rfnode properties

The Random Forest node uses an advanced implementation of a bagging algorithm with a tree model as the base model. This Random Forest modeling node in SPSS® Modeler is implemented in Python and requires the scikit-learn© Python library.

Table 1. rfnode properties

rfnode properties	Data type	Property description
role_use	string	Specify predefined to use predefined roles or custom to use custom field assignments. Default is predefined.
inputs	field	List of the field names for input.
splits	field	List of the field names for split.
n_estimators	integer	Number of trees to build. Default is 10.
specify_max_depth	Boolean	Specify custom max depth. If false, nodes are expanded until all leaves are pure or until all leaves contain less than min_samples_split samples. Default is false.
max_depth	integer	The maximum depth of the tree. Default is 10.
min_samples_leaf	integer	Minimum leaf node size. Default is 1.
max_features	string	The number of features to consider when looking for the best split: If auto, then max_features=sqrt(n_features) for classifier and max_features=sqrt(n_features) for regression. If sqrt, then max_features=sqrt(n_features). If log2, then max_features=log2 (n_features). Default is auto.
bootstrap	Boolean	Use bootstrap samples when building trees. Default is true.
oob_score	Boolean	Use out-of-bag samples to estimate the generalization accuracy. Default value is false.
extreme	Boolean	Use extremely randomized trees. Default is false.
use_random_seed	Boolean	Specify this to get replicated results. Default is false.
random_seed	integer	The random number seed to use when build trees. Specify any integer.
cache_size	float	The size of the kernel cache in MB. Default is 200.
enable_random_seed	Boolean	Enables the random_seed parameter. Specify true or false. Default is false.
enable_hpo	Boolean	Specify true or false to enable or disable the HPO options. If set to true, Rbfopt will be applied to determine the "best" Random Forest model automatically, which reaches the target objective value defined by the user with the following target_objval parameter.
target_objval	float	The objective function value (error rate of the model on the samples) you want to reach (for example, the value of the unknown optimum). Set this parameter to the appropriate value if the optimum is unknown (for example, 0.01).
max_iterations	integer	Maximum number of iterations for trying the model. Default is 1000.
max_evaluations	integer	Maximum number of function evaluations for trying the model, where the focus is accuracy over speed. Default is 300.