Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ExplanationMetadata

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1/classes.rb,
lib/google/apis/aiplatform_v1/representations.rb,
lib/google/apis/aiplatform_v1/representations.rb

Overview

Metadata describing the Model's input and output for explanation.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1ExplanationMetadata

Returns a new instance of GoogleCloudAiplatformV1ExplanationMetadata.



7051
7052
7053
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7051

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#feature_attributions_schema_uri ⇒ String

Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access. Corresponds to the JSON property featureAttributionsSchemaUri

Returns:

  • (String) 


7024
7025
7026
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7024

def feature_attributions_schema_uri
  @feature_attributions_schema_uri
end

#inputs ⇒ Hash<String,Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ExplanationMetadataInputMetadata>

Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature) . For custom images, the key must match with the key in instance. Corresponds to the JSON property inputs

Returns:



7036
7037
7038
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7036

def inputs
  @inputs
end

#latent_space_source ⇒ String

Name of the source to generate embeddings for example based explanations. Corresponds to the JSON property latentSpaceSource

Returns:

  • (String) 


7041
7042
7043
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7041

def latent_space_source
  @latent_space_source
end

#outputs ⇒ Hash<String,Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ExplanationMetadataOutputMetadata>

Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed. Corresponds to the JSON property outputs

Returns:



7049
7050
7051
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7049

def outputs
  @outputs
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



7056
7057
7058
7059
7060
7061
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7056

def update!(**args)
  @feature_attributions_schema_uri = args[:feature_attributions_schema_uri] if args.key?(:feature_attributions_schema_uri)
  @inputs = args[:inputs] if args.key?(:inputs)
  @latent_space_source = args[:latent_space_source] if args.key?(:latent_space_source)
  @outputs = args[:outputs] if args.key?(:outputs)
end