Merge branch 'main' into 1301-feature-request-add-confidence-interval…

…s-for-quantiles-in-surv_time
insightsengineering · Oct 23, 2024 · 11d7726 · 11d7726
2 parents 700fc94 + de68073
commit 11d7726
Show file tree

Hide file tree

Showing 77 changed files with 459 additions and 308 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,7 +1,7 @@
 ---
 # All available hooks: https://pre-commit.com/hooks.html
 # R specific hooks: https://github.com/lorenzwalthert/precommit
-default_stages: [commit]
+default_stages: [pre-commit]
 default_language_version:
   python: python3
 repos:

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: tern
 Title: Create Common TLGs Used in Clinical Trials
-Version: 0.9.6.9001
-Date: 2024-09-30
+Version: 0.9.6.9007
+Date: 2024-10-20
 Authors@R: c(
     person("Joe", "Zhu", , "[email protected]", role = c("aut", "cre")),
     person("Daniel", "Sabanés Bové", , "[email protected]", role = "aut"),
@@ -48,7 +48,7 @@ Imports:
     rlang (>= 1.1.0),
     scales (>= 1.2.0),
     stats,
-    survival (>= 3.2-13),
+    survival (>= 3.6-4),
     tibble (>= 2.0.0),
     tidyr (>= 0.8.3),
     utils

diff --git a/NEWS.md b/NEWS.md
@@ -1,4 +1,7 @@
-# tern 0.9.6.9001
+# tern 0.9.6.9007
+
+### Bug Fixes
+* Fixed bug in `a_summary()` causing non-unique `row_name` values to occur when multiple statistics are selected for count variables.
 
 # tern 0.9.6
 
@@ -16,6 +19,7 @@
 * Refactored `estimate_incidence_rate` to work as both an analyze function and a summarize function, controlled by the added `summarize` parameter. When `summarize = TRUE`, labels can be fine-tuned via the new `label_fmt` argument to the same function.
 * Added `fraction` statistic to the `analyze_var_count` method group.
 * Improved `summarize_glm_count()` documentation and all its associated functions to better describe the results and the functions' purpose.
+* Added `method` argument to `s_odds_ratio()` and `estimate_odds_ratio()` to control whether exact or approximate conditional likelihood calculations are used. 
 
 ### Bug Fixes
 * Added defaults for `d_count_cumulative` parameters as described in the documentation.

diff --git a/R/abnormal.R b/R/abnormal.R
@@ -23,8 +23,9 @@
 #'   for example, `abnormal = list(Low = c("LOW", "LOW LOW"), High = c("HIGH", "HIGH HIGH"))`.
 #' @param exclude_base_abn (`flag`)\cr whether to exclude subjects with baseline abnormality
 #'   from numerator and denominator.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("abnormal")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("abnormal"))``
 #'
 #' @note
 #' * `count_abnormal()` only considers a single variable that contains multiple abnormal levels.

diff --git a/R/abnormal_by_baseline.R b/R/abnormal_by_baseline.R
@@ -29,8 +29,9 @@
 #'
 #' @inheritParams argument_convention
 #' @param abnormal (`character`)\cr values identifying the abnormal range level(s) in `.var`.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("abnormal_by_baseline")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("abnormal_by_baseline"))``
 #'
 #' @note
 #' * `df` should be filtered to include only post-baseline records.

diff --git a/R/abnormal_by_marked.R b/R/abnormal_by_marked.R
@@ -28,8 +28,9 @@
 #' @inheritParams argument_convention
 #' @param category (`list`)\cr a list with different marked category names for single
 #'   and last or replicated.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("abnormal_by_marked")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("abnormal_by_marked"))``
 #'
 #' @note `Single, not last` and `Last or replicated` levels are mutually exclusive. If a patient has
 #'   abnormalities that meet both the `Single, not last` and `Last or replicated` criteria, then the

diff --git a/R/abnormal_by_worst_grade.R b/R/abnormal_by_worst_grade.R
@@ -27,8 +27,9 @@
 #' splits, one on variable `param` and one on variable `grade_dir`.
 #'
 #' @inheritParams argument_convention
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("abnormal_by_worst_grade")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("abnormal_by_worst_grade"))``
 #'
 #' @seealso [h_adlb_abnormal_by_worst_grade()] which pre-processes ADLB data frames to be used in
 #'   [count_abnormal_by_worst_grade()].

diff --git a/R/abnormal_by_worst_grade_worsen.R b/R/abnormal_by_worst_grade_worsen.R
@@ -28,8 +28,9 @@
 #'   * `id` (`string`)\cr subject variable name.
 #'   * `baseline_var` (`string`)\cr name of the data column containing baseline toxicity variable.
 #'   * `direction_var` (`string`)\cr see `direction_var` for more details.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("abnormal_by_worst_grade_worsen")`
-#'   to see all available statistics.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("abnormal_by_worst_grade_worsen"))``
 #'
 #' @seealso Relevant helper functions [h_adlb_worsen()] and [h_worsen_counter()] which are used within
 #' [s_count_abnormal_lab_worsen_by_baseline()] to process input data.

diff --git a/R/analyze_variables.R b/R/analyze_variables.R
@@ -45,9 +45,11 @@ control_analyze_vars <- function(conf_level = 0.95,
 #' columns) will be considered (`.df_row[[.var]]`, see [`rtables::additional_fun_params`]) and not the whole dataset.
 #'
 #' @inheritParams argument_convention
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("analyze_vars_numeric")` to see
-#'   statistics available for numeric variables, and `get_stats("analyze_vars_counts")` for statistics available
-#'   for non-numeric variables.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options for numeric variables are: ``r shQuote(get_stats("analyze_vars_numeric"))``
+#'
+#'   Options for non-numeric variables are: ``r shQuote(get_stats("analyze_vars_counts"))``
 #'
 #' @name analyze_variables
 #' @order 1
@@ -539,7 +541,7 @@ a_summary <- function(x,
   in_rows(
     .list = x_stats,
     .formats = .formats,
-    .names = .labels,
+    .names = names(.labels),
     .labels = .labels,
     .indent_mods = .indent_mods,
     .format_na_strs = na_str

diff --git a/R/bland_altman.R b/R/bland_altman.R
@@ -2,29 +2,32 @@
 #'
 #' @description `r lifecycle::badge("experimental")`
 #'
-#' Functions that use the Bland-Altman method to assess the agreement between two numerical vectors.
+#' Statistics function that uses the Bland-Altman method to assess the agreement between two numerical vectors
+#' and calculates a variety of statistics.
 #'
 #' @inheritParams argument_convention
 #' @param y (`numeric`)\cr vector of numbers we want to analyze, to be compared with `x`.
 #'
-#' @name bland_altman
-NULL
-
-#' @describeIn bland_altman Statistics function that compares two numeric vectors using the Bland-Altman method
-#'   and calculates a variety of statistics.
-#'
 #' @return
-#' * `s_bland_altman()` returns a named list of the following elements: `df`, `difference_mean`, `ci_mean`,
-#'   `difference_sd`, `difference_se`, `upper_agreement_limit`, `lower_agreement_limit`, `agreement_limit_se`,
-#'   `upper_agreement_limit_ci`, `lower_agreement_limit_ci`, `t_value`, and `n`.
+#' A named list of the following elements:
+#'   * `df`
+#'   * `difference_mean`
+#'   * `ci_mean`
+#'   * `difference_sd`
+#'   * `difference_se`
+#'   * `upper_agreement_limit`
+#'   * `lower_agreement_limit`
+#'   * `agreement_limit_se`
+#'   * `upper_agreement_limit_ci`
+#'   * `lower_agreement_limit_ci`
+#'   * `t_value`
+#'   * `n`
 #'
 #' @examples
 #' x <- seq(1, 60, 5)
 #' y <- seq(5, 50, 4)
-#' conf_level <- 0.9
 #'
-#' # Derive statistics that are needed for Bland-Altman plot
-#' s_bland_altman(x, y, conf_level = conf_level)
+#' s_bland_altman(x, y, conf_level = 0.9)
 #'
 #' @export
 s_bland_altman <- function(x, y, conf_level = 0.95) {
@@ -75,16 +78,24 @@ s_bland_altman <- function(x, y, conf_level = 0.95) {
   )
 }
 
-#' @describeIn bland_altman Graphing function that produces a Bland-Altman plot.
+#' Bland-Altman plot
 #'
-#' @return
-#' * `g_bland_altman()` returns a `ggplot` Bland-Altman plot.
+#' @description `r lifecycle::badge("experimental")`
+#'
+#' Graphing function that produces a Bland-Altman plot.
+#'
+#' @inheritParams s_bland_altman
+#'
+#' @return A `ggplot` Bland-Altman plot.
 #'
 #' @examples
-#' # Create a Bland-Altman plot
-#' g_bland_altman(x = x, y = y, conf_level = conf_level)
+#' x <- seq(1, 60, 5)
+#' y <- seq(5, 50, 4)
+#'
+#' g_bland_altman(x = x, y = y, conf_level = 0.9)
 #'
 #' @export
+#' @aliases bland_altman
 g_bland_altman <- function(x, y, conf_level = 0.95) {
   result_tem <- s_bland_altman(x, y, conf_level = conf_level)
   xpos <- max(result_tem$df$average) * 0.9 + min(result_tem$df$average) * 0.1

diff --git a/R/compare_variables.R b/R/compare_variables.R
@@ -14,9 +14,11 @@
 #' statistic.
 #'
 #' @inheritParams argument_convention
-#' @param .stats (`character`)\cr statistics to select for the table. Run
-#'   `get_stats("analyze_vars_numeric", add_pval = TRUE)` to see statistics available for numeric variables, and
-#'   `get_stats("analyze_vars_counts", add_pval = TRUE)` for statistics available for non-numeric variables.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options for numeric variables are: ``r shQuote(get_stats("analyze_vars_numeric", add_pval = TRUE))``
+#'
+#'   Options for non-numeric variables are: ``r shQuote(get_stats("analyze_vars_counts", add_pval = TRUE))``
 #'
 #' @note
 #' * For factor variables, `denom` for factor proportions can only be `n` since the purpose is to compare proportions

diff --git a/R/count_cumulative.R b/R/count_cumulative.R
@@ -14,8 +14,9 @@
 #' @inheritParams h_count_cumulative
 #' @inheritParams argument_convention
 #' @param thresholds (`numeric`)\cr vector of cutoff values for the counts.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("count_cumulative")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("count_cumulative"))``
 #'
 #' @seealso Relevant helper function [h_count_cumulative()], and descriptive function [d_count_cumulative()].
 #'

diff --git a/R/count_missed_doses.R b/R/count_missed_doses.R
@@ -12,8 +12,9 @@
 #' @inheritParams s_count_cumulative
 #' @inheritParams argument_convention
 #' @param thresholds (`numeric`)\cr minimum number of missed doses the patients had.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("count_missed_doses")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("count_missed_doses"))``
 #'
 #' @seealso
 #' * Relevant description function [d_count_missed_doses()] which generates labels for [count_missed_doses()].

diff --git a/R/count_occurrences.R b/R/count_occurrences.R
@@ -17,8 +17,9 @@
 #' @inheritParams argument_convention
 #' @param drop (`flag`)\cr whether non-appearing occurrence levels should be dropped from the resulting table.
 #'   Note that in that case the remaining occurrence levels in the table are sorted alphabetically.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("count_occurrences")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("count_occurrences"))``
 #'
 #' @note By default, occurrences which don't appear in a given row split are dropped from the table and
 #'   the occurrences in the table are sorted alphabetically per row split. Therefore, the corresponding layout

diff --git a/R/count_occurrences_by_grade.R b/R/count_occurrences_by_grade.R
@@ -24,8 +24,9 @@
 #' @param only_grade_groups (`flag`)\cr whether only the specified grade groups should be
 #'   included, with individual grade rows removed (`TRUE`), or all grades and grade groups
 #'   should be displayed (`FALSE`).
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("count_occurrences_by_grade")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("count_occurrences_by_grade"))``
 #'
 #' @seealso Relevant helper function [h_append_grade_groups()].
 #'

diff --git a/R/count_patients_events_in_cols.R b/R/count_patients_events_in_cols.R
@@ -19,9 +19,10 @@
 #'   that corresponding table cells will stay blank.
 #' @param custom_label (`string` or `NULL`)\cr if provided and `labelstr` is empty then this will
 #'   be used as label.
-#' @param .stats (`character`)\cr statistics to select for the table. Run
-#'   `get_stats("summarize_patients_events_in_cols")` to see available statistics for this function, in addition
-#'   to any added using `filters_list`.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   In addition to any statistics added using `filters_list`, statistic options are:
+#'   ``r shQuote(get_stats("summarize_patients_events_in_cols"))``
 #'
 #' @name count_patients_events_in_cols
 #' @order 1

diff --git a/R/count_patients_with_event.R b/R/count_patients_with_event.R
@@ -17,8 +17,9 @@
 #'   Multiple column names and flags are accepted in this format
 #'   `c("column_name1" = "flag1", "column_name2" = "flag2")`.
 #'   Note that only equality is being accepted as condition.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("count_patients_with_event")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("count_patients_with_event"))``
 #'
 #' @seealso [count_patients_with_flags]
 #'

diff --git a/R/count_patients_with_flags.R b/R/count_patients_with_flags.R
@@ -15,8 +15,9 @@
 #' @param flag_variables (`character`)\cr a vector specifying the names of `logical` variables from analysis dataset
 #'   used for counting the number of unique identifiers.
 #' @param flag_labels (`character`)\cr vector of labels to use for flag variables.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("count_patients_with_flags")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("count_patients_with_flags"))``
 #'
 #' @seealso [count_patients_with_event]
 #'

diff --git a/R/count_values.R b/R/count_values.R
@@ -11,8 +11,9 @@
 #'
 #' @inheritParams argument_convention
 #' @param values (`character`)\cr specific values that should be counted.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("count_values")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("count_values"))``
 #'
 #' @note
 #' * For `factor` variables, `s_count_values` checks whether `values` are all included in the levels of `x`

diff --git a/R/estimate_multinomial_rsp.R b/R/estimate_multinomial_rsp.R
@@ -7,8 +7,9 @@
 #' `var`, should be a factor variable, the values of which will be used as labels within the output table.
 #'
 #' @inheritParams argument_convention
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("estimate_multinomial_response")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("estimate_multinomial_response"))``
 #'
 #' @seealso Relevant description function [d_onco_rsp_label()].
 #'

diff --git a/R/estimate_proportion.R b/R/estimate_proportion.R
@@ -10,12 +10,13 @@
 #'
 #' @inheritParams prop_strat_wilson
 #' @inheritParams argument_convention
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("estimate_proportion")`
-#'   to see available statistics for this function.
 #' @param method (`string`)\cr the method used to construct the confidence interval
 #'   for proportion of successful outcomes; one of `waldcc`, `wald`, `clopper-pearson`,
 #'   `wilson`, `wilsonc`, `strat_wilson`, `strat_wilsonc`, `agresti-coull` or `jeffreys`.
 #' @param long (`flag`)\cr whether a long description is required.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("estimate_proportion"))``
 #'
 #' @seealso [h_proportions]
 #'

diff --git a/R/formatting_functions.R b/R/formatting_functions.R
@@ -1,7 +1,5 @@
 #' Formatting functions
 #'
-#' @description `r lifecycle::badge("stable")`
-#'
 #' See below for the list of formatting functions created in `tern` to work with `rtables`.
 #'
 #' Other available formats can be listed via [`formatters::list_valid_format_labels()`]. Additional

diff --git a/R/incidence_rate.R b/R/incidence_rate.R
@@ -19,8 +19,9 @@
 #' @param n_events (`string`)\cr name of integer variable indicating whether an event has been observed (1) or not (0).
 #' @param id_var (`string`)\cr name of variable used as patient identifier if `"n_unique"` is included in `.stats`.
 #'   Defaults to `"USUBJID"`.
-#' @param .stats (`character`)\cr statistics to select for the table. Run `get_stats("estimate_incidence_rate")`
-#'   to see available statistics for this function.
+#' @param .stats (`character`)\cr statistics to select for the table.
+#'
+#'   Options are: ``r shQuote(get_stats("estimate_incidence_rate"))``
 #' @param summarize (`flag`)\cr whether the function should act as an analyze function (`summarize = FALSE`), or a
 #'   summarize function (`summarize = TRUE`). Defaults to `FALSE`.
 #' @param label_fmt (`string`)\cr how labels should be formatted after a row split occurs if `summarize = TRUE`. The