ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R

Abstract

We introduce the C++ application and R package ranger. The software is a fast implementation of random forests for high dimensional data. Ensembles of classification, regression and survival trees are supported. We describe the implementation, provide examples, validate the package with a reference implementation, and compare runtime and memory usage with other implementations. The new software proves to scale best with the number of features, samples, trees, and features tried for splitting. Finally, we show that ranger is the fastest and most memory efficient implementation of random forests to analyze data on the scale of a genome-wide association study.

Cited by in corpus (64)

• Hyperparameters and Tuning Strategies for Random Forest
• Performance evaluation and hyperparameter tuning of statistical and machine-learning models using spatial data
• Soil Property and Class Maps of the Conterminous US at 100 meter Spatial Resolution based on a Compilation of National Soil Point Observations and Machine Learning
• Maize Yield and Nitrate Loss Prediction with Machine Learning Algorithms
• Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features
• Super ensemble learning for daily streamflow forecasting: Large-scale demonstration and comparison with multiple machine learning algorithms
• Large-scale benchmark study of survival prediction methods using multi-omics data
• Kriging Convolutional Networks
• Unbiased variable importance for random forests
• On the consistency of supervised learning with missing values
• survex: an R package for explaining machine learning survival models
• Graph-guided random forest for gene set selection
• On Explaining Machine Learning Models by Evolving Crucial and Compact Features
• Pitfalls and potentials in simulation studies: Questionable research practices in comparative simulation studies allow for spurious claims of superiority of any method
• A framework for probabilistic weather forecast post-processing across models and lead times using machine learning
• Sequential Permutation Testing of Random Forest Variable Importance Measures
• Bayesian Additive Regression Trees with Model Trees
• Merging satellite and gauge-measured precipitation using LightGBM with an emphasis on extreme quantiles
• On Wasted Contributions: Understanding the Dynamics of Contributor-Abandoned Pull Requests
• Opening the random forest black box by the analysis of the mutual impact of features
• Efficient nonparametric inference on the effects of stochastic interventions under two-phase sampling, with applications to vaccine efficacy trials
• Comparison of tree-based ensemble algorithms for merging satellite and earth-observed precipitation data at the daily time scale
• Confounder selection strategies targeting stable treatment effect estimators
• Comparison of machine learning algorithms for merging gridded satellite and earth-observed precipitation data
• A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them
• Two-Step Meta-Learning for Time-Series Forecasting Ensemble
• Fine-resolution landscape-scale biomass mapping using a spatiotemporal patchwork of LiDAR coverages
• A General Machine Learning Framework for Survival Analysis
• DOT: A flexible multi-objective optimization framework for transferring features across single-cell and spatial omics
• Yggdrasil Decision Forests: A Fast and Extensible Decision Forests Library
• Confidence intervals for the random forest generalization error
• Transparency, Auditability and eXplainability of Machine Learning Models in Credit Scoring
• Mapping historical forest biomass for stock-change assessments at parcel to landscape scales
• Key predictors for climate policy support and political mobilization: The role of beliefs and preferences
• Classification and mapping of low-statured 'shrubland' cover types in post-agricultural landscapes of the US Northeast
• Ensemble learning for blending gridded satellite and gauge-measured precipitation data
• Estimating NBA players salary share according to their performance on court: A machine learning approach
• Rank-transformed subsampling: inference for multiple data splitting and exchangeable p-values
• LimeSoDa: A Dataset Collection for Benchmarking of Machine Learning Regressors in Digital Soil Mapping
• Random forests, sound symbolism and Pokemon evolution
• From pixels to parcels: flexible, practical small-area uncertainty estimation for spatial averages obtained from aboveground biomass maps
• Measuring anomalies in cigarette sales by using official data from Spanish provinces: Are there only the anomalies detected by the Empty Pack Surveys (EPS) used by Transnational Tobacco Companies (TTCs)?
• Interpretable Machine Learning for Survival Analysis
• Evaluation of network-guided random forest for disease gene discovery
• The Yield Curve as a Recession Leading Indicator. An Application for Gradient Boosting and Random Forest
• Howzat? Appealing to Expert Judgement for Evaluating Human and AI Next-Step Hints for Novice Programmers
• What is to be gained by ensemble models in analysis of spectroscopic data?
• Using Sequential Statistical Tests for Efficient Hyperparameter Tuning
• Behavior of prediction performance metrics with rare events
• Clustered Flexible Calibration Plots For Binary Outcomes Using Random Effects Modeling
• Improving the Weighting Strategy in KernelSHAP
• Treatment Effect Estimation with Observational Network Data using Machine Learning
• Factor Importance Ranking and Selection using Total Indices
• A reluctant additive model framework for interpretable nonlinear individualized treatment rules
• Human Vs. Machines: Who Wins In Semiconductor Market Forecasting?
• Algorithm-agnostic significance testing in supervised learning with multimodal data
• Analysing Opportunity Cost of Care Work using Mixed Effects Random Forests under Aggregated Auxiliary Data
• Optimizing Prognostic Biomarker Discovery in Pancreatic Cancer Through Hybrid Ensemble Feature Selection and Multi-Omics Data
• Parallelizing MCMC with Machine Learning Classifier and Its Criterion Based on Kullback-Leibler Divergence
• Predicting MacroB12: Data-Driven Assessment of Pre-PEG B12 Utility and Clinical Caveats
• A Socio-Informatic Approach to Automated Account Classification on Social Media
• A Return to Biased Nets: New Specifications and Approximate Bayesian Inference
• Time series features for supporting hydrometeorological explorations and predictions in ungauged locations using large datasets
• Practical considerations for variable screening in the super learner