MLwrap (version 0.3.0)

plot_integrated_gradients: Plotting Integrated Gradients Plots

Description

The plot_integrated_gradients() function implements interpretability visualizations of integrated gradient attributions measuring feature importance through accumulated gradients along the interpolation path from baseline (zero vector) to observed input. Provides four visualization modalities: mean absolute attributions (bar plots), directional effects showing positive and negative contribution patterns (directional plots), distributional properties of attributions across instances (box plots), and individual-level attribution contributions (swarm plots).

Usage

plot_integrated_gradients(analysis_object, show_table = FALSE)

Value

analysis_object

Arguments

analysis_object

Fitted analysis_object with 'sensitivity_analysis(methods = "Integrated Gradients")'.

show_table

Boolean. Whether to print Integrated Gradients summarized results table.

See Also

sensitivity_analysis

Examples

# Note: For obtaining the Integrated Gradients plot the user needs to
# complete till sensitivity_analysis( ) function of the MLwrap pipeline
# using the Integrated Gradients method.
# See the full pipeline example under sensitivity_analysis()
# (Requires sensitivity_analysis(methods = "Integrated Gradients"))
# Final call signature:
# plot_integrated_gradients(wrap_object)