Model
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
Link copied to clipboard
constructor(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)
Properties
Link copied to clipboard
An endpoint in customer's account which has enabled DataCaptureConfig enabled.
Link copied to clipboard
Monitoring end time offset, e.g. PT0H
Link copied to clipboard
Index or JSONpath to locate predicted label(s)
Link copied to clipboard
Index or JSONpath to locate probabilities
Link copied to clipboard
The threshold for the class probability to be evaluated as a positive result.
Link copied to clipboard
Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defauts to FullyReplicated
Link copied to clipboard
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.
Link copied to clipboard
Monitoring start time offset, e.g. -PT1H