add engine docs for bonsai wrappers (#721)

* draft `boost_tree(engine = "lightgbm")` docs

* document remainder of bonsai engines, `translate` bug fix

* re`knit_engine_docs` to remove duplicate `min_n`

* party -> partykit

* update model flat file

* re-doc

Co-authored-by: Max Kuhn <[email protected]>

Author: simonpcouch

DESCRIPTION

@@ -90,4 +90,4 @@ Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
 Config/testthat/edition: 3
-RoxygenNote: 7.1.2.9000
+RoxygenNote: 7.2.0.9000

R/decision_tree_party.R

@@ -0,0 +1,12 @@
+#' Decision trees via partykit
+#'
+#' [partykit::ctree()] fits a model as a set of if/then statements that creates a
+#' tree-based structure using hypothesis testing methods.
+#'
+#' @includeRmd man/rmd/decision_tree_partykit.md details
+#'
+#' @name details_decision_tree_partykit
+#' @keywords internal
+NULL
+
+# See inst/README-DOCS.md for a description of how these files are processed

R/decision_tree_partykit.R

@@ -49,7 +49,7 @@ knit_engine_docs <- function(pattern = NULL) {
 
 extensions <- function() {
   c("baguette", "censored", "discrim", "multilevelmod", "plsmod",
-    "poissonreg", "rules")
+    "poissonreg", "rules", "bonsai")
 }
 
 # ------------------------------------------------------------------------------

R/engine_docs.R

@@ -1,12 +1,12 @@
-#' Random forests via party
+#' Random forests via partykit
 #'
-#' [party::cforest()] fits a model that creates a large number of decision
+#' [partykit::cforest()] fits a model that creates a large number of decision
 #' trees, each independent of the others. The final prediction uses all
 #' predictions from the individual trees and combines them.
 #'
-#' @includeRmd man/rmd/rand_forest_party.md details
+#' @includeRmd man/rmd/rand_forest_partykit.md details
 #'
-#' @name details_rand_forest_party
+#' @name details_rand_forest_partykit
 #' @keywords internal
 NULL
 

R/rand_forest_party.R renamed to R/rand_forest_partykit.R

@@ -166,7 +166,8 @@ deharmonize <- function(args, key) {
   merged <-
     dplyr::left_join(parsn, key, by = "parsnip") %>%
     dplyr::arrange(order)
-  # TODO correct for bad merge?
+
+  merged <- merged[!duplicated(merged$order),]
 
   names(args) <- merged$original
   args[!is.na(merged$original)]

R/translate.R

@@ -9,17 +9,22 @@
 "bart"	"regression"	"dbarts"	NA
 "boost_tree"	"censored regression"	"mboost"	"censored"
 "boost_tree"	"classification"	"C5.0"	NA
+"boost_tree"	"classification"	"lightgbm"	"bonsai"
 "boost_tree"	"classification"	"spark"	NA
 "boost_tree"	"classification"	"xgboost"	NA
+"boost_tree"	"regression"	"lightgbm"	"bonsai"
 "boost_tree"	"regression"	"spark"	NA
 "boost_tree"	"regression"	"xgboost"	NA
 "C5_rules"	"classification"	"C5.0"	"rules"
 "cubist_rules"	"regression"	"Cubist"	"rules"
-"decision_tree"	"censored regression"	"party"	"censored"
+"decision_tree"	"censored regression"	"partykit"	"censored"
+"decision_tree"	"censored regression"	"partykit"	"bonsai"
 "decision_tree"	"censored regression"	"rpart"	"censored"
 "decision_tree"	"classification"	"C5.0"	NA
+"decision_tree"	"classification"	"partykit"	"bonsai"
 "decision_tree"	"classification"	"rpart"	NA
 "decision_tree"	"classification"	"spark"	NA
+"decision_tree"	"regression"	"partykit"	"bonsai"
 "decision_tree"	"regression"	"rpart"	NA
 "decision_tree"	"regression"	"spark"	NA
 "discrim_flexible"	"classification"	"earth"	"discrim"
@@ -85,10 +90,13 @@
 "poisson_reg"	"regression"	"zeroinfl"	"poissonreg"
 "proportional_hazards"	"censored regression"	"glmnet"	"censored"
 "proportional_hazards"	"censored regression"	"survival"	"censored"
-"rand_forest"	"censored regression"	"party"	"censored"
+"rand_forest"	"censored regression"	"partykit"	"censored"
+"rand_forest"	"censored regression"	"partykit"	"bonsai"
+"rand_forest"	"classification"	"partykit"	"bonsai"
 "rand_forest"	"classification"	"randomForest"	NA
 "rand_forest"	"classification"	"ranger"	NA
 "rand_forest"	"classification"	"spark"	NA
+"rand_forest"	"regression"	"partykit"	"bonsai"
 "rand_forest"	"regression"	"randomForest"	NA
 "rand_forest"	"regression"	"ranger"	NA
 "rand_forest"	"regression"	"spark"	NA