Use the Accumulate argument to pass the homestyle variable, to easily compare the actual and predicted response for each observation.
CREATE TABLE rf_housing_predict DISTRIBUTE BY hash (sn) AS SELECT * FROM Forest_Predict ( ON housing_test PARTITION BY ANY ON rft_model AS ModelTable DIMENSION NumericInputs ('price ', 'lotsize ', 'bedrooms ', 'bathrms ', 'stories ', 'garagepl') CategoricalInputs ('driveway ', 'recroom ', 'fullbase ', 'gashw ', 'airco ', 'prefarea') IdColumn ('sn') Accumulate ('homestyle') Detailed ('false') );