class Google::Apis::BigqueryV2::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.
Attributes
Accuracy is the fraction of predictions given the correct label. For multiclass this is a micro-averaged metric. Corresponds to the JSON property `accuracy` @return [Float]
The F1 score is an average of recall and precision. For multiclass this is a macro-averaged metric. Corresponds to the JSON property `f1Score` @return [Float]
Logarithmic Loss. For multiclass this is a macro-averaged metric. Corresponds to the JSON property `logLoss` @return [Float]
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. Corresponds to the JSON property `precision` @return [Float]
Recall is the fraction of actual positive labels that were given a positive prediction. For multiclass this is a macro-averaged metric. Corresponds to the JSON property `recall` @return [Float]
Area Under a ROC Curve. For multiclass this is a macro-averaged metric. Corresponds to the JSON property `rocAuc` @return [Float]
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. Corresponds to the JSON property `threshold` @return [Float]
Public Class Methods
# File lib/google/apis/bigquery_v2/classes.rb, line 75 def initialize(**args) update!(**args) end
Public Instance Methods
Update properties of this object
# File lib/google/apis/bigquery_v2/classes.rb, line 80 def update!(**args) @accuracy = args[:accuracy] if args.key?(:accuracy) @f1_score = args[:f1_score] if args.key?(:f1_score) @log_loss = args[:log_loss] if args.key?(:log_loss) @precision = args[:precision] if args.key?(:precision) @recall = args[:recall] if args.key?(:recall) @roc_auc = args[:roc_auc] if args.key?(:roc_auc) @threshold = args[:threshold] if args.key?(:threshold) end