The ML.MIN_MAX_SCALER function

This document describes theML.MIN_MAX_SCALER function, which lets you scalea numerical_expression to the range[0, 1]. Negative values are set to0,and values above1 are set to1.

When used in theTRANSFORM clause,the range of[0,1] is automatically used in prediction, and predictedvalues outside that range are similarly capped.

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.MIN_MAX_SCALER(numerical_expression) OVER()

Arguments

ML.MIN_MAX_SCALER takes the following argument:

• numerical_expression: thenumericalexpression to scale.

Output

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

Example

The following example scales a set of numerical expressions to values between0 and1:

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

The output looks similar to the following:

+---+--------+| f | output |+---+--------+| 4 |   0.75 || 2 |   0.25 || 1 |    0.0 || 3 |    0.5 || 5 |    1.0 |+---+--------+

What's next

• For information about feature preprocessing, seeFeature preprocessing overview.