insightsengineering
[Bug]: MMRM in the efficacy gallery doesn't work.
What happened?
teal.gallery::launch_app("efficacy") starts nicely. All the tab works except MMRM which gives the following error message. Change to Kenward-Roger would produce the similar error message. Default is used for all the selection.
Relevant log output
unused argument (method = "Satterthwaite") when evaluating qenv code: anl <- ANL %>% dplyr::filter(ARM %in% c("A: Drug X", "B: Placebo", "C: Combination")) %>% dplyr::mutate(ARM = stats::relevel(ARM, ref = "A: Drug X")) %>% dplyr::mutate(ARM = droplevels(ARM)) %>% df_explicit_na(na_level = "") ANL_ADSL <- ANL_ADSL %>% dplyr::filter(ARM %in% c("A: Drug X", "B: Placebo", "C: Combination")) %>% dplyr::mutate(ARM = stats::relevel(ARM, ref = "A: Drug X")) %>% dplyr::mutate(ARM = droplevels(ARM)) %>% df_explicit_na(na_level = "") fit <- tern.mmrm::fit_mmrm(vars = list(response = "AVAL", covariates = NULL, id = "USUBJID", arm = "ARM", visit = "AVISIT"), data = anl, conf_level = 0.95, method = "Satterthwaite", cor_struct = "unstructured", weights_emmeans = "proportional", parallel = TRUE)
Code of Conduct
- [X] I agree to follow this project's Code of Conduct.
Contribution Guidelines
- [X] I agree to follow this project's Contribution Guidelines.
Security Policy
- [X] I agree to follow this project's Security Policy.
hey @JianWang2016 what is the output of your sessionInfo()? You can run it after your launch and turn off the teal app. This will be helpful in figuring out what combinations of packages do you have and whether you need to update one of them
Here is my sessionInfo() for which I get proper fit of the model in MMRM tab
R version 4.2.3 (2023-03-15 ucrt)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 19044)
Matrix products: default
locale:
[1] LC_COLLATE=English_Europe.utf8 LC_CTYPE=English_Europe.utf8 LC_MONETARY=English_Europe.utf8
[4] LC_NUMERIC=C LC_TIME=English_Europe.utf8
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] sparkline_2.0 nestcolor_0.1.2.9001 teal.modules.clinical_0.8.15.9006
[4] tern_0.8.4.9004 rtables_0.6.1.9010 formatters_0.5.0.9002
[7] teal.modules.general_0.2.15.9026 teal_0.13.0.9006 teal.transform_0.3.0.9003
[10] magrittr_2.0.3 teal.data_0.2.0.9003 shinyTree_0.2.7
[13] ggmosaic_0.3.3 ggplot2_3.4.2 scda.2022_0.1.4.9008
[16] scda_0.1.6.9004 dplyr_1.1.2 shiny_1.7.4.1
loaded via a namespace (and not attached):
[1] colorspace_2.1-0 ellipsis_0.3.2 rsconnect_0.8.29 rprojroot_2.0.3
[5] estimability_1.4.1 mmrm_0.2.2.9028 fs_1.6.2 rstudioapi_0.15.0
[9] remotes_2.4.2 ggrepel_0.9.3 DT_0.28 fansi_1.0.4
[13] mvtnorm_1.2-2 splines_4.2.3 R.methodsS3_1.8.2 cachem_1.0.8
[17] knitr_1.43 jsonlite_1.8.7 broom_1.0.5 geepack_1.3.9
[21] R.oo_1.25.0 compiler_4.2.3 httr_1.4.6 emmeans_1.8.7
[25] backports_1.4.1 assertthat_0.2.1 Matrix_1.5-3 fastmap_1.1.1
[29] lazyeval_0.2.2 cli_3.6.1 later_1.3.1 htmltools_0.5.5
[33] tools_4.2.3 gtable_0.3.3 glue_1.6.2 Rcpp_1.0.11
[37] jquerylib_0.1.4 styler_1.10.1 vctrs_0.6.2 nlme_3.1-162
[41] teal.logger_0.1.1.9007 crosstalk_1.2.0 xfun_0.39 stringr_1.5.0
[45] rbibutils_2.2.13 mime_0.12 lifecycle_1.0.3 shinyvalidate_0.1.2
[49] renv_1.0.0 staged.dependencies_0.2.8 MASS_7.3-58.2 scales_1.2.1
[53] promises_1.2.0.1 parallel_4.2.3 tern.gee_0.1.0.9006 TMB_1.9.4
[57] yaml_2.3.7 curl_5.0.1 memoise_2.0.1 teal.slice_0.3.0.9005
[61] teal.widgets_0.3.0.9003 sass_0.4.6 stringi_1.7.12 desc_1.4.2
[65] checkmate_2.2.0 teal.reporter_0.1.1.9016 teal.gallery_0.1.0.9010 Rdpack_2.4
[69] rlang_1.1.1 pkgconfig_2.0.3 evaluate_0.21 lattice_0.20-45
[73] teal.code_0.3.0.9006 fontawesome_0.5.1 purrr_1.0.1 htmlwidgets_1.6.2
[77] cowplot_1.1.1 tidyselect_1.2.0 parallelly_1.36.0 logger_0.2.2
[81] R6_2.5.1 generics_0.1.3 pillar_1.9.0 withr_2.5.0
[85] survival_3.5-3 tibble_3.2.1 shinyWidgets_0.7.6 utf8_1.2.3
[89] plotly_4.10.2 rmarkdown_2.23 grid_4.2.3 data.table_1.14.8
[93] git2r_0.32.0 forcats_1.0.0 digest_0.6.31 tern.mmrm_0.2.2.9005
[97] xtable_1.8-4 R.cache_0.16.0 tidyr_1.3.0 httpuv_1.6.11
[101] R.utils_2.12.2 munsell_0.5.0 viridisLite_0.4.2 bslib_0.5.0
[105] shinyjs_2.1.0
You can always run remove.packages('package_name') on few packages to remove them, and then install all dependencies of teal.gallery again with below code, run when in R working directory set to teal.gallery repository
if(!requireNamespace('remotes')) {
install.packages('remotes')
}
if(!requireNamespace('staged.dependencies')) {
remotes::install_github('openpharma/staged.dependencies')
}
x <- staged.dependencies::dependency_table(".")
staged.dependencies::install_deps(x, upgrade = "always")
This is the code I get after Fitting the model in MMRM tab
library(shiny)
library(dplyr)
library(scda)
library(scda.2022)
library(ggplot2)
library(ggmosaic)
library(shinyTree)
library(teal.data)
library(magrittr)
library(teal.transform)
library(teal)
library(teal.modules.general)
library(formatters)
library(rtables)
library(tern)
library(teal.modules.clinical)
library(nestcolor)
library(sparkline)
char_vars_asl <- c("STUDYID", "USUBJID", "SUBJID", "SITEID", "INVID", "INVNAM")
ADSL <- synthetic_cdisc_data("latest")$adsl
adsl_labels <- formatters::var_labels(ADSL, fill = FALSE)
adsl_labels <- c(adsl_labels, AGEGR1 = "Age Group")
ADSL <- ADSL %>%
mutate(AGEGR1 = factor(case_when(AGE < 45 ~ "<45", AGE >= 45 ~ ">=45"))) %>%
mutate_at(char_vars_asl, factor)
formatters::var_labels(ADSL) <- adsl_labels
ADQS <- synthetic_cdisc_data("latest")$adqs
adqs_labels <- formatters::var_labels(ADQS, fill = FALSE)
ADQS <- ADQS %>%
filter(ABLFL != "Y" & ABLFL2 != "Y") %>%
filter(AVISIT %in% c("WEEK 1 DAY 8", "WEEK 2 DAY 15", "WEEK 3 DAY 22")) %>%
mutate(AVISIT = as.factor(AVISIT), AVISITN = rank(AVISITN) %>% as.factor() %>% as.numeric() %>% as.factor())
formatters::var_labels(ADQS) <- adqs_labels
message(paste("Reproducibility of data import and preprocessing was not explicitly checked", " ('check = FALSE' is set). Contact app developer if this is an issue.\n"))
stopifnot(rlang::hash(ADSL) == "a09e28572f88ca759bd0a4c38febd757")
stopifnot(rlang::hash(ADQS) == "b77b3f0694b20595b4b9303b19b6ef36")
ADQS <- dplyr::inner_join(x = ADQS, y = ADSL[, c("STUDYID", "USUBJID"), drop = FALSE], by = c("STUDYID", "USUBJID"))
ANL_1 <- ADSL %>% dplyr::select(STUDYID, USUBJID, ARM)
ANL_2 <- ADQS %>%
dplyr::filter(PARAMCD == "FKSI-FWB") %>%
dplyr::select(STUDYID, USUBJID, PARAMCD, AVISIT)
ANL_3 <- ADQS %>% dplyr::select(STUDYID, USUBJID, PARAMCD, AVISIT, AVAL)
ANL <- ANL_1
ANL <- dplyr::inner_join(ANL, ANL_2, by = c("STUDYID", "USUBJID"))
ANL <- dplyr::inner_join(ANL, ANL_3, by = c("STUDYID", "USUBJID", "PARAMCD", "AVISIT"))
ANL <- ANL %>% formatters::var_relabel(ARM = "Description of Planned Arm", PARAMCD = "Parameter Code", USUBJID = "Unique Subject Identifier", AVISIT = "Analysis Visit", AVAL = "Analysis Value")
ANL_ADSL_1 <- ADSL %>% dplyr::select(STUDYID, USUBJID, ARM)
ANL_ADSL <- ANL_ADSL_1
ANL_ADSL <- ANL_ADSL %>% formatters::var_relabel(ARM = "Description of Planned Arm")
anl <- ANL %>%
dplyr::filter(ARM %in% c("A: Drug X", "B: Placebo", "C: Combination")) %>%
dplyr::mutate(ARM = stats::relevel(ARM, ref = "A: Drug X")) %>%
dplyr::mutate(ARM = droplevels(ARM)) %>%
df_explicit_na(na_level = "")
ANL_ADSL <- ANL_ADSL %>%
dplyr::filter(ARM %in% c("A: Drug X", "B: Placebo", "C: Combination")) %>%
dplyr::mutate(ARM = stats::relevel(ARM, ref = "A: Drug X")) %>%
dplyr::mutate(ARM = droplevels(ARM)) %>%
df_explicit_na(na_level = "")
fit <- tern.mmrm::fit_mmrm(vars = list(response = "AVAL", covariates = NULL, id = "USUBJID", arm = "ARM", visit = "AVISIT"), data = anl, conf_level = 0.95, method = "Satterthwaite", cor_struct = "unstructured", weights_emmeans = "proportional", parallel = TRUE)
lyt <- rtables::basic_table(subtitles = "Analysis Variable: AVAL, Endpoint: FKSI-FWB", main_footer = c("Weights for LS Means: proportional", "Correlation Structure: unstructured", "Adjustment Method: Satterthwaite")) %>%
rtables::split_cols_by(var = "ARM", ref_group = "A: Drug X") %>%
rtables::add_colcounts() %>%
rtables::split_rows_by("AVISIT") %>%
append_varlabels(ANL, "AVISIT") %>%
tern.mmrm::summarize_lsmeans(show_relative = "reduction") %>%
rtables::append_topleft(paste0(" ", structure(3,
levels = c("BFIALL", "FATIGI", "FKSI-FWB", "FKSI-TSE", "FKSIALL"), class = "factor"
)))
lsmeans_table <- rtables::build_table(lyt = lyt, df = df_explicit_na(broom::tidy(fit), na_level = ""), alt_counts_df = ANL_ADSL)
lsmeans_table