Class: Google::Apis::LanguageV1beta2::XpsClassificationEvaluationMetrics

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/language_v1beta2/classes.rb,
lib/google/apis/language_v1beta2/representations.rb,
lib/google/apis/language_v1beta2/representations.rb

Overview

Model evaluation metrics for classification problems. It can be used for image and video classification. Next tag: 9.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ XpsClassificationEvaluationMetrics

Returns a new instance of XpsClassificationEvaluationMetrics.



1513
1514
1515
# File 'lib/google/apis/language_v1beta2/classes.rb', line 1513

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

Instance Attribute Details

#au_prcFloat

The Area under precision recall curve metric. Corresponds to the JSON property auPrc

Returns:

  • (Float)


1479
1480
1481
# File 'lib/google/apis/language_v1beta2/classes.rb', line 1479

def au_prc
  @au_prc
end

#au_rocFloat

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

Returns:

  • (Float)


1485
1486
1487
# File 'lib/google/apis/language_v1beta2/classes.rb', line 1485

def au_roc
  @au_roc
end

#base_au_prcFloat

The Area under precision recall curve metric based on priors. Corresponds to the JSON property baseAuPrc

Returns:

  • (Float)


1490
1491
1492
# File 'lib/google/apis/language_v1beta2/classes.rb', line 1490

def base_au_prc
  @base_au_prc
end

#confidence_metrics_entriesArray<Google::Apis::LanguageV1beta2::XpsConfidenceMetricsEntry>

Metrics that have confidence thresholds. Precision-recall curve can be derived from it. Corresponds to the JSON property confidenceMetricsEntries



1496
1497
1498
# File 'lib/google/apis/language_v1beta2/classes.rb', line 1496

def confidence_metrics_entries
  @confidence_metrics_entries
end

#confusion_matrixGoogle::Apis::LanguageV1beta2::XpsConfusionMatrix

Confusion matrix of the model running the classification. Corresponds to the JSON property confusionMatrix



1501
1502
1503
# File 'lib/google/apis/language_v1beta2/classes.rb', line 1501

def confusion_matrix
  @confusion_matrix
end

#evaluated_examples_countFixnum

The number of examples used for model evaluation. Corresponds to the JSON property evaluatedExamplesCount

Returns:

  • (Fixnum)


1506
1507
1508
# File 'lib/google/apis/language_v1beta2/classes.rb', line 1506

def evaluated_examples_count
  @evaluated_examples_count
end

#log_lossFloat

The Log Loss metric. Corresponds to the JSON property logLoss

Returns:

  • (Float)


1511
1512
1513
# File 'lib/google/apis/language_v1beta2/classes.rb', line 1511

def log_loss
  @log_loss
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



1518
1519
1520
1521
1522
1523
1524
1525
1526
# File 'lib/google/apis/language_v1beta2/classes.rb', line 1518

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