quality_metrics

Define the available quality metrics to validate the explanation quality.

Classes:

Name	Description
QualityMetrics	Quality metrics object.
Sensitivity	Sensitivity object.
Infidelity	Infidelity object.

QualityMetrics

Quality metrics object.

Parameters:

Name	Type	Description	Default
name	str		required
number_of_perturbations	None | Unset | int		<xpdeep_api_client.types.Unset object at 0x7f35293a8380>

Attributes:

Name	Type	Description
additional_properties	dict[str, Any]	dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list. For example: dict(one=1, two=2)

Methods:

Name	Description
to_model	Convert to ExplanationConfigQualityMetric instance.

to_model() -> ExplanationConfigQualityMetric

Convert to ExplanationConfigQualityMetric instance.

Source code in src/xpdeep/explain/quality_metrics.py

@abstractmethod
def to_model(self) -> ExplanationConfigQualityMetric:
    """Convert to ExplanationConfigQualityMetric instance."""
    raise NotImplementedError

Sensitivity

Sensitivity object.

Parameters:

Name	Type	Description	Default
name	str	The metric name.	'sensitivity'
number_of_perturbations	int	The number of perturbations. The higher, the more accurate, byt computationally expensive.	10

Attributes:

Name	Type	Description
additional_properties	dict[str, Any]	dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list. For example: dict(one=1, two=2)

Methods:

Name	Description
to_model	Convert to ExplanationConfigQualityMetric instance.

name: str = 'sensitivity'

number_of_perturbations: int = 10

to_model() -> ExplanationConfigQualityMetric

Convert to ExplanationConfigQualityMetric instance.

Source code in src/xpdeep/explain/quality_metrics.py

def to_model(self) -> ExplanationConfigQualityMetric:
    """Convert to ExplanationConfigQualityMetric instance."""
    return ExplanationConfigQualityMetric(
        name=self.name,
        number_of_perturbations=self.number_of_perturbations,
    )

Infidelity

Infidelity object.

Parameters:

Name	Type	Description	Default
name	str	The metric name, default infidelity.	'infidelity'
number_of_perturbations	int	The number of perturbations. The higher, the more accurate, byt computationally expensive.	10

Attributes:

Name	Type	Description
additional_properties	dict[str, Any]	dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list. For example: dict(one=1, two=2)

Methods:

Name	Description
to_model	Convert to ExplanationConfigQualityMetric instance.

name: str = 'infidelity'

number_of_perturbations: int = 10

to_model() -> ExplanationConfigQualityMetric

Convert to ExplanationConfigQualityMetric instance.

Source code in src/xpdeep/explain/quality_metrics.py

def to_model(self) -> ExplanationConfigQualityMetric:
    """Convert to ExplanationConfigQualityMetric instance."""
    return ExplanationConfigQualityMetric(
        name=self.name,
        number_of_perturbations=self.number_of_perturbations,
    )