LIME VS shapash

I am very glad you liked it and thank you for your hint. In terms of citation, I never claimed the algorithm to be mine. But the implementation is 100% my work and the notebooks themselves are also only for educational purpose (university's course). On GitHub where the project's is hosted, I referenced the original author's work at the first place to ensure scientific integrity (https://github.com/longmakesstuff/LIME).

Basically, we desire to interpret how a black box model made its decision for a single sample. The code can be found at: https://github.com/longmakesstuff/LIME

There's work being done in that regard (like this python module), but as far as I know it's very clearly statistical guesstimates, and though it "works", the mathematical foundations are still somewhat shaky. There are heuristics in there we can't get rid of for now. But it's still better than nothing. Waaaaaay better than nothing.

Shapash – Python library to make machine learning interpretable\ (4 comments)

Try out eurybia, from the author of shapash which is a brilliant library as well.

With the new version of Shapash that is now available, you can document each model you release into production. Within a few lines of code, you can include in an HTML report all the information about your model (and its associated performance), the data it uses, its learning strategy, … this report is designed to be easily shared with a Data Protection Officer, an internal audit department, a risk control department, a compliance department, or anyone who wants to understand his work.