WeightedSumFitter.build

WeightedSumFitter.build(X, y, coords=None)

Construct the PyMC graph without sampling anything.

Merges the effective prior set (defaults -> data-derived -> user) and calls build_model(). Idempotent by skipping when the graph already exists: a graph is built at most once per instance, so this is safe to call before every sampling verb.

Parameters:

• X (DataArray) – Input features as a labeled array, or mapping inputs for models that accept them.

• y (DataArray) – Target values as a labeled array, or mapping inputs for models that accept them.

• coords (dict[str, Any] | None) – Dictionary with coordinate names for named dimensions.

Return type:

None