shap.Explanation

class shap.Explanation(values: npt.NDArray[Any] | list[Any] | Explanation, base_values: npt.NDArray[Any] | list[Any] | float | None = None, data: npt.NDArray[Any] | pd.DataFrame | list[Any] | None = None, display_data: npt.NDArray[Any] | pd.DataFrame | None = None, instance_names: Sequence[str] | npt.NDArray[Any] | None = None, feature_names: Sequence[str] | npt.NDArray[Any] | Alias | None = None, output_names: Sequence[str] | npt.NDArray[Any] | str | Alias | None = None, output_indexes: npt.NDArray[Any] | None = None, lower_bounds: npt.NDArray[Any] | None = None, upper_bounds: npt.NDArray[Any] | None = None, error_std: npt.NDArray[Any] | None = None, main_effects: npt.NDArray[Any] | None = None, hierarchical_values: npt.NDArray[Any] | list[Any] | None = None, clustering: npt.NDArray[Any] | list[Any] | None = None, compute_time: float | None = None)

A sliceable set of parallel arrays representing a SHAP explanation.

Notes

The instance methods such as .max() return new Explanation objects with the operation applied.

The class methods such as Explanation.max return OpChain objects that represent a set of dot chained operations without actually running them.

__init__(values: npt.NDArray[Any] | list[Any] | Explanation, base_values: npt.NDArray[Any] | list[Any] | float | None = None, data: npt.NDArray[Any] | pd.DataFrame | list[Any] | None = None, display_data: npt.NDArray[Any] | pd.DataFrame | None = None, instance_names: Sequence[str] | npt.NDArray[Any] | None = None, feature_names: Sequence[str] | npt.NDArray[Any] | Alias | None = None, output_names: Sequence[str] | npt.NDArray[Any] | str | Alias | None = None, output_indexes: npt.NDArray[Any] | None = None, lower_bounds: npt.NDArray[Any] | None = None, upper_bounds: npt.NDArray[Any] | None = None, error_std: npt.NDArray[Any] | None = None, main_effects: npt.NDArray[Any] | None = None, hierarchical_values: npt.NDArray[Any] | list[Any] | None = None, clustering: npt.NDArray[Any] | list[Any] | None = None, compute_time: float | None = None) → None

Methods

__init__(values[, base_values, data, ...])
cohorts(cohorts)	Split this explanation into several cohorts.
hstack(other)	Stack two explanations column-wise.
percentile(q[, axis])

Attributes

abs
argsort
base_values	Pass-through from the underlying slicer object.
clustering	Pass-through from the underlying slicer object.
data	Pass-through from the underlying slicer object.
display_data	Pass-through from the underlying slicer object.
error_std	Pass-through from the underlying slicer object.
feature_names	Pass-through from the underlying slicer object.
flip
hclust
hierarchical_values	Pass-through from the underlying slicer object.
identity
instance_names	Pass-through from the underlying slicer object.
lower_bounds	Pass-through from the underlying slicer object.
main_effects	Pass-through from the underlying slicer object.
max
mean
min
output_indexes	Pass-through from the underlying slicer object.
output_names	Pass-through from the underlying slicer object.
sample
shape	Compute the shape over potentially complex data nesting.
sum
upper_bounds	Pass-through from the underlying slicer object.
values	Pass-through from the underlying slicer object.

property base_values

Pass-through from the underlying slicer object.

property clustering

Pass-through from the underlying slicer object.

cohorts(cohorts: int | list[int] | tuple[int] | ndarray) → Cohorts

Split this explanation into several cohorts.

Parameters:

cohortsint or array

If this is an integer then we auto build that many cohorts using a decision tree. If this is an array then we treat that as an array of cohort names/ids for each instance.

Returns:

Cohorts object

property data

Pass-through from the underlying slicer object.

property display_data

Pass-through from the underlying slicer object.

property error_std

Pass-through from the underlying slicer object.

property feature_names

Pass-through from the underlying slicer object.

property hierarchical_values

Pass-through from the underlying slicer object.

hstack(other: Explanation) → Explanation

Stack two explanations column-wise.

Parameters:

othershap.Explanation

The other Explanation object to stack with.

Returns:

expshap.Explanation

A new Explanation object representing the stacked explanations.

property instance_names

Pass-through from the underlying slicer object.

property lower_bounds

Pass-through from the underlying slicer object.

property main_effects

Pass-through from the underlying slicer object.

property output_indexes

Pass-through from the underlying slicer object.

property output_names

Pass-through from the underlying slicer object.

property shape: tuple[int, ...]

Compute the shape over potentially complex data nesting.

property upper_bounds

Pass-through from the underlying slicer object.

property values

Pass-through from the underlying slicer object.