Regression Model Using TrainingFunction with TD_GLM - Analytics Database

Database Analytic Functions
Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Analytics Database
Release Number
17.20
Published
June 2022
ft:locale
en-US
ft:lastEdition
2025-04-01
dita:mapPath
gjn1627595495337.ditamap
dita:ditavalPath
qkf1628213546010.ditaval
dita:id
jmh1512506877710
Product Category
Teradata Vantage™
Input Table
id x y z w
1 106 108 114 10
2 106 380 390 10
3 106 179 340 10
4 106 153 380 10
5 106 166 243 10
6 294 326 328 20
7 4 299 158 50
8 4 299 237 50
9 4 301 193 30
10 4 301 186 30
Model Table
attribute predictor estimate value
-13 LocalSGD Iterations 1.00000000000000E 000 ?
-12 Nesterov ? TRUE
-11 Momentum 9.00E-01 ?
-10 Learning Rate (Final) 8.41E-03 ?
-9 Learning Rate (Initial) 1.00E-02 ?
-8 Number of Iterations 2.00000000000000E 000 CONVERGED
-7 Alpha 1.50E-01 Elasticnet
-6 Regularization 2.00E-02 ENABLED
-5 BIC 1.76975548934661E 002 ?
-4 AIC 1.76657782767942E 002 ?
-3 Number of Observations 8.00000000000000E 000 ?
-2 MSE 1.43183524428577E 009 ?
-1 Loss Function ? SQUARED_ERROR
0 (Intercept) -8.37474392156743E 002 ?
1 x -2.98450611997491E 004 ?
2 y -2.31418858908765E 005 ?
3 z -1.96116814935662E 005 ?

TD_SHAP SQL Call Using TD_GLM

SELECT * FROM TD_SHAP (
    ON exai AS InputTable
    ON GLMModel_table AS ModelTable DIMENSION
    USING
    IDColumn ('id')
    InputColumns('x','y','z')
    trainingFunction('td_glm')
    modelType('regression')
) AS dt;
TD_SHAP Output Using TD_GLM
id td_x_shap td_y_shap td_z_shap
1 -6.56591346394479E 005 3.31391805957352E 007 2.80250928543060E 007
2 -6.56591346394479E 005 -2.98067490274490E 007 -2.61031480679366E 007
3 -6.56591346394479E 005 1.67084416132129E 007 -1.62973073211535E 007
4 -6.56591346394479E 005 2.27253319448407E 007 -2.41419799185800E 007
5 -6.56591346394479E 005 1.97168867790268E 007 2.72602372760569E 006
6 -6.26746285194730E 006 -1.73101306463756E 007 -1.39439055419256E 007
7 2.38760489597993E 006 -1.10618214558390E 007 1.93959529971369E 007
8 2.38760489597993E 006 -1.10618214558390E 007 3.90272461721966E 006
9 2.38760489597993E 006 -1.15246591736565E 007 1.25318644743888E 007
10 2.38760489597993E 006 -1.15246591736565E 007 1.39046821789384E 007