Package software.amazon.awssdk.services.sagemaker.model

Interface EndpointInput.Builder

All Superinterfaces:
Buildable, CopyableBuilder<EndpointInput.Builder,EndpointInput>, SdkBuilder<EndpointInput.Builder,EndpointInput>, SdkPojo
Enclosing class:
EndpointInput
public static interface EndpointInput.Builder extends SdkPojo, CopyableBuilder<EndpointInput.Builder,EndpointInput>

  • Method Details

    • endpointName

      EndpointInput.Builder endpointName(String endpointName)

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

      Parameters:
      endpointName - An endpoint in customer's account which has enabled DataCaptureConfig enabled.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • localPath

      EndpointInput.Builder localPath(String localPath)

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

      Parameters:
      localPath - Path to the filesystem where the endpoint data is available to the container.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • s3InputMode

      EndpointInput.Builder s3InputMode(String s3InputMode)

      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.

      Parameters:
      s3InputMode - 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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • s3InputMode

      EndpointInput.Builder s3InputMode(ProcessingS3InputMode s3InputMode)

      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.

      Parameters:
      s3InputMode - 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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • s3DataDistributionType

      EndpointInput.Builder s3DataDistributionType(String s3DataDistributionType)

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

      Parameters:
      s3DataDistributionType - Whether input data distributed in Amazon S3 is fully replicated or sharded by an Amazon S3 key. Defaults to FullyReplicated
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • s3DataDistributionType

      EndpointInput.Builder s3DataDistributionType(ProcessingS3DataDistributionType s3DataDistributionType)

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

      Parameters:
      s3DataDistributionType - Whether input data distributed in Amazon S3 is fully replicated or sharded by an Amazon S3 key. Defaults to FullyReplicated
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • featuresAttribute

      EndpointInput.Builder featuresAttribute(String featuresAttribute)

      The attributes of the input data that are the input features.

      Parameters:
      featuresAttribute - The attributes of the input data that are the input features.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • inferenceAttribute

      EndpointInput.Builder inferenceAttribute(String inferenceAttribute)

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

      Parameters:
      inferenceAttribute - The attribute of the input data that represents the ground truth label.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • probabilityAttribute

      EndpointInput.Builder probabilityAttribute(String probabilityAttribute)

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

      Parameters:
      probabilityAttribute - In a classification problem, the attribute that represents the class probability.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • probabilityThresholdAttribute

      EndpointInput.Builder probabilityThresholdAttribute(Double probabilityThresholdAttribute)

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

      Parameters:
      probabilityThresholdAttribute - The threshold for the class probability to be evaluated as a positive result.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • startTimeOffset

      EndpointInput.Builder startTimeOffset(String startTimeOffset)

      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.

      Parameters:
      startTimeOffset - 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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • endTimeOffset

      EndpointInput.Builder endTimeOffset(String endTimeOffset)

      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.

      Parameters:
      endTimeOffset - 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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • excludeFeaturesAttribute

      EndpointInput.Builder excludeFeaturesAttribute(String excludeFeaturesAttribute)

      The attributes of the input data to exclude from the analysis.

      Parameters:
      excludeFeaturesAttribute - The attributes of the input data to exclude from the analysis.
      Returns:
      Returns a reference to this object so that method calls can be chained together.