TD_DecisionForest Examples | DecisionForest | Teradata Vantage - TD_DecisionForest Examples - Teradata Vantage

Teradata® VantageCloud Lake

Deployment
VantageCloud
Edition
Lake
Product
Teradata Vantage
Published
January 2023
Language
English (United States)
Last Update
2024-04-03
dita:mapPath
phg1621910019905.ditamap
dita:ditavalPath
pny1626732985837.ditaval
dita:id
phg1621910019905

Example: TD_DecisionForest Classification

Input table
encoded ROW_I attribute_1 attribute_2 attribute_3 ... attribute_49 sample_id
0 99 -0.0664 -0.0999 -0.0949 ... -0.0942 2
0 101 -0.0603 -0.0938 -0.0900 ... -0.0935 2
1 114 0.0000 0.0001 0.0001 ... 0.0001 2
1 115 0.0001 0.0001 0.0001 ... 0.0001 2
... ... ... ... ... ... ... ...

TD_DecisionForest Call for Classification

CREATE VOLATILE TABLE DecisionForestOutput AS (
SELECT * FROM TD_DecisionForest(
  ON DT_Input AS PARTITION BY ANY
USING
  ResponseColumn('encoded')
  InputColumns(‘[2:12]’)
  TreeType('CLASSIFICATION')
  ) AS dt
 ) WITH DATA
ON COMMIT PRESERVE ROWS;

TD_DecisionForest Output for Classification

SELECT * FROM DecisionForestOutput
task_index tree_num tree_order tree
24 0 0 {"id_":1,"size_":75,"maxDepth_":5,"label_":"1","responseCounts_":{"1":75},"nodeType_":"CLASSIFICATION_LEAF"}
35 0 0 {"id_":1,"size_":82,"maxDepth_":5,"label_":"0","responseCounts_":{"0":82},"nodeType_":"CLASSIFICATION_LEAF"}

Example: TD_DecisionForest Regression

The following is a sample of housing data taken from Boston housing dataset.
CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX PTRATIO B LSTAT medv
0.05188 0.0 4.49 0.0 0.449 6.015 45.1 4.4272 3.0 247 18.5 396.99 12.86 22.5
0.30347 0.0 7.38 0.0 0.493 6.312 28.9 5.4159 5.0 287 19.6 396.90 6.15 23.0
0.6147 0.0 6.20 0.0 0.507 6.618 80.8 3.2721 8.0 307 17.4 396.90 7.6 30.1
0.04527 0.0 11.93 0.0 0.537 6.120 76.7 2.2875 1.0 273 21.0 396.90 9.08 20.6
0.12816 12.5 6.07 0.0 0.409 5.885 33 6.4890 4.0 345 18.9 396.90 8.79 20.9
... ... ... ... ... ... ... ... ... ... ... ... ... ...

TD_DecisionForest SQL Call for Regression

SELECT * FROM TD_DecisionForest (
ON housing_sample AS inputtable PARTITION BY ANY
USING
  ResponseColumn('medv')
  InputColumns('[0:12]')
  MaxDepth(12)
  MinNodeSize(1)
  NumTrees(4)
  ModelType('REGRESSION')
  Seed(1)
  Mtry(3)
  MtrySeed(1)
) AS dt;

TD_DecisionForest Output for Regression

task_index tree_num tree_order regression_tree
0 0 0 {"id_":1,"sum_":201.700000,"sumSq_":6781.890000,"size_":6,"maxDepth_":12,"nodeType_":"REGRESSION_NODE","split_":{"splitValue_":7.091500,"attr_":"rm","type_":"REGRESSION_NUMERIC_SPLIT","score_":32984.915253,"scoreImprove_":32984.915253,"leftNodeSize_":5,"rightNodeSize_":1},"leftChild_":{"id_":2,"sum_":167.000000,"sumSq_":5577.800000,"size_":5,"maxDepth_":11,"value_":33.400000,"nodeType_":"REGRESSION_LEAF"},"rightChild_":{"id_":3,"sum_":34.700000,"sumSq_":1204.090000,"size_":1,"maxDepth_":11,"value_":34.700000,"nodeType_":"REGRESSION_LEAF"}}
2 0 0 {"id_":1,"sum_":208.800000,"sumSq_":4905.980000,"size_":9,"maxDepth_":12,"nodeType_":"REGRESSION_NODE","split_":{"splitValue_":6.465000,"attr_":"rm","type_":"REGRESSION_NUMERIC_SPLIT","score_":37076.368050,"scoreImprove_":37076.368050,"leftNodeSize_":8,"rightNodeSize_":1},"leftChild_":{"id_":2,"sum_":178.700000,"sumSq_":3999.970000,"size_":8,"maxDepth_":11,"value_":22.337500,"nodeType_":"REGRESSION_LEAF"},"rightChild_":{"id_":3,"sum_":30.100000,"sumSq_":906.010000,"size_":1,"maxDepth_":11,"value_":30.100000,"nodeType_":"REGRESSION_LEAF"}}
3 0 0 {"id_":1,"sum_":93.600000,"sumSq_":2194.560000,"size_":4,"maxDepth_":12,"nodeType_":"REGRESSION_NODE","split_":{"splitValue_":7.060000,"attr_":"lstat","type_":"REGRESSION_NUMERIC_SPLIT","score_":6272.052528,"scoreImprove_":6272.052528,"leftNodeSize_":3,"rightNodeSize_":1},"leftChild_":{"id_":2,"sum_":72.000000,"sumSq_":1728.000000,"size_":3,"maxDepth_":11,"value_":24.000000,"nodeType_":"REGRESSION_LEAF"},"rightChild_":{"id_":3,"sum_":21.600000,"sumSq_":466.560000,"size_":1,"maxDepth_":11,"value_":21.600000,"nodeType_":"REGRESSION_LEAF"}}