SHAP (SHapley Additive exPlanations) is a unified approach to explain the output of any machine learning model. SHAP connects game theory with local explanations, uniting several previous methods and representing the only possible consistent and locally accurate additive feature attribution method based on expectations (see the SHAP NIPS paper for details).
Questions tagged [shap]
453 questions
-2
votes
0 answers
MemoryError when computing SHAP values with large background dataset
I'm trying to compute SHAP values for my model using a large background dataset, but I'm running into memory issues. Here's the error I'm encountering:
Using 32663 background data samples could cause slower run times. Consider using…
MelinA
- 1
- 8
-2
votes
1 answer
how to use SHAP library for text classification?
i have text data and pip line model . i want to using shap library to Visualize the impact on all the output classes
i got this error :
TypeError: The passed model is not callable and cannot be analyzed directly with the given masker! Model:…
MelinA
- 1
- 8
-2
votes
1 answer
Get the variables list from shapely library
I'm using shap library to get the variables importance the issue I'm having is that I only find plots options but I need to get a list of the variables importance in order.
Luis Ramon Ramirez Rodriguez
- 9,591
- 27
- 102
- 181