Package: YARF 1.2.0

YARF: Yet Another Random Forests Package

A customizable, asynchronous, and parallelized random forest implementation. Supports user-defined splitting and aggregation behavior, missingness incorporated in attributes, and random-forest-based imputation.

Authors:Adam Kapelner [aut, cre, cph], Matt Olson [aut], Abhinav Patil [aut]

YARF_1.2.0.tar.gz
YARF_1.2.0.zip(r-4.7-any)YARF_1.2.0.zip(r-4.6-any)YARF_1.2.0.zip(r-4.5-any)
YARF_1.2.0.tgz(r-4.6-any)YARF_1.2.0.tgz(r-4.5-any)
YARF_1.2.0.tar.gz(r-4.7-any)YARF_1.2.0.tar.gz(r-4.6-any)
YARF_1.2.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
YARF/json (API)

# Install 'YARF' in R:

install.packages('YARF', repos = c('https://kapelner.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/kapelner/yarf/issues

Pkgdown/docs site:https://kapelner.github.io

Uses libs:

openjdk– OpenJDK Java runtime, using Hotspot JIT

Datasets:

ankara - Benchmark regression datasets
automobile - Automobile data
baseball - Benchmark regression datasets
boston - Benchmark regression datasets
compactiv - Benchmark regression datasets
ozone - Benchmark regression datasets
pole - Benchmark regression datasets
triazine - Benchmark regression datasets
wine.red - Benchmark regression datasets
wine.white - Benchmark regression datasets

On CRAN:

random-forest decision-trees ensemble-learning machine-learning statistical-learning supervised-learning classification regression variable-importance interaction-detection proximity-analysis out-of-bag missing-data missing-data-imputation custom-split-rules asynchronous-computing parallel-computing java javascript openjdk

3.56 score 1 stars 36 scripts 31 exports 44 dependencies

Last updated from:6677cdf142. Checks:6 OK, 3 NOTE. Indexed: yes.

Target	Result	Time
linux-devel	OK	174
source / vignettes	OK	231
linux-release	OK	162
macos-release	OK	138
macos-oldrel	OK	157
windows-devel	NOTE	123
windows-release	NOTE	159
windows-oldrel	NOTE	119
wasm-release	OK	130

Exports:calcAUC compute_raw_proximity_info cov_importance_test first_order_interaction_investigator get_tree_num_nodes_leaves_max_depths illustrate_trees model_fit_test prediction_nodes proximity_info prune_YARF_model query_variable_counts query_variable_proportions_across_trees set_YARF_num_cores shared_initial_substring tree_average_proximity_info YARF YARF_all_oob_results_matrix YARF_convergence yarf_duplicate YARF_predict_all_trees YARF_progress YARF_serialize YARF_set_aggregation_method YARF_stop YARF_update_with_oob_results YARF_update_with_oob_test_results YARF_update_with_oob_validation_results YARFBAG YARFCART YARFMissForest YARFROC

Dependencies:backports bit bit64 Bolstad2 checkmate cli clipr cpp11 crayon digest farver ggplot2 glue gridExtra gtable hms isoband labeling lifecycle magrittr pander pillar pkgconfig prettyunits progress R6 RColorBrewer Rcpp readr rJava rlang S7 scales stringi stringr tibble tidyselect tzdb utf8 vctrs viridisLite vroom withr YARFJARs

Getting started with YARF

Fit a classification forest | Inspect out-of-bag performance | Missing values

Rendered fromgetting-started.Rmdusingknitr::rmarkdown

Last update: 2026-09-01
Started: 2026-09-01

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Automobile data	automobile
Benchmark regression datasets	ankara baseball benchmark_datasets boston compactiv ozone pole triazine wine.red wine.white
Calculates the area under the curve	calcAUC
Computes information about the "proximity" of observations within the YARF model. Given two datasets, information is computed for all pairs of observations. Information returned is the prediction nodes (for all trees) for both objects and their common node in the tree structure plus much information about the nodes.	compute_raw_proximity_info
Tests the effect of H0: one, or two, ... or all covariates are not predictive (out of sample) via a permutation test. We permute the covariates column(s) and build YARF models 'num_permutation_samples' times. The p-val is determined by a permutation-like test.	cov_importance_test
Investigate First Order Interactions	first_order_interaction_investigator
Gets information about each tree: the number of nodes, number of leaves and maximum depth.	get_tree_num_nodes_leaves_max_depths
Illustrates trees to PNG files in the local directory.	illustrate_trees
Convenience method for testing a model's fit. The strategy is simple: one builds a YARF model from the residuals of the model you wish to fit and performs an omnibus test of all covariates against those residuals. This effecticely answers the question: "is there out-of-sample predictive information left over after this model was fit?" The p-val is determined by a permutation-like test.	model_fit_test
Computes a response prediction for new data observation(s).	predict.YARF
Returns the leaf nodes that are responsible for predictions for a given dataset.	prediction_nodes
Alias for summary.	print.YARF
Computes information about the "proximity" of observations within the YARF model. Given two datasets, information is computed for all pairs of observation.	proximity_info
Prunes the trees in a YARF mode. This is an irreversible modification to the tree structure.	prune_YARF_model
Function which queries the YARF model about how many times the variables are used when splitting	query_variable_counts
Function which queries the YARF model about the proportion of times the variables are used when splitting. This is a convenience method which merely normalizes the result of 'query_variable_counts'.	query_variable_proportions_across_trees
Sets the number of cores for YARF to use for all operations which are multithreaded (e.g. model construction, prediction, etc)	set_YARF_num_cores
Returns the shared initial portion of a string	shared_initial_substring
Prints a summary of the model to the console	summary.YARF
Computes information about the "proximity" of observations within the YARF model. Given two datasets, information is computed for all pairs of observations. Information is averaged over the trees in the model.	tree_average_proximity_info
Builds a YARF Model. There are many customizations available.	YARF
All OOB Results Matrix	YARF_all_oob_results_matrix
Plot YARF convergence	YARF_convergence
Duplicates the settings of YARF model. Wait is 'TRUE', all verbose logging is turned off and serializing is turned off as well.	yarf_duplicate
Computes a response prediction for new data observation(s) for all trees (unaggregated).	YARF_predict_all_trees
Prints out a message reflecting the progress of the YARF model construction	YARF_progress
Serializes the model so the user can use 'save' and 'save.image' to write it to a file that can be then loaded into another and/or future R session.	YARF_serialize
Sets the Tree Aggregation Method	YARF_set_aggregation_method
Halts the model building.	YARF_stop
Computes the out-of-bag (OOB) predictions for the training data. This gives a good sense of out-of-sample performance in the future.	YARF_update_with_oob_results
Computes the out-of-bag (OOB) predictions for the test subset of the training data. This function should only be run once. If it run again you risk adapting your model to the test data which will lead to overfitting and hence a biased out-of-sample performance estimate.	YARF_update_with_oob_test_results
Computes the out-of-bag (OOB) predictions for the validation subset of the training data. This allows the user to try many different models while still leaving test data for true out-of-sample performance estimation.	YARF_update_with_oob_validation_results
A convenience method to build a Bagged Tree model via YARF.	YARFBAG
A convenience method to build a CART model via YARF. There are many customizations available.	YARFCART
MissForest Imputation	YARFMissForest
ROC and ROC-like curves	YARFROC