GhosalBoostRF: Implements RF prediction interval method in Ghosal, Hooker...

In chancejohnstone/piRF: Prediction Intervals for Random Forests

Implements RF prediction interval method in Ghosal, Hooker 2018. Helper function.

Description

This function implements variant one and two of the prediction interval methods in Ghosal, Hooker 2018. Used inside rfint().

Usage

GhosalBoostRF(
  formula = NULL,
  train_data = NULL,
  pred_data = NULL,
  num_trees = NULL,
  min_node_size = NULL,
  m_try = NULL,
  keep_inbag = TRUE,
  intervals = FALSE,
  alpha = NULL,
  prop = NULL,
  variant = 1,
  num_threads = NULL,
  num_stages = NULL,
  interval_type = NULL
)

Arguments

formula	Object of class formula or character describing the model to fit. Interaction terms supported only for numerical variables.
train_data	Training data of class data.frame, matrix, dgCMatrix (Matrix) or gwaa.data (GenABEL). Matches ranger() requirements.
pred_data	Test data of class data.frame, matrix, dgCMatrix (Matrix) or gwaa.data (GenABEL). Utilizes ranger::predict() to get prediction intervals for test data.
num_trees	Number of trees.
min_node_size	Minimum number of observations before split at a node.
m_try	Number of variables to randomly select from at each split.
keep_inbag	Saves matrix of observations and which tree(s) they occur in. Required to be true to generate variance estimates for Ghosal, Hooker 2018 method.
intervals	Generate prediction intervals or not. Defaults to FALSE.
alpha	Significance level for prediction intervals.
prop	Proportion of training data to sample for each tree. Currently variant 2 not implemented.
variant	Choose which variant to use. Currently variant 2 not implemented.
num_threads	The number of threads to use in parallel. Default is the current number of cores.
num_stages	Number of boosting stages. Functional for >= 2; variance estimates need adjustment for variant 2.
interval_type	Type of prediction interval to generate. Options are method = c("two-sided", "lower", "upper"). Default is method = "two-sided".

chancejohnstone/piRF documentation built on April 14, 2025, 3:02 a.m.