TDigestResult
T-digest snapshot: means/weights are the centroid arrays sorted by mean, with quantiles precomputed for probabilities via CDF inversion.
Constructors
TDigestResult
Properties
compression
T-digest compression parameter; lower = more centroids, tighter quantiles.
means
Centroid means sorted ascending; parallel to weights.
probabilities
Probabilities at which quantiles are evaluated; parallel to quantiles.
quantiles
Estimated quantile values, parallel to probabilities.
totalWeight
Cumulative observation weight folded in.
totalWeights
Cumulative weight of observations folded into this result.
weights
Centroid weights, parallel to means.
True when totalWeights is not positive, including zero, negative values, and NaN.
Functions
equals
hashCode
toString
Scores value against the quantile precomputed at probability: 1.0 above it, otherwise 0.0. A NaN value or quantile scores zero.
Median and unscaled MAD of this snapshot's weighted centroid distribution. Every deviation uses the same median. Centroid compression loses within-centroid spread, so both estimates approximate the original observations. At an exact half-weight boundary the two adjacent values are averaged.
Convert centroids to a sparse histogram with bins centered on each centroid.