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.

Parameters:

Name	Type	Description	Default
variogram	Variogram	Variogram of the normal scores, with a sill near 1.	required
search	Search or sequence of Search	A sequence is searched in passes, each filling the targets the previous left unestimated.	required
tails	tuple of float	Lower and upper bounds of the back-transform, widened to cover the data; the data minimum and maximum by default.	required

cross_validate method descriptor

cross_validate(*, folds=None)

Re-estimates each sample's distribution from the others, through the same search passes, with the transform of all samples.

Parameters:

Name	Type	Description	Default
folds	int	Leave-one-out when None; otherwise k-fold, each sample estimated without the samples of its fold. Samples fitted with holes keep their holes whole: the j-th of the sorted hole ids goes to fold j % folds, an untagged sample i to fold i % folds.	None

Returns:

Type	Description
IndicatorCrossValidation	Without thresholds.

fit method descriptor

fit(
    coords,
    values,
    *,
    weights=None,
    holes=None,
    despike=False,
)

Stores the samples. Samples sharing a location keep the first one, with a warning naming their holes.

Parameters:

Name	Type	Description	Default
coords	(array_like, PointSet or BlockModel)		required
values	array_like or str	A value per sample, or the column of coords holding them; so for weights and holes.	required
weights	array_like or str	Declustering weights for the normal-score transform.	None
holes	array_like or str	Drill-hole ids or names, for max_per_hole.	None
despike	bool	Break ties in the values first, as despike does with its defaults, so tied samples get distinct scores; tied samples share their mean score otherwise.	False

from_parquet staticmethod

from_parquet(path)

Reads to_parquet output; raises InvalidInput on another class's file or a newer format.

predict method descriptor

predict(
    targets,
    *,
    cutoffs=None,
    quantiles=Ellipsis,
    discretization=None,
    diagnostics=False,
)

Conditional distribution at each target.

Parameters:

Name	Type	Description	Default
targets	(array_like, PointSet or BlockModel)		required
cutoffs	sequence of float	For probability_above and mean_above.	None
quantiles	sequence of float	Probabilities in [0, 1], for quantile_values.	Ellipsis
discretization	tuple of int	Points per axis of each block of a BlockModel targets: the distributions at the points are averaged, giving the distribution of the point values within the block rather than at its centroid.	None
diagnostics	bool	Fill IndicatorSummary.diagnostics.	False

Returns:

Type	Description
IndicatorSummary	No thresholds; correction is 0. NaN where the search found too few samples.

to_parquet method descriptor

to_parquet(path)

Writes samples and weights as Parquet columns and parameters as JSON in the file metadata; from_parquet reads it back.

used in

• multigaussian kriging