pulumi-aws-native-kotlin/com.pulumi.awsnative.sagemaker.kotlin.outputs/ModelQualityJobDefinitionEndpointInput

ModelQualityJobDefinitionEndpointInput

data class ModelQualityJobDefinitionEndpointInput(val endTimeOffset: String? = null, val endpointName: String, val inferenceAttribute: String? = null, val localPath: String, val probabilityAttribute: String? = null, val probabilityThresholdAttribute: Double? = null, val s3DataDistributionType: ModelQualityJobDefinitionEndpointInputS3DataDistributionType? = null, val s3InputMode: ModelQualityJobDefinitionEndpointInputS3InputMode? = null, val startTimeOffset: String? = null)

The endpoint for a monitoring job.

Constructors

fun ModelQualityJobDefinitionEndpointInput(endTimeOffset: String? = null, endpointName: String, inferenceAttribute: String? = null, localPath: String, probabilityAttribute: String? = null, probabilityThresholdAttribute: Double? = null, s3DataDistributionType: ModelQualityJobDefinitionEndpointInputS3DataDistributionType? = null, s3InputMode: ModelQualityJobDefinitionEndpointInputS3InputMode? = null, startTimeOffset: String? = null)

Types

Companion

object Companion

Properties

endpointName

val endpointName: String

endTimeOffset

val endTimeOffset: String? = null

Monitoring end time offset, e.g. PT0H

inferenceAttribute

val inferenceAttribute: String? = null

Index or JSONpath to locate predicted label(s)

localPath

val localPath: String

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

probabilityAttribute

val probabilityAttribute: String? = null

Index or JSONpath to locate probabilities

probabilityThresholdAttribute

val probabilityThresholdAttribute: Double? = null

s3DataDistributionType

val s3DataDistributionType: ModelQualityJobDefinitionEndpointInputS3DataDistributionType? = null

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

s3InputMode

val s3InputMode: ModelQualityJobDefinitionEndpointInputS3InputMode? = null

Whether the Pipe or File is used as the input mode for transfering 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

val startTimeOffset: String? = null

Monitoring start time offset, e.g. -PT1H