Skip to contents

Create ForestModelConfig Object

Source: R/config.R
createForestModelConfig.Rd

Create a forest model config object

This function is intended for advanced use cases in which users require detailed control of sampling algorithms and data structures. Minimal input validation and error checks are performed – users are responsible for providing the correct inputs. For tutorials on the "proper" usage of the stochtree's advanced workflow, we provide several vignettes at stochtree.ai

Usage

createForestModelConfig(
  feature_types = NULL,
  sweep_update_indices = NULL,
  num_trees = NULL,
  num_features = NULL,
  num_observations = NULL,
  variable_weights = NULL,
  leaf_dimension = 1,
  alpha = 0.95,
  beta = 2,
  min_samples_leaf = 5,
  max_depth = -1,
  leaf_model_type = 1,
  leaf_model_scale = NULL,
  variance_forest_shape = 1,
  variance_forest_scale = 1,
  cutpoint_grid_size = 100,
  num_features_subsample = NULL
)

Arguments

feature_types

Vector of integer-coded feature types (integers where 0 = numeric, 1 = ordered categorical, 2 = unordered categorical)

sweep_update_indices

Vector of (0-indexed) indices of trees to update in a sweep

num_trees

Number of trees in the forest being sampled

num_features

Number of features in training dataset

num_observations

Number of observations in training dataset

variable_weights

Vector specifying sampling probability for all p covariates in ForestDataset

leaf_dimension

Dimension of the leaf model (default: 1)

alpha

Root node split probability in tree prior (default: 0.95)

beta

Depth prior penalty in tree prior (default: 2.0)

min_samples_leaf

Minimum number of samples in a tree leaf (default: 5)

max_depth

Maximum depth of any tree in the ensemble in the model. Setting to -1 does not enforce any depth limits on trees. Default: -1.

leaf_model_type

Integer specifying the leaf model type (0 = constant leaf, 1 = univariate leaf regression, 2 = multivariate leaf regression). Default: 0.

leaf_model_scale

Scale parameter used in Gaussian leaf models (can either be a scalar or a q x q matrix, where q is the dimensionality of the basis and is only >1 when leaf_model_int = 2). Calibrated internally as 1/num_trees, propagated along diagonal if needed for multivariate leaf models.

variance_forest_shape

Shape parameter for IG leaf models (applicable when leaf_model_type = 3). Default: 1.

variance_forest_scale

Scale parameter for IG leaf models (applicable when leaf_model_type = 3). Default: 1.

cutpoint_grid_size

Number of unique cutpoints to consider (default: 100)

num_features_subsample

Number of features to subsample for the GFR algorithm

Value

ForestModelConfig object

Examples

config <- createForestModelConfig(num_trees = 10, num_features = 5, num_observations = 100)
#> Warning: `feature_types` not provided, will be assumed to be numeric
#> Warning: `variable_weights` not provided, will be assumed to be equal-weighted