random_forest_parameters: Hyperparameter optimisation or parameter tuning for Random...
In scorecardModelUtils: Credit Scorecard Modelling Utils

Description Usage Arguments Value Author(s) Examples

The function runs a grid search with k-fold cross validation to arrive at best parameter decided by some performance measure. The parameters that can be tuned using this function for random forest algorithm are - ntree, mtry, maxnodes and nodesize. The objective function to be minimised is the error (mean absolute error / mean squared error / root mean squared error). For the grid search, the possible values of each tuning parameter needs to be passed as an array into the function.

1 2	random_forest_parameters(base, target, model_type, ntree, mtry, maxnodes = NULL, nodesize, error = "rmse", cv = 1)

`base`	input dataframe
`target`	column / field name for the target variable to be passed as string (must be 0/1 type)
`model_type`	to be chosen among "regression" or "classification"
`ntree`	number of trees to be fitted
`mtry`	number of variable to be sampled as split criteria at each node
`maxnodes`	(optional) Maximum number of terminal nodes (default is NULL ie. no restriction on depth of the trees)
`nodesize`	minimum size of terminal nodes
`error`	(optional) error measure as objective function to be minimised, to be chosen among "mae", "mse" and "rmse" (default value is "rmse")
`cv`	(optional) k vakue for k-fold cross validation to be performed (default value is 1 ie. without cross validation)

An object of class "random_forest_parameters" is a list containing the following components:

`error_tab_detailed`	error summary for each cross validation sample of the parameter combinations iterated during grid search as a dataframe
`error_tab_summary`	error summary for each combination of parameters as a dataframe
`best_ntree`	ntree parameter of the optimal solution
`best_mtry`	mtry parameter of the optimal solution
`maxnodes`	maxnodes parameter of the optimal solution
`best_nodesize`	nodesize parameter of the optimal solution
`runtime`	runtime of the entire process

Arya Poddar <aryapoddar290990@gmail.com>

Aiana Goyal <aianagoel002@gmail.com>

data <- iris
suppressWarnings(RNGversion('3.5.0'))
set.seed(11)
data$Y <- sample(0:1,size=nrow(data),replace=TRUE)
rf_params_list <- random_forest_parameters(base = data,target = "Y",
                  model_type = "classification",ntree = 2,mtry = 1,nodesize = 3)
rf_params_list$error_tab_detailed
rf_params_list$error_tab_summary
rf_params_list$best_ntree
rf_params_list$best_mtry
rf_params_list$maxnodes
rf_params_list$best_nodesize
rf_params_list$runtime