XAI Inverse Estimation

[annahedstroem]

Description

• Docstring fixes in all metrics and fixed typos across code base
• Added call_kwargs_che
• Replaced assertions for attributions with warnings
• InveseEstimation implementation
  • tests for pixel flipping and localisation
  • implementation next to base.py
  • plotting functionality
• fixes in metric base class, including adding the call params, making hem available as self.attributes
• added return_auc_per_sampel to RegionPerturbation

Minimum acceptance criteria

• Specify what is necessary for the PR to be merged with the main branch.
• @mentions of the person that is apt to review these changes e.g., @annahedstroem

[annahedstroem]

OK.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 74.81481% with 34 lines in your changes are missing coverage. Please review.

Project coverage is 90.58%. Comparing base (6857561) to head (24ec8fa).

Files	Patch %	Lines
quantus/metrics/inverse_estimation.py	79.26%	17 Missing ⚠️
quantus/helpers/model/pytorch_model.py	12.50%	7 Missing ⚠️
quantus/helpers/warn.py	69.56%	7 Missing ⚠️
quantus/evaluation.py	88.88%	1 Missing ⚠️
...uantus/metrics/faithfulness/region_perturbation.py	80.00%	1 Missing ⚠️
quantus/metrics/faithfulness/road.py	75.00%	1 Missing ⚠️

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #337      +/-   ##
==========================================
- Coverage   91.15%   90.58%   -0.58%     
==========================================
  Files          66       67       +1     
  Lines        3925     4047     +122     
==========================================
+ Hits         3578     3666      +88     
- Misses        347      381      +34     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[annahedstroem]

first round of review ok

[annahedstroem]

another review, looks good.