kumulant/com.eignex.kumulant.stat.anomaly/GaussianScoreResult

GaussianScoreResult

@Serializable

@SerialName(value = "GaussianScoreResult")

data class GaussianScoreResult(val mean: Double, val variance: Double, val totalWeights: Double) : Result(source)

Snapshot from GaussianScorerStat: running mean / variance plus the most recently scored value. The score(x) helper computes a z-score |x - mean| / stdDev on demand using the captured stats.

Constructors

GaussianScoreResult

constructor(mean: Double, variance: Double, totalWeights: Double)

Properties

mean

val mean: Double

Running mean.

stdDev

val stdDev: Double

Sample standard deviation.

totalWeights

val totalWeights: Double

Cumulative observation weight folded in.

variance

val variance: Double

Running variance.

Functions

score

fun score(x: Double): Double

Absolute z-score |x - mean| / stdDev. Returns 0.0 when the running variance is degenerate (zero or near-zero) so a constant stream produces no false anomaly signal.