shap
shapash
Our great sponsors
shap | shapash | |
---|---|---|
38 | 8 | |
21,389 | 2,629 | |
1.6% | 2.4% | |
9.4 | 8.6 | |
6 days ago | 6 days ago | |
Jupyter Notebook | Jupyter Notebook | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
shap
-
[D] Convert a ML model into a rule based system
something like GitHub - shap/shap: A game theoretic approach to explain the output of any machine learning model.?
-
[P] tinyshap: A minimal implementation of the SHAP algorithm
A less than 100 lines of code implementation of KernelSHAP because I had a hard time understanding shap's code.
-
Model interpretation with many features
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.
-
Random Forest Estimation Question
Option 4) create SHAP values https://github.com/slundberg/shap to better understand what the RF did.
-
What Are the Most Important Statistical Ideas of the Past 50 Years?
Seconding Chris Molnar's excellent writeup. I also find the readme & example notebooks in Scott Lundberg's github repo to be a great way to get started. There are also references there for the original papers, which are surprisingly readable, imo. https://github.com/slundberg/shap
-
[Q] What's the community's opinion of "interpretable ML/AI"?
I've become a zealot about parametric stats, specifically from the Bayesian paradigm. Something about studying the core business problem, choosing the best distribution(s), and making inferences has been really rewarding for me. But increasingly, I'm seeing tools like SHAP, which allegedly enable users of black-box ML models to intuit what/how their models "think". (SHAP is just one example.)
- Looking into the "black box" of a neural network
-
Comparing Strings (Street Names) With Machine Learning
As more features are added to a model, the longer it will take to make a prediction. To help you find a suitable set of features, I have two suggestions, (1) recursive feature selection and (2) SHAP values. Using either of these methods can save you time as you find the right set of features for your model.
- [D] Has anyone ever used the SHAP and LIME models in machine learning?
-
How an ML algorithm shows which aspect of a comparison contributes more to the result?
If you are using more of a black-box method, two of the more common ways to determine how your dependent variables interact with your dependent variables are Shapley values and LIME. Shapley values are related to game theory from economics. Basically it attempts to answer how much each feature contributes to the predicted value compared to the average by looking at the average marginal contribution of a specific feature value across all potential combinations of feature values. A good python implementation and more details can be found here.
shapash
- [D] DL Practitioners, Do You Use Layer Visualization Tools s.a GradCam in Your Process?
-
This A.I.-generated artwork, Théâtre D'opéra Spatial, won first place at an art competition, and the art community isn't happy about it
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.
-
Hacker News top posts: Jun 14, 2022
Shapash – Python library to make machine learning interpretable\ (4 comments)
-
State of the Art data drift libraries on Python?
Try out eurybia, from the author of shapash which is a brilliant library as well.
- [D] Has anyone ever used the SHAP and LIME models in machine learning?
What are some alternatives?
Transformer-Explainability - [CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
captum - Model interpretability and understanding for PyTorch
lime - Lime: Explaining the predictions of any machine learning classifier
interpret - Fit interpretable models. Explain blackbox machine learning.
LIME - Tutorial notebooks on explainable Machine Learning with LIME (Original work: https://arxiv.org/abs/1602.04938)
awesome-production-machine-learning - A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
anchor - Code for "High-Precision Model-Agnostic Explanations" paper
articulated-animation - Code for Motion Representations for Articulated Animation paper
lucid - A collection of infrastructure and tools for research in neural network interpretability.
GlassCode - This plugin allows you to make JetBrains IDEs to be fully transparent while keeping the code sharp and bright.
trulens - Evaluation and Tracking for LLM Experiments