Class: AWSCDK::Sagemaker::CfnModelQualityJobDefinition::EndpointInputProperty

Inherits:
Jsii::Struct
  • Object
show all
Defined in:
sagemaker/cfn_model_quality_job_definition.rb

Overview

Input object for the endpoint.

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(endpoint_name:, local_path:, end_time_offset: nil, inference_attribute: nil, probability_attribute: nil, probability_threshold_attribute: nil, s3_data_distribution_type: nil, s3_input_mode: nil, start_time_offset: nil) ⇒ EndpointInputProperty

Returns a new instance of EndpointInputProperty.

Parameters:

  • endpoint_name (String)

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

  • local_path (String)

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

  • end_time_offset (String, nil) (defaults to: nil)

    If specified, monitoring jobs substract this time from the end time.

  • inference_attribute (String, nil) (defaults to: nil)

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

  • probability_attribute (String, nil) (defaults to: nil)

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

  • probability_threshold_attribute (Numeric, nil) (defaults to: nil)

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

  • s3_data_distribution_type (String, nil) (defaults to: nil)

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

  • s3_input_mode (String, nil) (defaults to: nil)

    Whether the Pipe or File is used as the input mode for transferring data for the monitoring job.

  • start_time_offset (String, nil) (defaults to: nil)

    If specified, monitoring jobs substract this time from the start time.



982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 982

def initialize(endpoint_name:, local_path:, end_time_offset: nil, inference_attribute: nil, probability_attribute: nil, probability_threshold_attribute: nil, s3_data_distribution_type: nil, s3_input_mode: nil, start_time_offset: nil)
  @endpoint_name = endpoint_name
  Jsii::Type.check_type(@endpoint_name, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJzdHJpbmcifQ==")), "endpointName")
  @local_path = local_path
  Jsii::Type.check_type(@local_path, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJzdHJpbmcifQ==")), "localPath")
  @end_time_offset = end_time_offset
  Jsii::Type.check_type(@end_time_offset, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJzdHJpbmcifQ==")), "endTimeOffset") unless @end_time_offset.nil?
  @inference_attribute = inference_attribute
  Jsii::Type.check_type(@inference_attribute, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJzdHJpbmcifQ==")), "inferenceAttribute") unless @inference_attribute.nil?
  @probability_attribute = probability_attribute
  Jsii::Type.check_type(@probability_attribute, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJzdHJpbmcifQ==")), "probabilityAttribute") unless @probability_attribute.nil?
  @probability_threshold_attribute = probability_threshold_attribute
  Jsii::Type.check_type(@probability_threshold_attribute, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJudW1iZXIifQ==")), "probabilityThresholdAttribute") unless @probability_threshold_attribute.nil?
  @s3_data_distribution_type = s3_data_distribution_type
  Jsii::Type.check_type(@s3_data_distribution_type, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJzdHJpbmcifQ==")), "s3DataDistributionType") unless @s3_data_distribution_type.nil?
  @s3_input_mode = s3_input_mode
  Jsii::Type.check_type(@s3_input_mode, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJzdHJpbmcifQ==")), "s3InputMode") unless @s3_input_mode.nil?
  @start_time_offset = start_time_offset
  Jsii::Type.check_type(@start_time_offset, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJzdHJpbmcifQ==")), "startTimeOffset") unless @start_time_offset.nil?
end

Instance Attribute Details

#end_time_offsetString? (readonly)

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 .



1019
1020
1021
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1019

def end_time_offset
  @end_time_offset
end

#endpoint_nameString (readonly)

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



1007
1008
1009
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1007

def endpoint_name
  @endpoint_name
end

#inference_attributeString? (readonly)

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



1024
1025
1026
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1024

def inference_attribute
  @inference_attribute
end

#local_pathString (readonly)

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



1012
1013
1014
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1012

def local_path
  @local_path
end

#probability_attributeString? (readonly)

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



1029
1030
1031
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1029

def probability_attribute
  @probability_attribute
end

#probability_threshold_attributeNumeric? (readonly)

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



1034
1035
1036
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1034

def probability_threshold_attribute
  @probability_threshold_attribute
end

#s3_data_distribution_typeString? (readonly)

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

Defaults to FullyReplicated



1041
1042
1043
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1041

def s3_data_distribution_type
  @s3_data_distribution_type
end

#s3_input_modeString? (readonly)

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 .



1048
1049
1050
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1048

def s3_input_mode
  @s3_input_mode
end

#start_time_offsetString? (readonly)

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 .



1055
1056
1057
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1055

def start_time_offset
  @start_time_offset
end

Class Method Details

.jsii_propertiesObject



1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1057

def self.jsii_properties
  {
    :endpoint_name => "endpointName",
    :local_path => "localPath",
    :end_time_offset => "endTimeOffset",
    :inference_attribute => "inferenceAttribute",
    :probability_attribute => "probabilityAttribute",
    :probability_threshold_attribute => "probabilityThresholdAttribute",
    :s3_data_distribution_type => "s3DataDistributionType",
    :s3_input_mode => "s3InputMode",
    :start_time_offset => "startTimeOffset",
  }
end

Instance Method Details

#to_jsiiObject



1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
# File 'sagemaker/cfn_model_quality_job_definition.rb', line 1071

def to_jsii
  result = {}
  result.merge!({
    "endpointName" => @endpoint_name,
    "localPath" => @local_path,
    "endTimeOffset" => @end_time_offset,
    "inferenceAttribute" => @inference_attribute,
    "probabilityAttribute" => @probability_attribute,
    "probabilityThresholdAttribute" => @probability_threshold_attribute,
    "s3DataDistributionType" => @s3_data_distribution_type,
    "s3InputMode" => @s3_input_mode,
    "startTimeOffset" => @start_time_offset,
  })
  result.compact
end