| English | 中文 |
A decision tree partitions predictors and fits a local response in each leaf. A random forest combines multiple randomized trees and averages their predictions. They share a family, while their complexity and stability controls remain distinct.
| Model | R learner | Python learner | Configuration and calls |
|---|---|---|---|
| Single decision tree | regr.rpart |
decision_tree |
Decision tree |
| Random forest | regr.ranger |
random_forest |
Random forest |
Both reuse language-specific preparation, fitting and common evaluation; no training code is copied into these navigation folders. R/Python parameters and seeds do not imply identical fits. Review the scientific comparison and plan before choosing settings. Return to model families.