pulumi-aws-native-kotlin/com.pulumi.awsnative.sagemaker.kotlin.inputs/ModelExplainabilityJobDefinitionEndpointInputArgs

ModelExplainabilityJobDefinitionEndpointInputArgs

data class ModelExplainabilityJobDefinitionEndpointInputArgs(val endpointName: Output<String>, val featuresAttribute: Output<String>? = null, val inferenceAttribute: Output<String>? = null, val localPath: Output<String>, val probabilityAttribute: Output<String>? = null, val s3DataDistributionType: Output<ModelExplainabilityJobDefinitionEndpointInputS3DataDistributionType>? = null, val s3InputMode: Output<ModelExplainabilityJobDefinitionEndpointInputS3InputMode>? = null) : ConvertibleToJava<ModelExplainabilityJobDefinitionEndpointInputArgs>

The endpoint for a monitoring job.

Constructors

fun ModelExplainabilityJobDefinitionEndpointInputArgs(endpointName: Output<String>, featuresAttribute: Output<String>? = null, inferenceAttribute: Output<String>? = null, localPath: Output<String>, probabilityAttribute: Output<String>? = null, s3DataDistributionType: Output<ModelExplainabilityJobDefinitionEndpointInputS3DataDistributionType>? = null, s3InputMode: Output<ModelExplainabilityJobDefinitionEndpointInputS3InputMode>? = null)

Functions

Link copied to clipboard
open override fun toJava(): ModelExplainabilityJobDefinitionEndpointInputArgs

Properties

Link copied to clipboard
val endpointName: Output<String>
Link copied to clipboard
val featuresAttribute: Output<String>? = null

JSONpath to locate features in JSONlines dataset

Link copied to clipboard
val inferenceAttribute: Output<String>? = null

Index or JSONpath to locate predicted label(s)

Link copied to clipboard
val localPath: Output<String>

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

Link copied to clipboard
val probabilityAttribute: Output<String>? = null

Index or JSONpath to locate probabilities

Link copied to clipboard
val s3DataDistributionType: Output<ModelExplainabilityJobDefinitionEndpointInputS3DataDistributionType>? = null

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

Link copied to clipboard
val s3InputMode: Output<ModelExplainabilityJobDefinitionEndpointInputS3InputMode>? = 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.