We use default values for the MaxDepth, MinNodeSize, Variance and NumSurrogates, and build 50 trees on two worker nodes. Both seed values are set to 100 for repeatability and mtry is assigned a value of 3 (sqrt(12)= 3.4), as it is a classification type decision tree.
A good starting point for mtry is sqrt(p) for classification and p/3 for regression, where p is number of variables used for prediction.
SELECT * FROM Forest_Drive (
ON (SELECT 1)
PARTITION BY 1
InputTable ('housing_train ')
OutputTable ('rft_model')
TreeType ('classification')
ResponseColumn ('homestyle')
NumericInputs ('price ', 'lotsize ', 'bedrooms ', 'bathrms ',
'stories ', 'garagepl')
CategoricalInputs ('driveway ', 'recroom ', 'fullbase ', 'gashw ',
'airco ', 'prefarea')
MaxDepth (12)
MinNodeSize (1)
NumTrees (50)
NumSurrogates (0)
Variance (0.0)
Mtry ('3')
MtrySeed ('100')
Seed ('100')
);