interpret-community
interpret-community copied to clipboard
interpretml
Interpret Community extends Interpret repository with additional interpretability techniques and utility functions to handle real-world datasets and workflows.
Signed-off-by: tongy Issue to be fixed: https://github.com/interpretml/interpret-community/issues/379
The feature_dependence parameter to the LinearExplainer has been deprecated for several years now in shap and it has been causing confusing warnings in our notebooks. This PR removes the parameter...
While adding tests in explanation adapter to improve code coverage, I found an error when include_local=False which is fixed in this PR. The issue was that we called create_local in...
we only seem to have one test for passing function to blackbox explainers and it is a negative test: https://github.com/interpretml/interpret-community/blob/master/test/common_tabular_tests.py#L726 we should validate this scenario more
- This PR helps choose the best possible surrogate model by training multiple surrogate models based on accuracy or r2_score. - If the training of multiple surrogate model fails for...
- It seems that there is no validations for explainable model parameters. This may cause cryptic Exceptions from explainable model classes. So catching these errors earlier. - Also refactoring some...
I ran a forecasting experiment in Azure ML and it chose SeasonalAverage algorithm as the best model. In the explanation, only the target column ‘WeeklySales’ had importance and none of...
Hi, i have seen that there is a function to calculate the r2 score of the surrogate model. I was wondering, are there any other simple metrics implemented to measure...
Was following example https://github.com/interpretml/interpret-community/blob/master/notebooks/explain-regression-local.ipynb on my own data and xgboost object, but get error `('Expecting data to be a DMatrix object, got: ', )` at explainer.explain_global(x_test). Changed x_test to DMatrix...
Metadata
Owner
Metadata
Interpret Community extends Interpret repository with additional interpretability techniques and utility functions to handle real-world datasets and workflows.