Struct aws_sdk_sagemaker::model::EndpointInput

#[non_exhaustive]
pub struct EndpointInput {
    pub endpoint_name: Option<String>,
    pub local_path: Option<String>,
    pub s3_input_mode: Option<ProcessingS3InputMode>,
    pub s3_data_distribution_type: Option<ProcessingS3DataDistributionType>,
    pub features_attribute: Option<String>,
    pub inference_attribute: Option<String>,
    pub probability_attribute: Option<String>,
    pub probability_threshold_attribute: Option<f64>,
    pub start_time_offset: Option<String>,
    pub end_time_offset: Option<String>,
}

Input object for the endpoint

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

endpoint_name: Option<String>

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

local_path: Option<String>

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

s3_input_mode: Option<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.

s3_data_distribution_type: Option<ProcessingS3DataDistributionType>

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

features_attribute: Option<String>

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

inference_attribute: Option<String>

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

probability_attribute: Option<String>

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

probability_threshold_attribute: Option<f64>

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

start_time_offset: Option<String>

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.

end_time_offset: Option<String>

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.

Implementations

impl EndpointInput

pub fn endpoint_name(&self) -> Option<&str>

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

pub fn local_path(&self) -> Option<&str>

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

pub fn s3_input_mode(&self) -> Option<&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.

pub fn s3_data_distribution_type(
    &self
) -> Option<&ProcessingS3DataDistributionType>

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

pub fn features_attribute(&self) -> Option<&str>

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

pub fn inference_attribute(&self) -> Option<&str>

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

pub fn probability_attribute(&self) -> Option<&str>

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

pub fn probability_threshold_attribute(&self) -> Option<f64>

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

pub fn start_time_offset(&self) -> Option<&str>

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.

pub fn end_time_offset(&self) -> Option<&str>

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.

impl EndpointInput

pub fn builder() -> Builder

Creates a new builder-style object to manufacture EndpointInput

Trait Implementations

impl Clone for EndpointInput

fn clone(&self) -> EndpointInput

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for EndpointInput

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq<EndpointInput> for EndpointInput

fn eq(&self, other: &EndpointInput) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &EndpointInput) -> bool

This method tests for !=.

impl StructuralPartialEq for EndpointInput