Updated R package code after running and fixing many CRAN errors/warnings/notes

Author: andrewherren

DESCRIPTION

@@ -9,7 +9,7 @@ Authors@R:
     person("Carlos", "Carvalho", role = "aut"),
     person("Jingyu", "He", role = "aut")
   )
-Description: Stochastic tree ensembles (XBART and BART) for supervised learning and causal inference
+Description: Stochastic tree ensembles (XBART and BART) for supervised learning and causal inference.
 License: MIT + file LICENSE
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
@@ -29,6 +29,7 @@ Suggests:
 VignetteBuilder: knitr
 SystemRequirements: C++17
 Imports: 
-    R6
+    R6,
+    stats
 URL: https://stochastictree.github.io/stochtree-r/
 Config/testthat/edition: 3

LICENSE

@@ -1,21 +1,2 @@
-MIT License
-
-Copyright (c) 2024 Drew Herren
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+YEAR: 2024
+COPYRIGHT HOLDER: stochtree authors

NAMESPACE

@@ -43,4 +43,13 @@ export(preprocessTrainMatrix)
 export(sample_sigma2_one_iteration)
 export(sample_tau_one_iteration)
 export(saveBCFModelToJsonFile)
+importFrom(R6,R6Class)
+importFrom(stats,lm)
+importFrom(stats,model.matrix)
+importFrom(stats,qgamma)
+importFrom(stats,resid)
+importFrom(stats,rnorm)
+importFrom(stats,sd)
+importFrom(stats,sigma)
+importFrom(stats,var)
 useDynLib(stochtree, .registration = TRUE)

R/bart.R

@@ -24,12 +24,11 @@
 #' We do not currently support (but plan to in the near future), test set evaluation for group labels
 #' that were not in the training set.
 #' @param rfx_basis_test (Optional) Test set basis for "random-slope" regression in additive random effects model.
-#' @param variable_weights Vector of length `ncol(X_train)` indicating a "weight" placed on each 
-#' variable for sampling purposes. Default: `rep(1/ncol(X_train),ncol(X_train))`.
 #' @param cutpoint_grid_size Maximum size of the "grid" of potential cutpoints to consider. Default: 100.
 #' @param tau_init Starting value of leaf node scale parameter. Calibrated internally as `1/num_trees` if not set here.
 #' @param alpha Prior probability of splitting for a tree of depth 0. Tree split prior combines `alpha` and `beta` via `alpha*(1+node_depth)^-beta`.
 #' @param beta Exponent that decreases split probabilities for nodes of depth > 0. Tree split prior combines `alpha` and `beta` via `alpha*(1+node_depth)^-beta`.
+#' @param leaf_model Model to use in the leaves, coded as integer with (0 = constant leaf, 1 = univariate leaf regression, 2 = multivariate leaf regression). Default: 0.
 #' @param min_samples_leaf Minimum allowable size of a leaf, in terms of training samples. Default: 5.
 #' @param nu Shape parameter in the `IG(nu, nu*lambda)` global error variance model. Default: 3.
 #' @param lambda Component of the scale parameter in the `IG(nu, nu*lambda)` global error variance prior. If not specified, this is calibrated as in Sparapani et al (2021).
@@ -298,7 +297,7 @@ bart <- function(X_train, y_train, W_train = NULL, group_ids_train = NULL,
 
     # Variable selection weights
     variable_weights <- rep(1/ncol(X_train), ncol(X_train))
-    
+
     # Run GFR (warm start) if specified
     if (num_gfr > 0){
         gfr_indices = 1:num_gfr
@@ -611,7 +610,7 @@ predict.bartmodel <- function(bart, X_test, W_test = NULL, group_ids_test = NULL
 #' Extract raw sample values for each of the random effect parameter terms.
 #'
 #' @param object Object of type `bcf` containing draws of a Bayesian causal forest model and associated sampling outputs.
-#'
+#' @param ... Other parameters to be used in random effects extraction
 #' @return List of arrays. The alpha array has dimension (`num_components`, `num_samples`) and is simply a vector if `num_components = 1`.
 #' The xi and beta arrays have dimension (`num_components`, `num_groups`, `num_samples`) and is simply a matrix if `num_components = 1`.
 #' The sigma array has dimension (`num_components`, `num_samples`) and is simply a vector if `num_components = 1`.
@@ -629,7 +628,7 @@ predict.bartmodel <- function(bart, X_test, W_test = NULL, group_ids_test = NULL
 #' )
 #' snr <- 3
 #' group_ids <- rep(c(1,2), n %/% 2)
-#' rfx_coefs <- matrix(c(-1, -1, 1, 1),nrow=2,byrow=T)
+#' rfx_coefs <- matrix(c(-1, -1, 1, 1), nrow=2, byrow=TRUE)
 #' rfx_basis <- cbind(1, runif(n, -1, 1))
 #' rfx_term <- rowSums(rfx_coefs[group_ids,] * rfx_basis)
 #' E_y <- f_XW + rfx_term
@@ -652,7 +651,7 @@ predict.bartmodel <- function(bart, X_test, W_test = NULL, group_ids_test = NULL
 #' bart_model <- bart(X_train = X_train, y_train = y_train, 
 #'                    group_ids_train = group_ids_train, rfx_basis_train = rfx_basis_train, 
 #'                    X_test = X_test, group_ids_test = group_ids_test, rfx_basis_test = rfx_basis_test, 
-#'                    num_gfr = 100, num_burnin = 0, num_mcmc = 100, sample_tau = T)
+#'                    num_gfr = 100, num_burnin = 0, num_mcmc = 100, sample_tau = TRUE)
 #' rfx_samples <- getRandomEffectSamples(bart_model)
 getRandomEffectSamples.bartmodel <- function(object, ...){
     result = list()

R/bcf.R

@@ -64,7 +64,7 @@
 #' x2 <- rnorm(n)
 #' x3 <- rnorm(n)
 #' x4 <- as.numeric(rbinom(n,1,0.5))
-#' x5 <- as.numeric(sample(1:3,n,replace=T))
+#' x5 <- as.numeric(sample(1:3,n,replace=TRUE))
 #' X <- cbind(x1,x2,x3,x4,x5)
 #' p <- ncol(X)
 #' g <- function(x) {ifelse(x[,5]==1,2,ifelse(x[,5]==2,-1,4))}
@@ -80,8 +80,8 @@
 #' snr <- 4
 #' y <- E_XZ + rnorm(n, 0, 1)*(sd(E_XZ)/snr)
 #' X <- as.data.frame(X)
-#' X$x4 <- factor(X$x4, ordered = T)
-#' X$x5 <- factor(X$x5, ordered = T)
+#' X$x4 <- factor(X$x4, ordered = TRUE)
+#' X$x5 <- factor(X$x5, ordered = TRUE)
 #' test_set_pct <- 0.2
 #' n_test <- round(test_set_pct*n)
 #' n_train <- n - n_test
@@ -766,7 +766,7 @@ bcf <- function(X_train, Z_train, y_train, pi_train = NULL, group_ids_train = NU
 #' x2 <- rnorm(n)
 #' x3 <- rnorm(n)
 #' x4 <- as.numeric(rbinom(n,1,0.5))
-#' x5 <- as.numeric(sample(1:3,n,replace=T))
+#' x5 <- as.numeric(sample(1:3,n,replace=TRUE))
 #' X <- cbind(x1,x2,x3,x4,x5)
 #' p <- ncol(X)
 #' g <- function(x) {ifelse(x[,5]==1,2,ifelse(x[,5]==2,-1,4))}
@@ -782,8 +782,8 @@ bcf <- function(X_train, Z_train, y_train, pi_train = NULL, group_ids_train = NU
 #' snr <- 4
 #' y <- E_XZ + rnorm(n, 0, 1)*(sd(E_XZ)/snr)
 #' X <- as.data.frame(X)
-#' X$x4 <- factor(X$x4, ordered = T)
-#' X$x5 <- factor(X$x5, ordered = T)
+#' X$x4 <- factor(X$x4, ordered = TRUE)
+#' X$x5 <- factor(X$x5, ordered = TRUE)
 #' test_set_pct <- 0.2
 #' n_test <- round(test_set_pct*n)
 #' n_train <- n - n_test
@@ -928,7 +928,7 @@ predict.bcf <- function(bcf, X_test, Z_test, pi_test = NULL, group_ids_test = NU
 #' Extract raw sample values for each of the random effect parameter terms.
 #'
 #' @param object Object of type `bcf` containing draws of a Bayesian causal forest model and associated sampling outputs.
-#'
+#' @param ... Other parameters to be used in random effects extraction
 #' @return List of arrays. The alpha array has dimension (`num_components`, `num_samples`) and is simply a vector if `num_components = 1`.
 #' The xi and beta arrays have dimension (`num_components`, `num_groups`, `num_samples`) and is simply a matrix if `num_components = 1`.
 #' The sigma array has dimension (`num_components`, `num_samples`) and is simply a vector if `num_components = 1`.
@@ -940,7 +940,7 @@ predict.bcf <- function(bcf, X_test, Z_test, pi_test = NULL, group_ids_test = NU
 #' x2 <- rnorm(n)
 #' x3 <- rnorm(n)
 #' x4 <- as.numeric(rbinom(n,1,0.5))
-#' x5 <- as.numeric(sample(1:3,n,replace=T))
+#' x5 <- as.numeric(sample(1:3,n,replace=TRUE))
 #' X <- cbind(x1,x2,x3,x4,x5)
 #' p <- ncol(X)
 #' g <- function(x) {ifelse(x[,5]==1,2,ifelse(x[,5]==2,-1,4))}
@@ -955,13 +955,13 @@ predict.bcf <- function(bcf, X_test, Z_test, pi_test = NULL, group_ids_test = NU
 #' E_XZ <- mu_x + Z*tau_x
 #' snr <- 3
 #' group_ids <- rep(c(1,2), n %/% 2)
-#' rfx_coefs <- matrix(c(-1, -1, 1, 1),nrow=2,byrow=T)
+#' rfx_coefs <- matrix(c(-1, -1, 1, 1), nrow=2, byrow=TRUE)
 #' rfx_basis <- cbind(1, runif(n, -1, 1))
 #' rfx_term <- rowSums(rfx_coefs[group_ids,] * rfx_basis)
 #' y <- E_XZ + rfx_term + rnorm(n, 0, 1)*(sd(E_XZ)/snr)
 #' X <- as.data.frame(X)
-#' X$x4 <- factor(X$x4, ordered = T)
-#' X$x5 <- factor(X$x5, ordered = T)
+#' X$x4 <- factor(X$x4, ordered = TRUE)
+#' X$x5 <- factor(X$x5, ordered = TRUE)
 #' test_set_pct <- 0.2
 #' n_test <- round(test_set_pct*n)
 #' n_train <- n - n_test
@@ -991,7 +991,7 @@ predict.bcf <- function(bcf, X_test, Z_test, pi_test = NULL, group_ids_test = NU
 #'                  Z_test = Z_test, pi_test = pi_test, group_ids_test = group_ids_test,
 #'                  rfx_basis_test = rfx_basis_test, 
 #'                  num_gfr = 100, num_burnin = 0, num_mcmc = 100, 
-#'                  sample_sigma_leaf_mu = T, sample_sigma_leaf_tau = F)
+#'                  sample_sigma_leaf_mu = TRUE, sample_sigma_leaf_tau = FALSE)
 #' rfx_samples <- getRandomEffectSamples(bcf_model)
 getRandomEffectSamples.bcf <- function(object, ...){
     result = list()
@@ -1026,7 +1026,7 @@ getRandomEffectSamples.bcf <- function(object, ...){
 #' x2 <- rnorm(n)
 #' x3 <- rnorm(n)
 #' x4 <- as.numeric(rbinom(n,1,0.5))
-#' x5 <- as.numeric(sample(1:3,n,replace=T))
+#' x5 <- as.numeric(sample(1:3,n,replace=TRUE))
 #' X <- cbind(x1,x2,x3,x4,x5)
 #' p <- ncol(X)
 #' g <- function(x) {ifelse(x[,5]==1,2,ifelse(x[,5]==2,-1,4))}
@@ -1041,13 +1041,13 @@ getRandomEffectSamples.bcf <- function(object, ...){
 #' E_XZ <- mu_x + Z*tau_x
 #' snr <- 3
 #' group_ids <- rep(c(1,2), n %/% 2)
-#' rfx_coefs <- matrix(c(-1, -1, 1, 1),nrow=2,byrow=T)
+#' rfx_coefs <- matrix(c(-1, -1, 1, 1), nrow=2, byrow=TRUE)
 #' rfx_basis <- cbind(1, runif(n, -1, 1))
 #' rfx_term <- rowSums(rfx_coefs[group_ids,] * rfx_basis)
 #' y <- E_XZ + rfx_term + rnorm(n, 0, 1)*(sd(E_XZ)/snr)
 #' X <- as.data.frame(X)
-#' X$x4 <- factor(X$x4, ordered = T)
-#' X$x5 <- factor(X$x5, ordered = T)
+#' X$x4 <- factor(X$x4, ordered = TRUE)
+#' X$x5 <- factor(X$x5, ordered = TRUE)
 #' test_set_pct <- 0.2
 #' n_test <- round(test_set_pct*n)
 #' n_train <- n - n_test
@@ -1077,7 +1077,7 @@ getRandomEffectSamples.bcf <- function(object, ...){
 #'                  Z_test = Z_test, pi_test = pi_test, group_ids_test = group_ids_test,
 #'                  rfx_basis_test = rfx_basis_test, 
 #'                  num_gfr = 100, num_burnin = 0, num_mcmc = 100, 
-#'                  sample_sigma_leaf_mu = T, sample_sigma_leaf_tau = F)
+#'                  sample_sigma_leaf_mu = TRUE, sample_sigma_leaf_tau = FALSE)
 #' # bcf_json <- convertBCFModelToJson(bcf_model)
 convertBCFModelToJson <- function(object){
     jsonobj <- createCppJson()
@@ -1160,7 +1160,7 @@ convertBCFModelToJson <- function(object){
 #' x2 <- rnorm(n)
 #' x3 <- rnorm(n)
 #' x4 <- as.numeric(rbinom(n,1,0.5))
-#' x5 <- as.numeric(sample(1:3,n,replace=T))
+#' x5 <- as.numeric(sample(1:3,n,replace=TRUE))
 #' X <- cbind(x1,x2,x3,x4,x5)
 #' p <- ncol(X)
 #' g <- function(x) {ifelse(x[,5]==1,2,ifelse(x[,5]==2,-1,4))}
@@ -1175,10 +1175,13 @@ convertBCFModelToJson <- function(object){
 #' E_XZ <- mu_x + Z*tau_x
 #' snr <- 3
 #' group_ids <- rep(c(1,2), n %/% 2)
-#' rfx_coefs <- matrix(c(-1, -1, 1, 1),nrow=2,byrow=T)
+#' rfx_coefs <- matrix(c(-1, -1, 1, 1), nrow=2, byrow=TRUE)
 #' rfx_basis <- cbind(1, runif(n, -1, 1))
 #' rfx_term <- rowSums(rfx_coefs[group_ids,] * rfx_basis)
 #' y <- E_XZ + rfx_term + rnorm(n, 0, 1)*(sd(E_XZ)/snr)
+#' X <- as.data.frame(X)
+#' X$x4 <- factor(X$x4, ordered = TRUE)
+#' X$x5 <- factor(X$x5, ordered = TRUE)
 #' test_set_pct <- 0.2
 #' n_test <- round(test_set_pct*n)
 #' n_train <- n - n_test
@@ -1206,9 +1209,9 @@ convertBCFModelToJson <- function(object){
 #'                  pi_train = pi_train, group_ids_train = group_ids_train, 
 #'                  rfx_basis_train = rfx_basis_train, X_test = X_test, 
 #'                  Z_test = Z_test, pi_test = pi_test, group_ids_test = group_ids_test,
-#'                  rfx_basis_test = rfx_basis_test, ordered_cat_vars = c(4,5), 
+#'                  rfx_basis_test = rfx_basis_test, 
 #'                  num_gfr = 100, num_burnin = 0, num_mcmc = 100, 
-#'                  sample_sigma_leaf_mu = T, sample_sigma_leaf_tau = F)
+#'                  sample_sigma_leaf_mu = TRUE, sample_sigma_leaf_tau = FALSE)
 #' # saveBCFModelToJsonFile(bcf_model, "test.json")
 saveBCFModelToJsonFile <- function(object, filename){
     # Convert to Json
@@ -1232,7 +1235,7 @@ saveBCFModelToJsonFile <- function(object, filename){
 #' x2 <- rnorm(n)
 #' x3 <- rnorm(n)
 #' x4 <- as.numeric(rbinom(n,1,0.5))
-#' x5 <- as.numeric(sample(1:3,n,replace=T))
+#' x5 <- as.numeric(sample(1:3,n,replace=TRUE))
 #' X <- cbind(x1,x2,x3,x4,x5)
 #' p <- ncol(X)
 #' g <- function(x) {ifelse(x[,5]==1,2,ifelse(x[,5]==2,-1,4))}
@@ -1247,10 +1250,13 @@ saveBCFModelToJsonFile <- function(object, filename){
 #' E_XZ <- mu_x + Z*tau_x
 #' snr <- 3
 #' group_ids <- rep(c(1,2), n %/% 2)
-#' rfx_coefs <- matrix(c(-1, -1, 1, 1),nrow=2,byrow=T)
+#' rfx_coefs <- matrix(c(-1, -1, 1, 1), nrow=2, byrow=TRUE)
 #' rfx_basis <- cbind(1, runif(n, -1, 1))
 #' rfx_term <- rowSums(rfx_coefs[group_ids,] * rfx_basis)
 #' y <- E_XZ + rfx_term + rnorm(n, 0, 1)*(sd(E_XZ)/snr)
+#' X <- as.data.frame(X)
+#' X$x4 <- factor(X$x4, ordered = TRUE)
+#' X$x5 <- factor(X$x5, ordered = TRUE)
 #' test_set_pct <- 0.2
 #' n_test <- round(test_set_pct*n)
 #' n_train <- n - n_test
@@ -1278,9 +1284,9 @@ saveBCFModelToJsonFile <- function(object, filename){
 #'                  pi_train = pi_train, group_ids_train = group_ids_train, 
 #'                  rfx_basis_train = rfx_basis_train, X_test = X_test, 
 #'                  Z_test = Z_test, pi_test = pi_test, group_ids_test = group_ids_test,
-#'                  rfx_basis_test = rfx_basis_test, ordered_cat_vars = c(4,5), 
+#'                  rfx_basis_test = rfx_basis_test, 
 #'                  num_gfr = 100, num_burnin = 0, num_mcmc = 100, 
-#'                  sample_sigma_leaf_mu = T, sample_sigma_leaf_tau = F)
+#'                  sample_sigma_leaf_mu = TRUE, sample_sigma_leaf_tau = FALSE)
 #' # bcf_json <- convertBCFModelToJson(bcf_model)
 #' # bcf_model_roundtrip <- createBCFModelFromJson(bcf_json)
 createBCFModelFromJson <- function(json_object){
@@ -1368,7 +1374,7 @@ createBCFModelFromJson <- function(json_object){
 #' x2 <- rnorm(n)
 #' x3 <- rnorm(n)
 #' x4 <- as.numeric(rbinom(n,1,0.5))
-#' x5 <- as.numeric(sample(1:3,n,replace=T))
+#' x5 <- as.numeric(sample(1:3,n,replace=TRUE))
 #' X <- cbind(x1,x2,x3,x4,x5)
 #' p <- ncol(X)
 #' g <- function(x) {ifelse(x[,5]==1,2,ifelse(x[,5]==2,-1,4))}
@@ -1383,10 +1389,13 @@ createBCFModelFromJson <- function(json_object){
 #' E_XZ <- mu_x + Z*tau_x
 #' snr <- 3
 #' group_ids <- rep(c(1,2), n %/% 2)
-#' rfx_coefs <- matrix(c(-1, -1, 1, 1),nrow=2,byrow=T)
+#' rfx_coefs <- matrix(c(-1, -1, 1, 1), nrow=2, byrow=TRUE)
 #' rfx_basis <- cbind(1, runif(n, -1, 1))
 #' rfx_term <- rowSums(rfx_coefs[group_ids,] * rfx_basis)
 #' y <- E_XZ + rfx_term + rnorm(n, 0, 1)*(sd(E_XZ)/snr)
+#' X <- as.data.frame(X)
+#' X$x4 <- factor(X$x4, ordered = TRUE)
+#' X$x5 <- factor(X$x5, ordered = TRUE)
 #' test_set_pct <- 0.2
 #' n_test <- round(test_set_pct*n)
 #' n_train <- n - n_test
@@ -1414,9 +1423,9 @@ createBCFModelFromJson <- function(json_object){
 #'                  pi_train = pi_train, group_ids_train = group_ids_train, 
 #'                  rfx_basis_train = rfx_basis_train, X_test = X_test, 
 #'                  Z_test = Z_test, pi_test = pi_test, group_ids_test = group_ids_test,
-#'                  rfx_basis_test = rfx_basis_test, ordered_cat_vars = c(4,5), 
+#'                  rfx_basis_test = rfx_basis_test, 
 #'                  num_gfr = 100, num_burnin = 0, num_mcmc = 100, 
-#'                  sample_sigma_leaf_mu = T, sample_sigma_leaf_tau = F)
+#'                  sample_sigma_leaf_mu = TRUE, sample_sigma_leaf_tau = FALSE)
 #' # saveBCFModelToJsonFile(bcf_model, "test.json")
 #' # bcf_model_roundtrip <- createBCFModelFromJsonFile("test.json")
 createBCFModelFromJsonFile <- function(json_filename){

R/generics.R

@@ -1,5 +1,7 @@
 #' Generic function for extracting random effect samples from a model object (BCF, BART, etc...)
 #' 
+#' @param object Fitted model object from which to extract random effects
+#' @param ... Other parameters to be used in random effects extraction
 #' @return List of random effect samples
 #' @export
 getRandomEffectSamples <- function(object, ...) UseMethod("getRandomEffectSamples")

R/serialization.R

@@ -369,6 +369,7 @@ createCppJson <- function() {
 
 #' Create a C++ Json object from a Json file
 #'
+#' @param json_filename Name of file to read. Must end in `.json`.
 #' @return `CppJson` object
 #' @export
 createCppJsonFile <- function(json_filename) {

R/stochtree-package.R

@@ -1,2 +1,15 @@
+## usethis namespace: start
+#' @importFrom stats lm
+#' @importFrom stats model.matrix
+#' @importFrom stats qgamma
+#' @importFrom stats resid
+#' @importFrom stats rnorm
+#' @importFrom stats sd
+#' @importFrom stats sigma
+#' @importFrom stats var
+#' @importFrom R6 R6Class
+## usethis namespace: end
+NULL
+
 #' @useDynLib stochtree, .registration = TRUE
 "_PACKAGE"