From ed3ab7e7c4e342d3c382c3a9a663601d7c82b530 Mon Sep 17 00:00:00 2001
From: Marvin Wright <github@wrig.de>
Date: Wed, 6 Nov 2024 11:24:59 +0100
Subject: [PATCH] fix docs/exports

---
 NAMESPACE      | 2 ++
 R/hshrink.R    | 3 +++
 R/print.R      | 2 ++
 man/hshrink.Rd | 5 +++++
 4 files changed, 12 insertions(+)

diff --git a/NAMESPACE b/NAMESPACE
index 64d06c481..6dd599111 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -11,6 +11,8 @@ S3method(print,deforest.ranger)
 S3method(print,ranger)
 S3method(print,ranger.forest)
 S3method(print,ranger.prediction)
+S3method(str,ranger)
+S3method(str,ranger.forest)
 S3method(timepoints,ranger)
 S3method(timepoints,ranger.prediction)
 export(csrf)
diff --git a/R/hshrink.R b/R/hshrink.R
index 001866f4f..45794e847 100644
--- a/R/hshrink.R
+++ b/R/hshrink.R
@@ -39,6 +39,9 @@
 #' @return The ranger object is modified in-place. 
 #'
 #' @examples
+#' ## Hierarchical shrinkage for a probablity forest
+#' rf <- ranger(Species ~ ., iris, node.stats = TRUE, probability = TRUE)
+#' hshrink(rf, lambda = 5)
 ##' @references
 ##' \itemize{
 ##'   \item Agarwal, A., Tan, Y.S., Ronen, O., Singh, C. & Yu, B. (2022). Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models. Proceedings of the 39th International Conference on Machine Learning, PMLR 162:111-135.
diff --git a/R/print.R b/R/print.R
index 90e78bc2b..8f02bf096 100644
--- a/R/print.R
+++ b/R/print.R
@@ -103,11 +103,13 @@ print.ranger.prediction <- function(x, ...) {
   }
 }
 
+##' @export
 str.ranger.forest <- function(object, max.level = 2, ...) {
   class(object) <- "list"
   str(object, max.level = max.level, ...)
 }
 
+##' @export
 str.ranger <- function(object, max.level = 2, ...) {
   class(object) <- "list"
   str(object, max.level = max.level, ...)
diff --git a/man/hshrink.Rd b/man/hshrink.Rd
index e48c9a2e9..fd813e59a 100644
--- a/man/hshrink.Rd
+++ b/man/hshrink.Rd
@@ -19,6 +19,11 @@ Apply hierarchical shrinkage to a ranger object.
 Hierarchical shrinkage is a regularization technique that recursively shrinks node predictions towards parent node predictions. 
 For details see Agarwal et al. (2022).
 }
+\examples{
+## Hierarchical shrinkage for a probablity forest
+rf <- ranger(Species ~ ., iris, node.stats = TRUE, probability = TRUE)
+hshrink(rf, lambda = 5)
+}
 \references{
 \itemize{
   \item Agarwal, A., Tan, Y.S., Ronen, O., Singh, C. & Yu, B. (2022). Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models. Proceedings of the 39th International Conference on Machine Learning, PMLR 162:111-135.