Pyreal pipeline
Understanding the Pyreal process
To generate interpretable explanationl, Pyreal follows a specific transformation pipeline:
Data is transformed from the original feature space to the algorithm feature space
x_orig →
algorithm_transformers.transform()
→ x_algorithm
Data in the algorithm feature space is fed into the explanation algorithm, which results in an explanation in the algorithm feature space. The explanation algorithm may additionally transform data to the model-ready feature space to make predictions
x_algorithm →
Explainer.produce()
→ explanation_algorithmx_algorithm →
model_transformers.transform()
→ x_model
The explanation is transformed to the original feature space by undoing the algorithm transforms
explanation_algorithm →
algorithm_transformers.inverse_transform_explanation()
→ explanation_orig
The explanation is transformed to the interpretable feature space by running additional explanation transforms
explanation_orig →
interpret_transformers.transform_explanation()
→ explanation_interpret
For local explanations, the original data is transformed to the interpretable feature space
x_orig →
interpret_transformers.transform()
→ x_interpret
Last updated