-
Good evening from Brazil.
My name is Raphael, I´m undergraduate student from PUC-Rio and I´m trying to use SHAPLEY on a academic work but I´m having a problem when i try to load a dataset from goog…
-
We have implemented shap_values in catboost (http://catboost.yandex or https://github.com/catboost/catboost), it works really cool, thank you very much!
It'll be on pypi in tomorrow's release.
One…
-
The following notebook [tree_shap_solution.ipynb ](https://github.com/prakharrathi25/artificial-intelligence-for-trading/blob/master/part2_ai_algorithms_in_trading/quizzes_and_exercises/21_feature_imp…
-
Is it correct to use SHAP + a masker with a custom tokenizer to explain a fine-tuned BERT model?
My doubt is linked to the different tokenization, since BERT tokenizer does WordPiece tokenization (…
-
How is the shap values for multi output regression for Kernal Explainer is calculated? Are the individual outputs considered separately when calculating the shap values of the features? Or are all the…
-
### Problem Description
I have tried SHAP on my Vision Transformer Model, and it said that it does not recognize the following layers:
- nn.GELU
- nn.Identity
- nn.LayerNorm
Could you please a…
-
Hi @slundberg ,
First, I wanted to say many thanks for this amazing package.
I am using the LinearExplainer with a logistic regression for a binary classification. My problem is that I only have…
-
### Problem Description
First of all, thanks for the idea and implementartion!
We're adopting SHAP values in our model evaluations and find them very useful overall but struggle with the fact that…
-
**Describe the bug**
While working on the Blazepose model, we observed that the ttnn conv2d operation fails to produce the expected output shape for four different input configurations. Instead, the …
-
TODO: Add FeatureSelector choosing features by feature importance(Split, Gain, Shap) [*](https://www.kaggle.com/ogrellier/feature-selection-with-null-importances)