interpretable-ml-book VS shap

If you're a student, I'd recommend this book :https://christophm.github.io/interpretable-ml-book/

Pretty much everyone shows SHAP plots now. Definitely the way to go. Check out the Christoph Molnar book. https://christophm.github.io/interpretable-ml-book/

Yes, there are many techniques beyond the two you listed. I suggest doing a survey of techniques (hint: explainable AI or XAI), starting with the following book: Interpretable Machine Learning.

Ah, alright. It sounds like you're looking for interpretability so I'd suggest this amazing overview of it by Christoph Molnar. If you choose the right models, or the right way of interpreting those, it can help a ton in communicating not only your results, but also what you did to obtain them.

Not necessarily; decision trees, Naive Bayes, etc., are interpretable. I'd refer to Molnar--specifically his Interpretable Machine Learning text--if you are interested in that subject.

Consulting something like Interpretable Machine Learning or the documentation of a package like the vip package would also be a really, really good place to start.

Just read a book called Interpretable Machine Learning which focuses on analyzing ML models and determine which inputs has more impact in the result.

Calling it a book on SHAP undersells it. https://christophm.github.io/interpretable-ml-book/

something like GitHub - shap/shap: A game theoretic approach to explain the output of any machine learning model.?

A less than 100 lines of code implementation of KernelSHAP because I had a hard time understanding shap's code.

We use tools like SHAP to explain what the model is doing to stakeholders.

https://github.com/slundberg/shap this or https://github.com/marcotcr/lime would be relevant to you, especially if you want to look at explaining a single prediction.

See this closed topic for more detail: https://github.com/slundberg/shap/issues/29

Dr. Molnar recently had a semi-viral post on LinkedIn and on Twitter, where he essentially highlights the booming popularity [and power] of using SHAP for explainable AI (which I agree with), but that it also comes with problems; i.e., the open source implementation has thousands of pull requests, bugs, and issues and yet there is no permanent or significant funding to go in and fix them.

Option 4) create SHAP values https://github.com/slundberg/shap to better understand what the RF did.

txtai pipelines are wrappers around Hugging Face pipelines with logic to easily integrate with txtai's workflow framework. Given that, we can use the SHAP library to explain predictions.