View Source GoogleApi.AIPlatform.V1.Model.GoogleCloudAiplatformV1SchemaModelevaluationMetricsForecastingEvaluationMetricsQuantileMetricsEntry (google_api_ai_platform v0.24.0)

Entry for the Quantiles loss type optimization objective.

Attributes

observedQuantile (type: float(), default: nil) - This is a custom metric that calculates the percentage of true values that were less than the predicted value for that quantile. Only populated when optimization_objective is minimize-quantile-loss and each entry corresponds to an entry in quantiles The percent value can be used to compare with the quantile value, which is the target value.
quantile (type: float(), default: nil) - The quantile for this entry.
scaledPinballLoss (type: number(), default: nil) - The scaled pinball loss of this quantile.

Summary

Types

t()

Functions

decode(value, options)

Unwrap a decoded JSON object into its complex fields.

Types

t()

@type t() ::
  %GoogleApi.AIPlatform.V1.Model.GoogleCloudAiplatformV1SchemaModelevaluationMetricsForecastingEvaluationMetricsQuantileMetricsEntry{
    observedQuantile: float() | nil,
    quantile: float() | nil,
    scaledPinballLoss: number() | nil
  }

Functions

decode(value, options)

@spec decode(struct(), keyword()) :: struct()

Unwrap a decoded JSON object into its complex fields.