Setup hyperparameters for LightCART training.
Usage
setup_LightCART(
num_leaves = 32L,
max_depth = -1L,
lambda_l1 = 0,
lambda_l2 = 0,
min_data_in_leaf = 20L,
max_cat_threshold = 32L,
min_data_per_group = 100L,
linear_tree = FALSE,
objective = NULL,
ifw = FALSE
)Arguments
- num_leaves
(Tunable) Positive integer: Maximum number of leaves in one tree.
- max_depth
(Tunable) Integer: Maximum depth of trees.
- lambda_l1
(Tunable) Numeric: L1 regularization.
- lambda_l2
(Tunable) Numeric: L2 regularization.
- min_data_in_leaf
(Tunable) Positive integer: Minimum number of data in a leaf.
- max_cat_threshold
(Tunable) Positive integer: Maximum number of categories for categorical features.
- min_data_per_group
(Tunable) Positive integer: Minimum number of observations per categorical group.
- linear_tree
(Tunable) Logical: If TRUE, use linear trees.
- objective
Character: Objective function.
- ifw
Logical: If TRUE, use Inverse Frequency Weighting in classification.
Details
Get more information from lightgbm::lgb.train.
Examples
lightcart_hyperparams <- setup_LightCART(num_leaves = 32L, ifw = FALSE)
lightcart_hyperparams
#> <LightCARTHyperparameters>
#> hyperparameters:
#> num_leaves: <int> 32
#> max_depth: <int> -1
#> lambda_l1: <nmr> 0.00
#> lambda_l2: <nmr> 0.00
#> min_data_in_leaf: <int> 20
#> max_cat_threshold: <int> 32
#> min_data_per_group: <int> 100
#> linear_tree: <lgc> FALSE
#> objective: <NUL> NULL
#> ifw: <lgc> FALSE
#> tunable_hyperparameters: <chr> num_leaves, max_depth, lambda_l1, lambda_l2, min_data_in_leaf, max_cat_threshold, min_data_per_group, linear_tree, ifw
#> fixed_hyperparameters: <chr> objective
#> tuned: <int> -1
#> resampled: <int> 0
#> n_workers: <int> 1
#>
#> No search values defined for tunable hyperparameters.