Merge pull request #84 from NSAPH-Software/JOSS

Joss

Author: Naeemkh

.github/workflows/R-CMD-check.yaml

@@ -23,7 +23,7 @@ jobs:
       matrix:
         config:
           - {os: windows-latest, r: 'release'}
-          #- {os: macOS-latest, r: 'release'} #deactivate until snprintf issue resolves.
+          - {os: macOS-latest, r: 'release'}
           - {os: ubuntu-20.04, r: 'release', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
           #- {os: ubuntu-20.04, r: 'devel', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
 

NEWS.md

@@ -5,6 +5,11 @@
 - `estimate_cerf_nngp` takes `outcome_col`, `treatment_col`, and `covariates_col` names as inputs.
 - `estimate_cerf_gp` takes `outcome_col`, `treatment_col`, and `covariates_col` names as inputs.
 
+## Added
+
+- `estimate_cerf_gp` and `estimate_cerf_nngp` have notes on selecting `w`.
+
+
 
 # GPCERF 0.2.2 (2024-02-16)
 

R/estimate_cerf_gp.R

@@ -7,7 +7,8 @@
 #' for the provided set of hyperparameters.
 #'
 #' @param data A data.frame of observation data.
-#' @param w A vector of exposure level to compute CERF.
+#' @param w A vector of exposure level to compute CERF (please also see the
+#' notes).
 #' @param gps_m An S3 gps object including:
 #'   gps: A data.frame of GPS vectors.
 #'     - Column 1: GPS
@@ -31,6 +32,18 @@
 #' used by internal packages.
 #' @param kernel_fn A kernel function. A default value is a Gaussian Kernel.
 #'
+#' @note
+#' Please note that `w` is a vector representing a grid of exposure levels at
+#' which the CERF is to be estimated. This grid can include both observed and
+#' hypothetical values of the exposure variable. The purpose of defining this
+#' grid is to provide a structured set of points across the exposure spectrum
+#' for estimating the CERF. This approach is essential in nonparametric models
+#' like Gaussian Processes (GPs), where the CERF is evaluated at specific points
+#' to understand the relationship between the exposure and outcome variables
+#' across a continuum. It facilitates a comprehensive analysis by allowing
+#' practitioners to examine the effect of varying exposure levels, including
+#' those not directly observed in the dataset.
+#'
 #' @return
 #' A cerf_gp object that includes the following values:
 #'  - w, the vector of exposure levels.
@@ -221,8 +234,6 @@ estimate_cerf_gp <- function(data, w, gps_m, params,
       })
   }
 
-  logger::log_debug("Number of generated tuning results: {length(tune_res)}")
-
   # Tuning results include:
   # cb: covariate balance for each confounder. This is the average of all
   #     all covariate balance for each requested exposure values.
@@ -235,6 +246,7 @@ estimate_cerf_gp <- function(data, w, gps_m, params,
   # Select the combination of hyperparameters that provides the lowest
   # covariate balance ----------------------------------------------------------
   if (nrow(tune_params_subset) > 1) {
+    logger::log_debug("Number of generated tuning results: {length(tune_res)}")
     opt_idx <- order(sapply(tune_res, function(x) {mean(x$cb)}))[1]
   } else {
     opt_idx <- 1

R/estimate_cerf_nngp.R

@@ -8,7 +8,8 @@
 #' match (the lowest covariate balance) for the provided set of hyperparameters.
 #'
 #' @param data A data.frame of observation data.
-#' @param w A vector of exposure level to compute CERF.
+#' @param w A vector of exposure level to compute CERF (please also see the
+#' notes).
 #' @param gps_m An S3 gps object including:
 #'   gps: A data.frame of GPS vectors.
 #'     - Column 1: GPS
@@ -36,6 +37,18 @@
 #' @param nthread An integer value that represents the number of threads to be
 #' used by internal packages.
 #'
+#' @note
+#' Please note that `w` is a vector representing a grid of exposure levels at
+#' which the CERF is to be estimated. This grid can include both observed and
+#' hypothetical values of the exposure variable. The purpose of defining this
+#' grid is to provide a structured set of points across the exposure spectrum
+#' for estimating the CERF. This approach is essential in nonparametric models
+#' like Gaussian Processes (GPs), where the CERF is evaluated at specific points
+#' to understand the relationship between the exposure and outcome variables
+#' across a continuum. It facilitates a comprehensive analysis by allowing
+#' practitioners to examine the effect of varying exposure levels, including
+#' those not directly observed in the dataset.
+#'
 #' @return
 #' A cerf_nngp object that includes the following values:
 #'  - w, the vector of exposure levels.

README.md

@@ -73,12 +73,12 @@ Optimal hyper parameters(#trial: 300):
   alpha = 12.9154966501488   beta = 12.9154966501488   g_sigma = 0.1
 
 Optimal covariate balance: 
-  cf1 = 0.072 
+  cf1 = 0.069 
   cf2 = 0.082 
-  cf3 = 0.062 
-  cf4 = 0.068 
+  cf3 = 0.063 
+  cf4 = 0.066 
   cf5 = 0.056 
-  cf6 = 0.082
+  cf6 = 0.081
 
 Original covariate balance: 
   cf1 = 0.222 
@@ -87,7 +87,7 @@ Original covariate balance:
   cf4 = 0.318 
   cf5 = 0.198 
   cf6 = 0.257
-            ----***----       
+            ----***----      
 ```
 
 <p>
@@ -148,10 +148,10 @@ Optimal hyper parameters(#trial: 300):
   alpha = 0.0278255940220712   beta = 0.215443469003188   g_sigma = 0.1
 
 Optimal covariate balance: 
-  cf1 = 0.058 
-  cf2 = 0.071 
-  cf3 = 0.087 
-  cf4 = 0.066 
+  cf1 = 0.062 
+  cf2 = 0.070 
+  cf3 = 0.091 
+  cf4 = 0.062 
   cf5 = 0.076 
   cf6 = 0.088
 
@@ -162,7 +162,7 @@ Original covariate balance:
   cf4 = 0.296 
   cf5 = 0.208 
   cf6 = 0.225
-            ----***----                    
+            ----***----                       
 ```
 
 <p>

docker_singularity/Dockerfile

@@ -30,9 +30,9 @@ RUN R -e "install.packages(c( \
     'rlang', \
     'Rfast', \
     'SuperLearner', \
+    'ranger', \
     'wCorr'), repos='https://cloud.r-project.org')"
 
-ENV RENV_VERSION 0.15.1
 RUN R -e "install.packages('remotes', repos = c(CRAN = 'https://cloud.r-project.org'))"
-RUN R -e "remotes::install_github('rstudio/renv@${RENV_VERSION}')"
+
 

docker_singularity/README.md

@@ -37,9 +37,9 @@ Run the following code to download and spin up the image.
 
 ```s
 docker run -it --rm \
-        -p 8230:8787 \
+        -p 8231:8787 \
         -e USER=rstudio \
         -e PASSWORD=pass \
-        -v "/path/to/your/folder/on/host:/home/rstudio/Project" nsaphsoftware/gpcerf_dev
+        -v $PWD:/home/rstudio/Project nsaphsoftware/gpcerf_dev
 
 ```