anchor icon indicating copy to clipboard operation
anchor copied to clipboard

Code for "High-Precision Model-Agnostic Explanations" paper

Results 25 anchor issues
Sort by recently updated
recently updated
newest added

How can we run `anchor_tabular.AnchorTabularExplainer` in batch incrementally for large set of training data? I need help to do adaptively learning after laoding ` anchor_tabular.AnchorTabularExplainer` learned from previous chunk of...

Still in the process of understanding the core algo but from the current understanding found it weird for the explainer to be returning empty `anchors`. Is that by design? Mentioned...

![image](https://user-images.githubusercontent.com/16265544/111620647-f6bfdf00-8821-11eb-8fc4-05b72c5e83b6.png) I clone the repository and run "Anchor on tabular data.ipynb" and occure this error comment this two line like: ![image](https://user-images.githubusercontent.com/16265544/111621513-0ab81080-8823-11eb-9a0c-4297e9af1ffd.png) then everything goes well.

Text、tabular data、image, I have no idea how to perturb different data format specifically, and seems there is no explicit mention in paper.

Hi, I noticed in this comment [here](https://github.com/marcotcr/anchor/issues/57#issuecomment-690758122) that Spacy support has been removed (though I could be interpreting that wrong). Does this mean it can be removed as a dependency?...

There seems to be a comment [here](https://github.com/marcotcr/anchor/blob/f1a7a9f1c863cec2d3bffa0820dfa9a9cfffcc46/anchor/anchor_tabular.py#L289) stating that something will no longer work. Is that still the case or is that an old comment? Also, in this function, why...

When running anchor I receive the following error explainer = anchor_tabular.AnchorTabularExplainer(possible_outcomes, feature_names, X2E, categorical_names) explainer.fit(X_train, y_train, X_test, y_test) Traceback (most recent call last): File "", line 1, in explainer =...

When installing anchor from pypi, scikit-learn 0.24 (current stable release) is installed as a dependency. However, this is incompatible, resulting in 'TypeError: ufunc 'isnan' not supported for the input types,...

Hi Marco, could you include some image examples as well?

I am using HELOC dataset which can be downloaded from https://community.fico.com/s/explainable-machine-learning-challenge?tabset-3158a=2. I am using an XGBoost model as classification function and trying to use Anchors as an explainability technique over...