Class AggregateClassificationMetrics

Aggregate metrics for classification/classifier models. For multi-class models, the metrics are either macro-averaged or micro-averaged. When macro-averaged, the metrics are calculated for each label and then an unweighted average is taken of those values. When micro-averaged, the metric is calculated globally by counting the total number of correctly predicted rows.

Inheritance
System.Object
AggregateClassificationMetrics
Inherited Members
System.Object.Equals(System.Object)
System.Object.Equals(System.Object, System.Object)
System.Object.GetHashCode()
System.Object.GetType()
System.Object.MemberwiseClone()
System.Object.ReferenceEquals(System.Object, System.Object)
System.Object.ToString()
Namespace: Google.Apis.Bigquery.v2.Data
Assembly: Google.Apis.Bigquery.v2.dll
Syntax
public class AggregateClassificationMetrics : IDirectResponseSchema

Properties

Accuracy

Accuracy is the fraction of predictions given the correct label. For multiclass this is a micro-averaged metric.

Declaration
[JsonProperty("accuracy")]
public virtual double? Accuracy { get; set; }
Property Value
Type Description
System.Nullable<System.Double>

ETag

The ETag of the item.

Declaration
public virtual string ETag { get; set; }
Property Value
Type Description
System.String

F1Score

The F1 score is an average of recall and precision. For multiclass this is a macro-averaged metric.

Declaration
[JsonProperty("f1Score")]
public virtual double? F1Score { get; set; }
Property Value
Type Description
System.Nullable<System.Double>

LogLoss

Logarithmic Loss. For multiclass this is a macro-averaged metric.

Declaration
[JsonProperty("logLoss")]
public virtual double? LogLoss { get; set; }
Property Value
Type Description
System.Nullable<System.Double>

Precision

Precision is the fraction of actual positive predictions that had positive actual labels. For multiclass this is a macro-averaged metric treating each class as a binary classifier.

Declaration
[JsonProperty("precision")]
public virtual double? Precision { get; set; }
Property Value
Type Description
System.Nullable<System.Double>

Recall

Recall is the fraction of actual positive labels that were given a positive prediction. For multiclass this is a macro-averaged metric.

Declaration
[JsonProperty("recall")]
public virtual double? Recall { get; set; }
Property Value
Type Description
System.Nullable<System.Double>

RocAuc

Area Under a ROC Curve. For multiclass this is a macro-averaged metric.

Declaration
[JsonProperty("rocAuc")]
public virtual double? RocAuc { get; set; }
Property Value
Type Description
System.Nullable<System.Double>

Threshold

Threshold at which the metrics are computed. For binary classification models this is the positive class threshold. For multi-class classfication models this is the confidence threshold.

Declaration
[JsonProperty("threshold")]
public virtual double? Threshold { get; set; }
Property Value
Type Description
System.Nullable<System.Double>

Implements