PREDICT_SVM_REGRESSOR

Use an SVM model to perform regression on samples in an input relation, and returns the predicted value as a FLOAT data type.

Syntax

PREDICT_SVM_REGRESSOR(input‑columns
	      USING PARAMETERS model_name='model‑name'
                              [, match_by_pos=match‑by‑position] )

Arguments

input‑columns Comma-separated list of columns to use from the input relation, or asterisk (*) to select all columns.

Parameter Settings

Parameter name Set to…
model_name Name of the model (case-insensitive)
match_by_pos

Boolean value that specifies how input columns are matched to model features:

  • false (default): Match by name.

  • true: Match by the position of columns in the input columns list.

Examples

=> SELECT PREDICT_SVM_REGRESSOR(waiting USING PARAMETERS model_name='mySvmRegModel')
           FROM faithful ORDER BY id;
 PREDICT_SVM_REGRESSOR
--------------------
   4.06488248694445
   2.30392277646291 
   3.71269054484815
   2.867429883817
   4.48751281746003
   2.37436116488217
   4.69882798271781
   4.48751281746003
   2.09260761120512
…
 (272 rows)

This example shows how you can use the PREDICT_SVM_REGRESSOR function on the faithful table, using the match_by_pos parameter. In this example, the waiting column was replaced with the constant 40:

=> SELECT PREDICT_SVM_REGRESSOR(40 USING PARAMETERS model_name='mySvmRegModel', match_by_pos='true')
           FROM faithful ORDER BY id;
 PREDICT_SVM_REGRESSOR
--------------------
   1.31778533859324
   1.31778533859324
   1.31778533859324 
   1.31778533859324
   1.31778533859324
   1.31778533859324
   1.31778533859324
   1.31778533859324
   1.31778533859324
…
 (272 rows)

See Also