DiCE
interpret
Our great sponsors
DiCE | interpret | |
---|---|---|
2 | 6 | |
1,270 | 5,988 | |
2.1% | 1.2% | |
8.2 | 9.7 | |
10 days ago | 6 days ago | |
Python | C++ | |
MIT License | MIT License |
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.
DiCE
-
[D] Have researchers given up on traditional machine learning methods?
- all domains requiring high interpretability absolutely ignore deep learning at all, and put all their research into traditional ML; see e.g. counterfactual examples, important interpretability methods in finance, or rule-based learning, important in medical or law applications
-
[R] The Shapley Value in Machine Learning
Counter-factual and recourse-based explanations are alternative approach to model explanations. I used to work in a large financial institution, and we were researching whether counter-factual explanation methods would lead to better reason codes for adverse action notices.
interpret
-
[D] Alternatives to the shap explainability package
Maybe InterpretML? It's developed and maintained by Microsoft Research and consolidates a lot of different explainability methods.
-
What Are the Most Important Statistical Ideas of the Past 50 Years?
You may also find Explainable Boosting Machines interesting: https://github.com/interpretml/interpret
They're a bit like a best of both worlds between linear models and random forests (generalized additive models fit with boosted decision trees)
Disclosure: I helped build this open source package
-
[N] Google confirms DeepMind Health Streams project has been killed off
Microsoft Explainable Boosting Machine (which is a Gaussian Additive Model and not a Gradient Boosted Trees ๐ model) is a step in that direction https://github.com/interpretml/interpret
-
[Discussion] XGBoost is the way.
Also I'd recommend everyone who works with xgboost to give EBM's a try! They perform comparably (except in the case of extreme interactions) but are actually interpretable! https://github.com/interpretml/interpret/ Beside that they since on runtime they're practically a lookup table they're very quick (at the cost of longer training time).
-
[D] Generalized Additive Modelsโฆ with trees?
Open source code by Microsoft: https://github.com/interpretml/interpret (called EBM in this implementation).
-
Machine Learning with Medical Data (unbalanced dataset)
If it's not an image, have a go at Microsoft's Explainable Boosting Maching) https://github.com/interpretml/interpret which is not a GBM but a GAM (Gradient Boosting Machine vs Gradient Additive Model). This will also give you explanation via SHAP or LIME values.
What are some alternatives?
OmniXAI - OmniXAI: A Library for eXplainable AI
shap - A game theoretic approach to explain the output of any machine learning model.
CARLA - CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
shapash - ๐ Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
AIX360 - Interpretability and explainability of data and machine learning models
alibi - Algorithms for explaining machine learning models
harakiri - Help applications kill themselves
imodels - Interpretable ML package ๐ for concise, transparent, and accurate predictive modeling (sklearn-compatible).
stranger - Chat anonymously with a randomly chosen stranger
medspacy - Library for clinical NLP with spaCy.
shapley - The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).
decision-tree-classifier - Decision Tree Classifier and Boosted Random Forest