") %>% filter(USUBJID %in% adsl$USUBJID)
+adsl <- random.cdisc.data::cadsl %>% slice(1:40)
+adlb <- random.cdisc.data::cadlb %>% filter(USUBJID %in% adsl$USUBJID)
 
 # Pre-processing
 adlb$AVISIT_txt <- adlb$AVISIT

diff --git a/book/graphs/other/mng01.qmd b/book/graphs/other/mng01.qmd
@@ -15,13 +15,11 @@ subtitle: Mean Plot
 
 library(dplyr)
 library(tern)
-library(scda)
-library(scda.2022)
 library(nestcolor)
 
-adsl <- synthetic_cdisc_dataset("latest", "adsl")
-adlb <- synthetic_cdisc_dataset("latest", "adlb")
-advs <- synthetic_cdisc_dataset("latest", "advs")
+adsl <- random.cdisc.data::cadsl
+adlb <- random.cdisc.data::cadlb
+advs <- random.cdisc.data::cadvs
 
 adsl_f <- adsl %>%
   filter(SAFFL == "Y") %>%
@@ -211,13 +209,11 @@ library(teal.modules.clinical)
 ## Data reproducible code
 data <- teal_data()
 data <- within(data, {
-  library(scda)
-  library(scda.2022)
   library(dplyr)
   library(forcats)
 
-  ADSL <- synthetic_cdisc_dataset("latest", "adsl")
-  ADLB <- synthetic_cdisc_dataset("latest", "adlb") %>%
+  ADSL <- random.cdisc.data::cadsl
+  ADLB <- random.cdisc.data::cadlb %>%
     mutate(AVISIT = fct_reorder(AVISIT, AVISITN, min))
 })
 datanames <- c("ADSL", "ADLB")

diff --git a/book/graphs/pharmacokinetic/pkcg01.qmd b/book/graphs/pharmacokinetic/pkcg01.qmd
@@ -14,13 +14,11 @@ subtitle: Plot of PK Concentration Over Time by Subject
 #| code-fold: show
 
 library(tern)
-library(scda)
-library(scda.2022)
 library(dplyr)
 library(ggplot2)
 library(nestcolor)
 
-adpc <- synthetic_cdisc_dataset("latest", "adpc")
+adpc <- random.cdisc.data::cadpc
 ```
 
 ## Plot in Linear Scale

diff --git a/book/graphs/pharmacokinetic/pkcg02.qmd b/book/graphs/pharmacokinetic/pkcg02.qmd
@@ -14,13 +14,11 @@ subtitle: Plot of PK Concentration Over Time by Cohort/Treatment Group/Dose
 #| code-fold: show
 
 library(tern)
-library(scda)
-library(scda.2022)
 library(dplyr)
 library(ggplot2)
 library(nestcolor)
 
-adpc <- synthetic_cdisc_dataset("latest", "adpc")
+adpc <- random.cdisc.data::cadpc
 ```
 
 ## Plot in Linear Scale