The ML.STANDARD_SCALER function

This document describes theML.STANDARD_SCALER function, which lets you scalea numerical expression by usingz-score.

When used in theTRANSFORM clause,thestandard deviation andmean values calculated to standardize theexpression are automatically used in prediction.

You can use this function with models that supportmanual feature preprocessing. For moreinformation, see the following documents:

• End-to-end user journeys for ML models
• Contribution analysis user journey

Syntax

ML.STANDARD_SCALER(numerical_expression) OVER()

Arguments

ML.STANDARD_SCALER takes the following argument:

• numerical_expression: thenumericalexpression to scale.

Output

ML.STANDARD_SCALER returns aFLOAT64 value that represents the scalednumerical expression.

Example

The following example scales a set of numerical expressions to have amean of0 and standard deviation of1:

SELECTf,ML.STANDARD_SCALER(f)OVER()ASoutputFROMUNNEST([1,2,3,4,5])ASf;

The output looks similar to the following:

+---+---------------------+| f |       output        |+---+---------------------+| 1 | -1.2649110640673518 || 5 |  1.2649110640673518 || 2 | -0.6324555320336759 || 4 |  0.6324555320336759 || 3 |                 0.0 |+---+---------------------+

What's next

• For information about feature preprocessing, seeFeature preprocessing overview.