In this example, DecisionForest specifies CategoricalEncoding ('Hashing') when it builds the Model table; therefore, DecisionForestPredict_MLE requires NumericInputs and CategoricalInputs.
DecisionForest Input
- InputTable: housing_train, as in DecisionForest Example: TreeType ('classification'), OutOfBag ('false')
DecisionForest SQL Call
SELECT * FROM DecisionForest (
ON housing_train AS InputTable
OUT TABLE OutputTable (rft_model)
OUT TABLE MonitorTable (housing_monitor_table)
USING
ResponseColumn ('homestyle')
NumericInputs ('price','lotsize','bedrooms','bathrms','stories', 'garagepl')
CategoricalInputs ('driveway','recroom','fullbase','gashw','airco','prefarea')
TreeType ('classification')
MinNodeSize ('2')
MaxDepth ('12')
NumTrees ('3')
CategoricalEncoding ('hashing')
) AS dt ;
DecisionForestPredict_MLE Input
- Input table: housing_test, as in DecisionForestPredict_MLE Example: Omit Responses
- Model: rft_model, output by DecisionForest Example: TreeType ('classification'), OutOfBag ('false')
DecisionForestPredict_MLE SQL Call
SELECT * FROM DecisionForestPredict_MLE (
ON housing_test PARTITION BY ANY
ON rft_model AS Model DIMENSION
USING
IDColumn ('sn')
NumericInputs ('price','lotsize','bedrooms','bathrms','stories', 'garagepl')
CategoricalInputs ('driveway','recroom','fullbase','gashw','airco','prefarea')
) AS dt;