trustyai.explainers.LimeResults

class trustyai.explainers.LimeResults(saliencyResults: SaliencyResults)

Wraps LIME results. This object is returned by the LimeExplainer, and provides a variety of methods to visualize and interact with the explanation.

__init__(saliencyResults: SaliencyResults)

Constructor method. This is called internally, and shouldn’t ever need to be used manually.

Methods

__init__(saliencyResults)	Constructor method.
as_dataframe()	Return the LIME result as a dataframe.
as_html()	Return the LIME results as Pandas Styler objects.
saliency_map()	Return a dictionary of found saliencies.

as_dataframe() → DataFrame

Return the LIME result as a dataframe.

Returns:

pandas.DataFrame

Dictionary of DataFrames, keyed by output name, containing the results of the LIME explanation. For each model output, the table will contain the following columns:

• Feature: The name of the feature

• Value: The value of the feature for this particular input.

• Saliency: The importance of this feature to the output.

• Confidence: The confidence of this explanation as returned by the explainer.

as_html() → Styler

Return the LIME results as Pandas Styler objects.

Returns:

Dict[str, pandas.Styler]

Dictionary of stylers keyed by output name. Each styler containing the results of the LIME explanation for that particular output, in the same schema as in as_dataframe(). This will:

• Color each Saliency based on how their magnitude.

saliency_map() → Dict[str, Saliency]

Return a dictionary of found saliencies.

Returns:

Dict[str, Saliency]

A dictionary of Saliency objects, keyed by output name.