This example uses the same housing data set as the previous examples. Instead of trying to predict the style of the house, this example uses homestyle as a predictor and tries to predict the price of the house. Because the response variable (price) is numeric, the TreeType is regression.
Input
InputTable: housing_train, as in DecisionForest Example: TreeType ('classification'), OutOfBag ('false')SQL Call
SELECT * FROM DecisionForest ( ON housing_train AS InputTable OUT TABLE OutputTable (df_model) OUT TABLE OutputMessageTable (df_monitor_table) USING TreeType ('regression') ResponseColumn ('price') NumericInputs ('lotsize','bedrooms','bathrms','stories','garagepl') CategoricalInputs ('homestyle','driveway','recroom','fullbase','gashw','airco','prefarea') MaxDepth (6) MinNodeSize (2) NumTrees (50) OutOfBag ('true') ) AS dt;
Output
message
------------------------------------------------
Computing 50 regression trees.
Each worker is computing 25 trees.
Each tree will contain approximately 246 points.
Poisson sampling parameter: 1.00
Mean of squared residuals: 1.1802873865165223E8
% Var explained: 97.78732397804998
Decision forest created.
This query returns the following table:
SELECT task_index, tree_num, CAST (tree AS VARCHAR(50)) FROM df_model ORDER BY 1;
task_index tree_num tree ---------- -------- -------------------------------------------------- 4 0 {"sum_":1.681685E7,"sumSq_":1.4238502825E12,"size_ 4 1 {"sum_":1.727905E7,"sumSq_":1.3643563875E12,"size_ 4 2 {"sum_":1.694355E7,"sumSq_":1.3956032975E12,"size_ 4 3 {"sum_":1.908355E7,"sumSq_":1.4617931525E12,"size_ 4 4 {"sum_":1.806E7,"sumSq_":1.474040925E12,"size_":25 4 5 {"sum_":1.63545E7,"sumSq_":1.320355595E12,"size_": 4 6 {"sum_":1.862795E7,"sumSq_":1.4897402375E12,"size_ 4 7 {"sum_":1.759165E7,"sumSq_":1.3890647825E12,"size_ 4 8 {"sum_":1.558195E7,"sumSq_":1.2663727725E12,"size_ 4 9 {"sum_":1.537575E7,"sumSq_":1.2086245025E12,"size_ 4 10 {"sum_":1.581315E7,"sumSq_":1.1909563425E12,"size_ 4 11 {"sum_":1.75272E7,"sumSq_":1.341120065E12,"size_": 4 12 {"sum_":1.673795E7,"sumSq_":1.3203427375E12,"size_ 4 13 {"sum_":1.703575E7,"sumSq_":1.3940797775E12,"size_ 4 14 {"sum_":1.507785E7,"sumSq_":1.1982603775E12,"size_ 4 15 {"sum_":1.538635E7,"sumSq_":1.2125508275E12,"size_ 4 16 {"sum_":1.56961E7,"sumSq_":1.259207185E12,"size_": 4 17 {"sum_":1.892375E7,"sumSq_":1.4711988825E12,"size_ 4 18 {"sum_":1.57514E7,"sumSq_":1.28476287E12,"size_":2 4 19 {"sum_":1.62982E7,"sumSq_":1.305691615E12,"size_": 4 20 {"sum_":1.56613E7,"sumSq_":1.193288085E12,"size_": 4 21 {"sum_":1.719835E7,"sumSq_":1.3850259525E12,"size_ 4 22 {"sum_":1.72148E7,"sumSq_":1.361429395E12,"size_": 4 23 {"sum_":1.558585E7,"sumSq_":1.2253462225E12,"size_ 4 24 {"sum_":1.713935E7,"sumSq_":1.3091327925E12,"size_ 5 0 {"sum_":1.499364E7,"sumSq_":1.09838566255E12,"size 5 1 {"sum_":1.621284E7,"sumSq_":1.21153072755E12,"size 5 2 {"sum_":1.584329E7,"sumSq_":1.20964782505E12,"size 5 3 {"sum_":1.8707295E7,"sumSq_":1.446280402525E12,"si 5 4 {"sum_":1.66777E7,"sumSq_":1.261864825E12,"size_": 5 5 {"sum_":1.641145E7,"sumSq_":1.3340593525E12,"size_ 5 6 {"sum_":1.791324E7,"sumSq_":1.35688597255E12,"size 5 7 {"sum_":1.57669E7,"sumSq_":1.177536645E12,"size_": 5 8 {"sum_":1.4742645E7,"sumSq_":1.112824970025E12,"si 5 9 {"sum_":1.548094E7,"sumSq_":1.19681165255E12,"size 5 10 {"sum_":1.6602745E7,"sumSq_":1.345563175025E12,"si 5 11 {"sum_":1.696595E7,"sumSq_":1.2466159725E12,"size_ 5 12 {"sum_":1.6895545E7,"sumSq_":1.356572220025E12,"si 5 13 {"sum_":1.630075E7,"sumSq_":1.2469239875E12,"size_ 5 14 {"sum_":1.43426E7,"sumSq_":1.07212618E12,"size_":2 5 15 {"sum_":1.4557895E7,"sumSq_":1.101687512525E12,"si 5 16 {"sum_":1.4730795E7,"sumSq_":1.099434292525E12,"si 5 17 {"sum_":1.824529E7,"sumSq_":1.39450218005E12,"size 5 18 {"sum_":1.510695E7,"sumSq_":1.1471032125E12,"size_ 5 19 {"sum_":1.5264045E7,"sumSq_":1.125377830025E12,"si 5 20 {"sum_":1.6693645E7,"sumSq_":1.395296370025E12,"si 5 21 {"sum_":1.5762345E7,"sumSq_":1.110753800025E12,"si 5 22 {"sum_":1.748599E7,"sumSq_":1.34602377005E12,"size 5 23 {"sum_":1.5813695E7,"sumSq_":1.199732752525E12,"si 5 24 {"sum_":1.6980695E7,"sumSq_":1.333814232525E12,"si
Download a zip file of all examples and a SQL script file that creates their input tables from the attachment in the left sidebar.