capping_report builtin

capping_report(
    values,
    caps,
    *,
    domains=None,
    domain_column=None,
    weights=None,
    data=None,
)

Weighted statistics per domain before and after capping, and the metal removed.

Parameters:

Name	Type	Description	Default
values	array_like or str	Values, or their column in data; NaN is skipped.	required
caps	dict	Cap per domain; domains left out are not capped.	required
domains	array_like	Domain of each value, int or str.	None
domain_column	str	Column of data holding the domains; give it or domains.	None
weights	array_like or str	Declustering weights; default the volumes of a BlockModel data, else 1.	None
data	(PointSet, BlockModel, Table or dict)	Where column names are looked up.	None

Returns:

Type	Description
Table	domain (sorted, then "all"), cap (null when not capped), n, n_capped (values above the cap), mean, std, cv, max, the same after capping as mean_capped, std_capped, cv_capped, max_capped, and metal_removed, the sum of (value - cap) × weight above the cap; 1 - mean_capped / mean is the fraction removed.

used in

• top cuts
• capping transform