DashAI.back.explainability.PartialDependence

class PartialDependence(model: BaseModel, lower_percentile: float = 0.05, upper_percentile: float = 0.95, grid_resolution: int = 100)[source]

PartialDependence is a model-agnostic explainability method that shows the average prediction of a machine learning model for each possible value of a feature.

__init__(model: BaseModel, lower_percentile: float = 0.05, upper_percentile: float = 0.95, grid_resolution: int = 100)[source]

Initialize a new instance of a PartialDependence explainer.

Parameters:

  • model (BaseModel) – Model to be explained.

  • lower_percentile (int) – The lower and upper percentile used to limit the feature values. Defaults to 0.05

  • upper_percentile (int) – The lower and upper percentile used to limit the feature values. Default to 0.95

  • grid_resolution (int) – The number of equidistant points to split the range of the target feature. Defaults to 100.

Methods

__init__(model[, lower_percentile, ...])

Initialize a new instance of a PartialDependence explainer.

explain(dataset)

Method to generate the explanation

get_schema()

Generates the component related Json Schema.

plot(explanation)

Method to create the explanation plot.

validate_and_transform(raw_data)

It takes the data given by the user to initialize the model and returns it with all the objects that the model needs to work.

Attributes

COMPATIBLE_COMPONENTS

TYPE