estimation

name	summary	used in
Search	Neighborhood: radius is in meters along the major axis of the search ellipsoid (rotation azimuth, dip, rake and ratios semi/major, minor/major), or of the variogram's anisotropy when no ellipsoid is given.	72
calibrate_search	Scores candidate searches for a fitted estimator, one row per scenario, to compare side by side.	1
neighborhood_stats	Distances and value statistics of the k nearest samples around targets; n_holes counts distinct holes within radius; values and holes may name columns of coords.
HighGrade	High-grade restriction of a Search: samples above threshold are left out (mode="drop") or capped at threshold (mode="clamp") beyond radius of the target.	1
OrdinaryKriging	Kriging with an unknown, locally constant mean (weights sum to 1).	31
SimpleKriging	Kriging with a known global mean.	1
BlockKriging	Ordinary kriging of block averages; targets are block centers of size.	14
UniversalKriging	Kriging with a polynomial drift of degree in the coordinates.	2
ExternalDriftKriging	Kriging with a polynomial drift of degree (0 by default) plus one column per external drift variable, evaluated at the samples with fit and at the targets with predict.	2
FactorialKriging	Estimates only the selected components: structures by index, plus the nugget if asked.
DualKriging	Global dual kriging with a polynomial drift of degree (no search).
BayesianKriging	Kriging with a Gaussian prior on the drift coefficients.
Cokriging	Cokriging of variable from samples of several variables under a linear model of coregionalization; means switches to simple cokriging.	2
IndicatorKriging	Ordinary kriging of the indicator value <= threshold; estimates are probabilities.	1
MultipleIndicatorKriging	Multiple indicator kriging: P(value <= t) kriged at every threshold, corrected for order relations, completed within classes and in the tails, and summarized at each target.	4
CategoricalIndicatorKriging	Indicator kriging of categories: the probability of each category kriged from its indicator, clipped to [0, 1] and rescaled to sum 1 at each target.	4
MultigaussianKriging	Multigaussian kriging: the values take a normal-score transform, the scores are simple-kriged about 0, and the Gaussian distribution of the score at each target, with the kriged mean and variance, is back-transformed into data units.	1
InverseDistance	Inverse-distance weighting; a variogram supplies anisotropic distances.	13
NearestNeighbor		4
MovingAverage		2
MovingMedian
LocalLeastSquares	Local polynomial of degree fitted to the neighbors.