aws-cdk-lib.aws_sagemaker.CfnModelQualityJobDefinition.EndpointInputProperty

interface EndpointInputProperty

LanguageType name
.NETAmazon.CDK.AWS.Sagemaker.CfnModelQualityJobDefinition.EndpointInputProperty
Gogithub.com/aws/aws-cdk-go/awscdk/v2/awssagemaker#CfnModelQualityJobDefinition_EndpointInputProperty
Javasoftware.amazon.awscdk.services.sagemaker.CfnModelQualityJobDefinition.EndpointInputProperty
Pythonaws_cdk.aws_sagemaker.CfnModelQualityJobDefinition.EndpointInputProperty
TypeScript aws-cdk-lib » aws_sagemaker » CfnModelQualityJobDefinition » EndpointInputProperty

Input object for the endpoint.

Example

// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_sagemaker as sagemaker } from 'aws-cdk-lib';
const endpointInputProperty: sagemaker.CfnModelQualityJobDefinition.EndpointInputProperty = {
  endpointName: 'endpointName',
  localPath: 'localPath',

  // the properties below are optional
  endTimeOffset: 'endTimeOffset',
  inferenceAttribute: 'inferenceAttribute',
  probabilityAttribute: 'probabilityAttribute',
  probabilityThresholdAttribute: 123,
  s3DataDistributionType: 's3DataDistributionType',
  s3InputMode: 's3InputMode',
  startTimeOffset: 'startTimeOffset',
};

Properties

NameTypeDescription
endpointNamestringAn endpoint in customer's account which has enabled DataCaptureConfig enabled.
localPathstringPath to the filesystem where the endpoint data is available to the container.
endTimeOffset?stringIf specified, monitoring jobs substract this time from the end time.
inferenceAttribute?stringThe attribute of the input data that represents the ground truth label.
probabilityAttribute?stringIn a classification problem, the attribute that represents the class probability.
probabilityThresholdAttribute?numberThe threshold for the class probability to be evaluated as a positive result.
s3DataDistributionType?stringWhether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key.
s3InputMode?stringWhether the Pipe or File is used as the input mode for transferring data for the monitoring job.
startTimeOffset?stringIf specified, monitoring jobs substract this time from the start time.

endpointName

Type: string

An endpoint in customer's account which has enabled DataCaptureConfig enabled.


localPath

Type: string

Path to the filesystem where the endpoint data is available to the container.


endTimeOffset?

Type: string (optional)

If specified, monitoring jobs substract this time from the end time.

For information about using offsets for scheduling monitoring jobs, see Schedule Model Quality Monitoring Jobs .


inferenceAttribute?

Type: string (optional)

The attribute of the input data that represents the ground truth label.


probabilityAttribute?

Type: string (optional)

In a classification problem, the attribute that represents the class probability.


probabilityThresholdAttribute?

Type: number (optional)

The threshold for the class probability to be evaluated as a positive result.


s3DataDistributionType?

Type: string (optional)

Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key.

Defaults to FullyReplicated


s3InputMode?

Type: string (optional)

Whether the Pipe or File is used as the input mode for transferring data for the monitoring job.

Pipe mode is recommended for large datasets. File mode is useful for small files that fit in memory. Defaults to File .


startTimeOffset?

Type: string (optional)

If specified, monitoring jobs substract this time from the start time.

For information about using offsets for scheduling monitoring jobs, see Schedule Model Quality Monitoring Jobs .