random_search: Random optimization of hyperparameters

In ModelOriented/forester: Quick and Simple Tools for Training and Testing of Tree-Based Models

Random optimization of hyperparameters

Description

Random optimization of hyperparameters

Usage

random_search(
  train_data,
  y = NULL,
  time = NULL,
  status = NULL,
  engine,
  type,
  max_evals = 10,
  parallel = FALSE,
  verbose = FALSE
)

Arguments

train_data	A training data for models created by 'prepare_data()' function.
y	A string that indicates a target column name for regression or classification. Either y, or pair: time, status can be used.
time	A string that indicates a time column name for survival analysis task. Either y, or pair: time, status can be used.
status	A string that indicates a status column name for survival analysis task. Either y, or pair: time, status can be used.
engine	A vector of tree-based models that shall be created. Possible values are: ‘ranger', 'xgboost','decision_tree', 'lightgbm', 'catboost'. Doesn’t matter for survival analysis.
type	A string that determines if Machine Learning task is the 'binary_clf', 'regression', 'survival', or 'multiclass' task.
max_evals	The number of trained models for each model type in 'engine'.
parallel	A logical value, if set to TRUE, the function will use parallel computing. By default set to FALSE.
verbose	A logical value, if set to TRUE, provides all information about the process, if FALSE gives none. Set to FALSE by default.

Value

A list consisting of models created via random search and ranked list of models scores.

ModelOriented/forester documentation built on June 6, 2024, 7:29 a.m.