This function generates a parameter grid to be used in the cross-validation of gradient boosting decision tree (GBDT) models.
Arguments
- n_iterations
A numeric vector of the number of iterations (trees) for the GBDT model. This is equivalent to
nrounds
in XGBoost,num_iterations
in LightGBM, anditerations
in CatBoost.- max_depth
A numeric vector of the maximum tree depths. This parameter is equivalent to
max_depth
in XGBoost and LightGBM, anddepth
in CatBoost.- learning_rate
A numeric vector of learning rates for the GBDT model. This parameter is equivalent to
eta
in XGBoost,learning_rate
in LightGBM, and ignored in CatBoost.