Amazonka.FraudDetector.Types.TrainingMetrics

Documentation

data TrainingMetrics

The training metric details.

See: newTrainingMetrics smart constructor.

Constructors

TrainingMetrics'

Fields

• auc :: Maybe Double

  The area under the curve. This summarizes true positive rate (TPR) and false positive rate (FPR) across all possible model score thresholds. A model with no predictive power has an AUC of 0.5, whereas a perfect model has a score of 1.0.

• metricDataPoints :: Maybe [MetricDataPoint]

  The data points details.

Instances

FromJSON TrainingMetrics

Defined in Amazonka.FraudDetector.Types.TrainingMetrics

Methods

parseJSON :: Value -> Parser TrainingMetrics

parseJSONList :: Value -> Parser [TrainingMetrics]

Generic TrainingMetrics

Defined in Amazonka.FraudDetector.Types.TrainingMetrics

Associated Types

type Rep TrainingMetrics :: Type -> Type

Methods

from :: TrainingMetrics -> Rep TrainingMetrics x

to :: Rep TrainingMetrics x -> TrainingMetrics

Read TrainingMetrics

Defined in Amazonka.FraudDetector.Types.TrainingMetrics

Methods

readsPrec :: Int -> ReadS TrainingMetrics

readList :: ReadS [TrainingMetrics]

readPrec :: ReadPrec TrainingMetrics

readListPrec :: ReadPrec [TrainingMetrics]

Show TrainingMetrics

Defined in Amazonka.FraudDetector.Types.TrainingMetrics

Methods

showsPrec :: Int -> TrainingMetrics -> ShowS

show :: TrainingMetrics -> String

showList :: [TrainingMetrics] -> ShowS

NFData TrainingMetrics

Defined in Amazonka.FraudDetector.Types.TrainingMetrics

Methods

rnf :: TrainingMetrics -> ()

Eq TrainingMetrics

Defined in Amazonka.FraudDetector.Types.TrainingMetrics

Methods

(==) :: TrainingMetrics -> TrainingMetrics -> Bool

(/=) :: TrainingMetrics -> TrainingMetrics -> Bool

Hashable TrainingMetrics

Defined in Amazonka.FraudDetector.Types.TrainingMetrics

Methods

hashWithSalt :: Int -> TrainingMetrics -> Int

hash :: TrainingMetrics -> Int

type Rep TrainingMetrics

Defined in Amazonka.FraudDetector.Types.TrainingMetrics

type Rep TrainingMetrics = D1 ('MetaData "TrainingMetrics" "Amazonka.FraudDetector.Types.TrainingMetrics" "amazonka-frauddetector-2.0-CdXFXtLV8DgKo4Kta7Jw61" 'False) (C1 ('MetaCons "TrainingMetrics'" 'PrefixI 'True) (S1 ('MetaSel ('Just "auc") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Double)) :*: S1 ('MetaSel ('Just "metricDataPoints") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe [MetricDataPoint]))))

newTrainingMetrics :: TrainingMetrics

Create a value of TrainingMetrics with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:auc:TrainingMetrics', trainingMetrics_auc - The area under the curve. This summarizes true positive rate (TPR) and false positive rate (FPR) across all possible model score thresholds. A model with no predictive power has an AUC of 0.5, whereas a perfect model has a score of 1.0.

$sel:metricDataPoints:TrainingMetrics', trainingMetrics_metricDataPoints - The data points details.

trainingMetrics_auc :: Lens' TrainingMetrics (Maybe Double)

The area under the curve. This summarizes true positive rate (TPR) and false positive rate (FPR) across all possible model score thresholds. A model with no predictive power has an AUC of 0.5, whereas a perfect model has a score of 1.0.

trainingMetrics_metricDataPoints :: Lens' TrainingMetrics (Maybe [MetricDataPoint])

The data points details.