Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaModelevaluationMetricsForecastingEvaluationMetrics

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

Metrics for forecasting evaluation results.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1SchemaModelevaluationMetricsForecastingEvaluationMetrics

Returns a new instance of GoogleCloudAiplatformV1SchemaModelevaluationMetricsForecastingEvaluationMetrics.



17121
17122
17123
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17121

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

Instance Attribute Details

#mean_absolute_error ⇒ Float

Mean Absolute Error (MAE). Corresponds to the JSON property meanAbsoluteError

Returns:

  • (Float) 


17078
17079
17080
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17078

def mean_absolute_error
  @mean_absolute_error
end

#mean_absolute_percentage_error ⇒ Float

Mean absolute percentage error. Infinity when there are zeros in the ground truth. Corresponds to the JSON property meanAbsolutePercentageError

Returns:

  • (Float) 


17084
17085
17086
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17084

def mean_absolute_percentage_error
  @mean_absolute_percentage_error
end

#quantile_metrics ⇒ Array<Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaModelevaluationMetricsForecastingEvaluationMetricsQuantileMetricsEntry>

The quantile metrics entries for each quantile. Corresponds to the JSON property quantileMetrics

Returns:



17089
17090
17091
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17089

def quantile_metrics
  @quantile_metrics
end

#r_squared ⇒ Float

Coefficient of determination as Pearson correlation coefficient. Undefined when ground truth or predictions are constant or near constant. Corresponds to the JSON property rSquared

Returns:

  • (Float) 


17095
17096
17097
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17095

def r_squared
  @r_squared
end

#root_mean_squared_error ⇒ Float

Root Mean Squared Error (RMSE). Corresponds to the JSON property rootMeanSquaredError

Returns:

  • (Float) 


17100
17101
17102
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17100

def root_mean_squared_error
  @root_mean_squared_error
end

#root_mean_squared_log_error ⇒ Float

Root mean squared log error. Undefined when there are negative ground truth values or predictions. Corresponds to the JSON property rootMeanSquaredLogError

Returns:

  • (Float) 


17106
17107
17108
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17106

def root_mean_squared_log_error
  @root_mean_squared_log_error
end

#root_mean_squared_percentage_error ⇒ Float

Root Mean Square Percentage Error. Square root of MSPE. Undefined/imaginary when MSPE is negative. Corresponds to the JSON property rootMeanSquaredPercentageError

Returns:

  • (Float) 


17112
17113
17114
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17112

def root_mean_squared_percentage_error
  @root_mean_squared_percentage_error
end

#weighted_absolute_percentage_error ⇒ Float

Weighted Absolute Percentage Error. Does not use weights, this is just what the metric is called. Undefined if actual values sum to zero. Will be very large if actual values sum to a very small number. Corresponds to the JSON property weightedAbsolutePercentageError

Returns:

  • (Float) 


17119
17120
17121
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17119

def weighted_absolute_percentage_error
  @weighted_absolute_percentage_error
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



17126
17127
17128
17129
17130
17131
17132
17133
17134
17135
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 17126

def update!(**args)
  @mean_absolute_error = args[:mean_absolute_error] if args.key?(:mean_absolute_error)
  @mean_absolute_percentage_error = args[:mean_absolute_percentage_error] if args.key?(:mean_absolute_percentage_error)
  @quantile_metrics = args[:quantile_metrics] if args.key?(:quantile_metrics)
  @r_squared = args[:r_squared] if args.key?(:r_squared)
  @root_mean_squared_error = args[:root_mean_squared_error] if args.key?(:root_mean_squared_error)
  @root_mean_squared_log_error = args[:root_mean_squared_log_error] if args.key?(:root_mean_squared_log_error)
  @root_mean_squared_percentage_error = args[:root_mean_squared_percentage_error] if args.key?(:root_mean_squared_percentage_error)
  @weighted_absolute_percentage_error = args[:weighted_absolute_percentage_error] if args.key?(:weighted_absolute_percentage_error)
end