Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsClassificationEvaluationMetrics

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1beta1/classes.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb

Overview

Metrics for classification evaluation results.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsClassificationEvaluationMetrics

Returns a new instance of GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsClassificationEvaluationMetrics.



50814
50815
50816
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 50814

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

Instance Attribute Details

#au_prc ⇒ Float

The Area Under Precision-Recall Curve metric. Micro-averaged for the overall evaluation. Corresponds to the JSON property auPrc

Returns:

  • (Float) 


50787
50788
50789
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 50787

def au_prc
  @au_prc
end

#au_roc ⇒ Float

The Area Under Receiver Operating Characteristic curve metric. Micro-averaged for the overall evaluation. Corresponds to the JSON property auRoc

Returns:

  • (Float) 


50793
50794
50795
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 50793

def au_roc
  @au_roc
end

#confidence_metrics ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsClassificationEvaluationMetricsConfidenceMetrics>

Metrics for each confidenceThreshold in 0.00,0.05,0.10,...,0.95,0.96,0.97,0. 98,0.99 and positionThreshold = INT32_MAX_VALUE. ROC and precision-recall curves, and other aggregated metrics are derived from them. The confidence metrics entries may also be supplied for additional values of positionThreshold, but from these no aggregated metrics are computed. Corresponds to the JSON property confidenceMetrics

Returns:



50802
50803
50804
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 50802

def confidence_metrics
  @confidence_metrics
end

#confusion_matrix ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsConfusionMatrix

Confusion matrix of the evaluation. Corresponds to the JSON property confusionMatrix

Returns:



50807
50808
50809
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 50807

def confusion_matrix
  @confusion_matrix
end

#log_loss ⇒ Float

The Log Loss metric. Corresponds to the JSON property logLoss

Returns:

  • (Float) 


50812
50813
50814
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 50812

def log_loss
  @log_loss
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



50819
50820
50821
50822
50823
50824
50825
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 50819

def update!(**args)
  @au_prc = args[:au_prc] if args.key?(:au_prc)
  @au_roc = args[:au_roc] if args.key?(:au_roc)
  @confidence_metrics = args[:confidence_metrics] if args.key?(:confidence_metrics)
  @confusion_matrix = args[:confusion_matrix] if args.key?(:confusion_matrix)
  @log_loss = args[:log_loss] if args.key?(:log_loss)
end