Merge pull request #47 from GSK-Biostatistics/exmples

Adding examples
GSK-Biostatistics · Jun 17, 2024 · 69b8aec · 69b8aec
2 parents fb7f58f + a55dfdc
commit 69b8aec
Show file tree

Hide file tree

Showing 15 changed files with 191 additions and 232 deletions.
diff --git a/R/post.R b/R/post.R
@@ -50,6 +50,13 @@
 #' @importFrom dplyr pull
 #' @importFrom purrr safely map map2
 #' @importFrom distributional dist_normal dist_mixture is_distribution parameters
+#' @examples
+#' library(distributional)
+#' library(dplyr)
+#' post_treated <- calc_post_norm(internal_data = filter(int_norm_df, trt == 1),
+#'                                response = y,
+#'                                prior = dist_normal(50, 10),
+#'                                internal_sd = 0.15)
 #'
 calc_post_norm<- function(
     internal_data,
@@ -150,12 +157,13 @@ calc_post_norm<- function(
 #' @importFrom dplyr pull
 #' @importFrom purrr safely map map2
 #' @importFrom distributional dist_beta dist_mixture is_distribution parameters
-#'
-calc_post_beta<- function(
-    internal_data,
-    response,
-    prior
-){
+#' @examples
+#' library(dplyr)
+#' library(distributional)
+#' calc_post_beta(internal_data = filter(int_binary_df, trt == 1),
+#'                               response = y,
+#'                               prior = dist_beta(0.5, 0.5))
+calc_post_beta<- function(internal_data, response, prior){
   # Checking internal data and response variable
   if(is_prop_scr(internal_data)){
     data <- internal_data$internal_df

diff --git a/R/ps.R b/R/ps.R
@@ -48,6 +48,20 @@
 #' @importFrom dplyr mutate filter tibble as_tibble
 #' @importFrom stats glm
 #' @importFrom cobalt bal.tab
+#' @examples
+#' # This can be used for both continuous and binary data
+#' library(dplyr)
+#' # Continuous
+#' calc_prop_scr(internal_df = filter(int_norm_df, trt == 0),
+#'                        external_df = ex_norm_df,
+#'                        id_col = subjid,
+#'                        model = ~ cov1 + cov2 + cov3 + cov4)
+#' # Binary
+#' calc_prop_scr(internal_df = filter(int_binary_df, trt == 0),
+#'                        external_df = ex_binary_df,
+#'                        id_col = subjid,
+#'                        model = ~ cov1 + cov2 + cov3 + cov4)
+#'
 calc_prop_scr <- function(internal_df, external_df,
                             id_col, model, ...){
   if(!is_formula(model)){
@@ -197,6 +211,14 @@ glance.prop_scr <- function(x, ...){
 #'
 #' @return Boolean
 #' @export
+#' @examples
+#' library(dplyr)
+#' x <- calc_prop_scr(internal_df = filter(int_norm_df, trt == 0),
+#'                        external_df = ex_norm_df,
+#'                        id_col = subjid,
+#'                        model = ~ cov1 + cov2 + cov3 + cov4)
+#' is_prop_scr(x)
+#'
 is_prop_scr <- function(x){
   inherits(x, "prop_scr")
 }
@@ -237,6 +259,16 @@ test_prop_scr <- function(x){
 #'    theme_bw
 #' @importFrom dplyr bind_rows
 #' @importFrom stringr str_glue
+#' @examples
+#' library(dplyr)
+#' ps_obj <- calc_prop_scr(internal_df = filter(int_norm_df, trt == 0),
+#'                        external_df = ex_norm_df,
+#'                        id_col = subjid,
+#'                        model = ~ cov1 + cov2 + cov3 + cov4)
+#' # Plotting the Propensity Scores
+#' prop_scr_hist(ps_obj)
+#' # Or plotting the inverse probability weights
+#' prop_scr_hist(ps_obj, variable = "ipw")
 prop_scr_hist <- function(x, variable = c("propensity score", "ps", "inverse probability weight", "ipw"),
                           ...){
   test_prop_scr(x)
@@ -293,6 +325,17 @@ prop_scr_hist <- function(x, variable = c("propensity score", "ps", "inverse pro
 #'   theme_bw
 #' @importFrom dplyr bind_rows
 #' @importFrom stringr str_glue
+#' @examples
+#' library(dplyr)
+#' ps_obj <- calc_prop_scr(internal_df = filter(int_norm_df, trt == 0),
+#'                        external_df = ex_norm_df,
+#'                        id_col = subjid,
+#'                        model = ~ cov1 + cov2 + cov3 + cov4)
+#' # Plotting the Propensity Scores
+#' prop_scr_dens(ps_obj)
+#' # Or plotting the inverse probability weights
+#' prop_scr_dens(ps_obj, variable = "ipw")
+#'
 prop_scr_dens <- function(x, variable = c("propensity score", "ps", "inverse probability weight", "ipw"),
                           ...){
   test_prop_scr(x)
@@ -348,6 +391,15 @@ prop_scr_dens <- function(x, variable = c("propensity score", "ps", "inverse pro
 #' @importFrom ggplot2 ggplot aes geom_point labs scale_color_manual ggtitle
 #'   theme_bw geom_vline
 #' @importFrom tidyr pivot_longer
+#' @examples
+#' library(dplyr)
+#' ps_obj <- calc_prop_scr(internal_df = filter(int_norm_df, trt == 0),
+#'                        external_df = ex_norm_df,
+#'                        id_col = subjid,
+#'                        model = ~ cov1 + cov2 + cov3 + cov4)
+#' # Plotting the Propensity Scores
+#' prop_scr_love(ps_obj, reference_line = 0.1)
+#'
 prop_scr_love <- function(x, reference_line = NULL, ...){
   test_prop_scr(x)
 

diff --git a/R/utils.R b/R/utils.R
@@ -1,6 +1,8 @@
 #' Plot Distribution
 #'
-#' @param ... Distributional object(s) to plot. If there are multiple objects you can name them.
+#' @param ... Distributional object(s) to plot. When passing multiple objects
+#'   naming them will change the labels in the plot, else they will use the
+#'   distributional format
 #'
 #' @return ggplot object that is the density of the provided distribution
 #' @export
@@ -9,6 +11,12 @@
 #' @importFrom ggplot2 ggplot theme_bw
 #' @importFrom ggdist stat_slabinterval
 #' @importFrom purrr map_chr map_lgl
+#' @examples
+#' library(distributional)
+#' plot_dist(dist_normal(0, 1))
+#' #Plotting Multiple
+#' plot_dist(dist_normal(0, 1), dist_normal(10, 5))
+#' plot_dist('Prior' = dist_normal(0, 1), 'Posterior' = dist_normal(10, 5))
 plot_dist <- function(...){
   input <- list(...)
   if(!all(map_lgl(input, is_distribution))){
@@ -20,7 +28,7 @@ plot_dist <- function(...){
   fill_alpha <- ifelse(n > 1, 0.5, 1)
   if(is.null(Distributions) & n > 1){
     Distributions <- map_chr(input, format)
-    if(unique(Distributions) != n)
+    if(length(unique(Distributions)) != n)
       Distributions <- paste0(1:n,": ", Distributions)
 
   }

diff --git a/README.Rmd b/README.Rmd
@@ -2,7 +2,6 @@
 output: github_document
 ---
 
-
 ```{r, include = FALSE}
 knitr::opts_chunk$set(
   collapse = TRUE,
@@ -13,114 +12,36 @@ knitr::opts_chunk$set(
 ```
 
 # beastt
-## Bayesian Evaluation, Analysis, and Simulation Software Tools for Trials (BEASTT)
+
+## Bayesian Evaluation, Analysis, and Simulation Software Tools for Trials (beastt)
 
 <!-- badges: start -->
-[![Lifecycle: experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html#experimental)
-[![CRAN status](https://www.r-pkg.org/badges/version/beastt)](https://CRAN.R-project.org/package=beastt)
-[![R-CMD-check](https://github.com/GSK-Biostatistics/beastt/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/GSK-Biostatistics/beastt/actions/workflows/R-CMD-check.yaml)
+
+[![Lifecycle: experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html#experimental) [![CRAN status](https://www.r-pkg.org/badges/version/beastt)](https://CRAN.R-project.org/package=beastt) [![R-CMD-check](https://github.com/GSK-Biostatistics/beastt/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/GSK-Biostatistics/beastt/actions/workflows/R-CMD-check.yaml)
+
 <!-- badges: end -->
 
 ## Overview
 
-Welcome to the "beastt" package! This R package is designed to assist users in performing
-Bayesian dynamic borrowing with covariate adjustment via inverse probability weighting for
-simulations and data analyses in clinical trials.
+Welcome to the "beastt" package! This R package is designed to assist users in performing Bayesian dynamic borrowing with covariate adjustment via inverse probability weighting for simulations and data analyses in clinical trials.
 
 ## Installation
 
-You can install the development version of beastt from [GitHub](https://github.com/) with:
+You can install the development version of {beastt} from [GitHub](https://github.com/) with:
 
 ``` r
 # install.packages("devtools")
 devtools::install_github("GSK-Biostatistics/beastt")
 ```
 
-## Functions
-
-### `calc_prop_scr()`
-
-Calculate propensity scores using this function and obtain the inverse probability weight 
-calculated for each subject. Propensity scores are essential in order to balance baseline
-covariate distributions between internal and external trial participants.
-
-**Usage:**
-
-```R
-calc_prop_scr(internal_df, external_df, id_col, model)
-```
-
-- `internal_df`: Internal dataset.
-- `external_df`: External dataset.
-- `id_col`: Name of the column in both datasets used to identify each subject.
-- `model`: Model used to calculate propensity scores.
-
-### `calc_power_prior()`
-
-Calculate power priors based on a distribution, hyperparameters, a weighted object and a response variable. 
-Power priors provide a Bayesian framework for incorporating external information into the analysis.
-
-**Usage:**
-
-```R
-calc_power_prior(prior, weighted_obj, response)
-```
-
-- `prior`: A {distributional} object that is the prior of the external data.
-- `weighted_obj`: A weighted object created by calling `calc_prop_scr()`.
-- `response`: Name of the response variable.
-- `...`: Additional parameters needed depending on the type of power prior used.
-
-## Examples
-
-Here are some examples demonstrating the usage of the package:
-
-```R
-library(beastt)
-library(ggdist)
-library(ggplot2)
-
-set.seed(1234)
+## Usage
 
-# Create internal and external datasets
-internal_df <- data.frame(id_col = 1:20, cov1 = rnorm(10, 2), cov2 = rnorm(100, 20), 
-                          y = rnorm(20, mean = 5, sd = 3)
-external_df <- data.frame(id_col = 21:40, cov1 = rnorm(10, 2), cov2 = rnorm(100, 18), 
-                          y = rnorm(20, mean = 8, sd = 4)
-
-# Example for propensity score calculation
-model <- as.formula("~cov1 + cov2")
-psscores <- calc_prop_scr(internal_df = internal_df, external_df = external_df, 
-                           id_col = id_col, model = model)
-
-# Example for power prior calculation using a Normal prior for external data
-powerprior <- calc_power_prior(prior = dist_normal(15, 100), weighted_obj = psscores, 
-                               response = y)
-
-# Plot power prior and interval
-ggplot(tibble(), aes(xdist = powerprior, y = 1)) +
-  stat_slabinterval()
-```
+At the moment {beastt} covers cases when borrowing from external control data with either normal or binary endpoints. For more information, see the vignettes. Future updates are expected to include cases with survival endpoints and repeated measure.
 
 ## Contributing
 
-Feel free to contribute to the "beastt" package by reporting issues or submitting pull requests on the GitHub repository.
+Feel free to contribute to the {beastt} package by reporting issues or submitting pull requests on the GitHub repository.
 
 ## License
 
-This package is released under the [Apache License](>= 2).
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+This package is released under the [Apache License](%3E=%202).