class Aws::SageMaker::Types::EndpointInput

Input object for the endpoint

@note When making an API call, you may pass EndpointInput

data as a hash:

    {
      endpoint_name: "EndpointName", # required
      local_path: "ProcessingLocalPath", # required
      s3_input_mode: "Pipe", # accepts Pipe, File
      s3_data_distribution_type: "FullyReplicated", # accepts FullyReplicated, ShardedByS3Key
      features_attribute: "String",
      inference_attribute: "String",
      probability_attribute: "String",
      probability_threshold_attribute: 1.0,
      start_time_offset: "MonitoringTimeOffsetString",
      end_time_offset: "MonitoringTimeOffsetString",
    }

@!attribute [rw] endpoint_name

An endpoint in customer's account which has enabled
`DataCaptureConfig` enabled.
@return [String]

@!attribute [rw] local_path

Path to the filesystem where the endpoint data is available to the
container.
@return [String]

@!attribute [rw] s3_input_mode

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`.
@return [String]

@!attribute [rw] s3_data_distribution_type

Whether input data distributed in Amazon S3 is fully replicated or
sharded by an S3 key. Defaults to `FullyReplicated`
@return [String]

@!attribute [rw] features_attribute

The attributes of the input data that are the input features.
@return [String]

@!attribute [rw] inference_attribute

The attribute of the input data that represents the ground truth
label.
@return [String]

@!attribute [rw] probability_attribute

In a classification problem, the attribute that represents the class
probability.
@return [String]

@!attribute [rw] probability_threshold_attribute

The threshold for the class probability to be evaluated as a
positive result.
@return [Float]

@!attribute [rw] start_time_offset

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][1].

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-model-quality-schedule.html
@return [String]

@!attribute [rw] end_time_offset

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][1].

[1]: https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-model-quality-schedule.html
@return [String]

@see docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/EndpointInput AWS API Documentation

Constants

SENSITIVE