interface MLSyntheticDataParametersProperty
| Language | Type name |
|---|---|
.NET | Amazon.CDK.AWS.CleanRooms.CfnAnalysisTemplate.MLSyntheticDataParametersProperty |
Go | github.com/aws/aws-cdk-go/awscdk/v2/awscleanrooms#CfnAnalysisTemplate_MLSyntheticDataParametersProperty |
Java | software.amazon.awscdk.services.cleanrooms.CfnAnalysisTemplate.MLSyntheticDataParametersProperty |
Python | aws_cdk.aws_cleanrooms.CfnAnalysisTemplate.MLSyntheticDataParametersProperty |
TypeScript | aws-cdk-lib » aws_cleanrooms » CfnAnalysisTemplate » MLSyntheticDataParametersProperty |
Parameters that control the generation of synthetic data for machine learning, including privacy settings and column classification details.
Example
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_cleanrooms as cleanrooms } from 'aws-cdk-lib';
const mLSyntheticDataParametersProperty: cleanrooms.CfnAnalysisTemplate.MLSyntheticDataParametersProperty = {
columnClassification: {
columnMapping: [{
columnName: 'columnName',
columnType: 'columnType',
isPredictiveValue: false,
}],
},
epsilon: 123,
maxMembershipInferenceAttackScore: 123,
};
Properties
| Name | Type | Description |
|---|---|---|
| column | IResolvable | Column | Classification details for data columns that specify how each column should be treated during synthetic data generation. |
| epsilon | number | The epsilon value for differential privacy when generating synthetic data. |
| max | number | The maximum acceptable score for membership inference attack vulnerability. |
columnClassification
Type:
IResolvable | Column
Classification details for data columns that specify how each column should be treated during synthetic data generation.
epsilon
Type:
number
The epsilon value for differential privacy when generating synthetic data.
Lower values provide stronger privacy guarantees but may reduce data utility.
maxMembershipInferenceAttackScore
Type:
number
The maximum acceptable score for membership inference attack vulnerability.
Synthetic data generation fails if the score for the resulting data exceeds this threshold.

.NET
Go
Java
Python
TypeScript