Table 2. Optimal parameters that resulted in highest OOB score for training set.

Parameter	Value
n_estimators	22
criterion	‘gini’
max_features	$\sqrt{3}$
max_depth	None
min_samples_split	2
min_samples_leaf	3
min_weight_fraction_leaf	0
max_leaf_nodes	None
bootstrap	True
oob_score	True
n_jobs	-1
random_state	42
class_weight	‘balanced_subsample’