Version 0.3.0 #13
Merged
Version 0.3.0 #13
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Implementation of the method Integrated Gradients using the R6 class `IntegratedGradient` - Add documentation for the new class - Add tests for the new class
* Implementing the method DeepSHAP as the R6 class `DeepSHAp` * Add documentation for this new class * Add tests for this new class
* SHAP: Wraps the R package `fastshap` * LIME: Wraps the R package `lime` * Add test and documentation for both methods
* Add argument `output_label`: In addition to the output index with `output_idx`, the new argument `output_label` for the output label can now also be specified in order to calculate only certain output nodes * Small fix for the method `ExpectedGradient` * Update R documentation
…ethod and show them in the plots generated by plot()
…to the example body
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
convert()instead ofConverter$new()orrun_grad()instead ofGradient$new()plot()method now creates a small box within the plot with the prediction for the instance and the corresponding class. This info box also contains the sum of the relevances and, if available, the decomposition target of the method. Displaying the box can be toggled with theshow_predsargument.output_idx, the new argumentoutput_labelfor the output label can now also be specified in order to calculate or visualize only certain output nodes.boxplot()function for the interpretation methods has been renamedplot_global()due to the inappropriate name (especially for images). The old methodboxplot()can still be used, but throws a warning for imagedata and executes the method
plot_global()internally.