Input
The input table is housing_train, as in GLM Example 3: Gaussian Distribution Analysis with Default Options.
SQL Call
Because the response variable has a Gaussian distribution, the call specifies Family ('GAUSSIAN'). Alpha (1) indicates L1 (LASSO) regularization.
DROP TABLE housing_model; DROP TABLE housing_factor_table; CREATE MULTISET TABLE housing_model AS ( SELECT * FROM GLML1L2 ( ON housing_train AS InputTable OUT TABLE FactorTable (housing_factor_table) USING FeatureColumns ('lotsize','bedrooms','bathrms','stories','garagepl','driveway', 'recroom','fullbase','gashw','airco','prefarea','homestyle') CategoricalColumns ('driveway','recroom','fullbase','gashw','airco','prefarea','homestyle') ResponseColumn ('price') Family ('GAUSSIAN') Alpha (1) Lambda (0.02) Randomization ('t') ) AS dt ) WITH DATA;
Output
attribute | category | estimate | information |
---|---|---|---|
(Intercept) | 16975.5082421567 | p | |
driveway | yes | 2822.64319583435 | p |
recroom | yes | 1208.48422621322 | p |
fullbase | yes | 3588.31635406472 | p |
gashw | yes | 5787.02116797583 | p |
airco | yes | 6478.76213487311 | p |
prefarea | yes | 6465.59515171777 | p |
homestyle | Eclectic | 16550.8330586448 | p |
homestyle | bungalow | 54128.4244993102 | p |
lotsize | 2.08097633429999 | p | |
bedrooms | 782.136874756127 | p | |
bathrms | 6772.3377658822 | p | |
stories | 2445.64482074556 | p | |
garagepl | 1483.10124561545 | p | |
Family | Gaussian | ||
Regularization | Lasso | ||
Alpha | 1 | ||
Lambda | 0.02 | ||
Iterations # | 45 | ||
Converged | true | ||
Rows # | 492 | ||
Features # | 13 | ||
RMSE | 10385.6617634216 | ||
AIC | -8.99272582914559 | ||
BIC | 49.7859762017467 |
(housing_factor_table not shown here.)