Skip to content

EndpointInput

Source code in docs_src/capo_sagemaker/types/endpoint_input.py
class EndpointInput(TypedDict, closed=True):
    endpoint_name: NotRequired["capo_sagemaker.types.endpoint_name.EndpointName"]
    """<p>An endpoint in customer's account which has enabled <code>DataCaptureConfig</code> enabled.</p>"""
    local_path: NotRequired[
        "capo_sagemaker.types.processing_local_path.ProcessingLocalPath"
    ]
    """<p>Path to the filesystem where the endpoint data is available to the container.</p>"""
    s3_input_mode: NotRequired[
        "capo_sagemaker.types.processing_s3_input_mode.ProcessingS3InputMode"
    ]
    """<p>Whether the <code>Pipe</code> or <code>File</code> is used as the input mode for transferring data for the monitoring job. <code>Pipe</code> mode is recommended for large datasets. <code>File</code> mode is useful for small files that fit in memory. Defaults to <code>File</code>.</p>"""
    s3_data_distribution_type: NotRequired[
        "capo_sagemaker.types.processing_s3_data_distribution_type.ProcessingS3DataDistributionType"
    ]
    """<p>Whether input data distributed in Amazon S3 is fully replicated or sharded by an Amazon S3 key. Defaults to <code>FullyReplicated</code> </p>"""
    features_attribute: NotRequired["capo_sagemaker.types.string.String"]
    """<p>The attributes of the input data that are the input features.</p>"""
    inference_attribute: NotRequired["capo_sagemaker.types.string.String"]
    """<p>The attribute of the input data that represents the ground truth label.</p>"""
    probability_attribute: NotRequired["capo_sagemaker.types.string.String"]
    """<p>In a classification problem, the attribute that represents the class probability.</p>"""
    probability_threshold_attribute: NotRequired[
        "capo_sagemaker.types.probability_threshold_attribute.ProbabilityThresholdAttribute"
    ]
    """<p>The threshold for the class probability to be evaluated as a positive result.</p>"""
    start_time_offset: NotRequired[
        "capo_sagemaker.types.monitoring_time_offset_string.MonitoringTimeOffsetString"
    ]
    """<p>If specified, monitoring jobs substract this time from the start time. For information about using offsets for scheduling monitoring jobs, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-model-quality-schedule.html">Schedule Model Quality Monitoring Jobs</a>.</p>"""
    end_time_offset: NotRequired[
        "capo_sagemaker.types.monitoring_time_offset_string.MonitoringTimeOffsetString"
    ]
    """<p>If specified, monitoring jobs substract this time from the end time. For information about using offsets for scheduling monitoring jobs, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-model-quality-schedule.html">Schedule Model Quality Monitoring Jobs</a>.</p>"""
    exclude_features_attribute: NotRequired[
        "capo_sagemaker.types.exclude_features_attribute.ExcludeFeaturesAttribute"
    ]
    """<p>The attributes of the input data to exclude from the analysis.</p>"""

end_time_offset instance-attribute

end_time_offset: NotRequired[MonitoringTimeOffsetString]

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.

endpoint_name instance-attribute

endpoint_name: NotRequired[EndpointName]

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

exclude_features_attribute instance-attribute

exclude_features_attribute: NotRequired[ExcludeFeaturesAttribute]

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

features_attribute instance-attribute

features_attribute: NotRequired[String]

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

inference_attribute instance-attribute

inference_attribute: NotRequired[String]

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

local_path instance-attribute

local_path: NotRequired[ProcessingLocalPath]

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

probability_attribute instance-attribute

probability_attribute: NotRequired[String]

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

probability_threshold_attribute instance-attribute

probability_threshold_attribute: NotRequired[ProbabilityThresholdAttribute]

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

s3_data_distribution_type instance-attribute

s3_data_distribution_type: NotRequired[ProcessingS3DataDistributionType]

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

s3_input_mode instance-attribute

s3_input_mode: NotRequired[ProcessingS3InputMode]

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.

start_time_offset instance-attribute

start_time_offset: NotRequired[MonitoringTimeOffsetString]

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.