shapley
sagemaker-explaining-credit-decisions
shapley | sagemaker-explaining-credit-decisions | |
---|---|---|
7 | 2 | |
210 | 94 | |
- | - | |
2.7 | 2.4 | |
10 months ago | 12 months ago | |
Python | Python | |
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.
shapley
-
AstraZeneca Researchers Explain the Concept and Applications of the Shapley Value in Machine Learning
Code for https://arxiv.org/abs/2202.05594 found: https://github.com/benedekrozemberczki/shapley
- Calculating and approximating the Shapley value in voting games
- Show HN: Pruning Machine Learning Models with the Shapley Value
- Show HN: Shapley: Explaining Machine Learning Ensembles
- Shapley - a Python library for solving weighted voting games.
- Show HN: Shapley – a Python library for scoring ML models in an ensemble
sagemaker-explaining-credit-decisions
-
Deploying a LightGBM classifier as a AWS Sagemaker endpoint?
Have looked at: https://sagemaker-examples.readthedocs.io/en/latest/advanced_functionality/scikit_bring_your_own/scikit_bring_your_own.html https://docs.aws.amazon.com/sagemaker/latest/dg/docker-containers-create.html https://sagemaker-immersionday.workshop.aws/lab3/option1.html The above don't specify LightGBM, but the concept of Bring Your Own Container/Algorithm is the same. I think this article might be more than what you need, buy it does reference LightGBM https://github.com/awslabs/sagemaker-explaining-credit-decisions And also this one https://github.com/aws-samples/amazon-sagemaker-script-mode/blob/master/lightgbm-byo/lightgbm-byo.ipynb
-
Ask the Experts: AWS Data Science and ML Experts - - Mar 9th @ 8AM ET / 1PM GMT!
Yes, SageMaker is an end to end service covering data labeling, data preparation, model training, model deployment, model monitoring, etc. This recent video will give you a grand hands-on tour of SageMaker: https://www.twitch.tv/aws/video/929163653. Training and deployment is based on Docker containers, either built-in (algorithms and open source frameworks) or your own. With respect to LightGBM, you can easily start from the built-in scikit-learn container, and add LightGBM to it. Here's a complete example: https://github.com/awslabs/sagemaker-explaining-credit-decisions.
What are some alternatives?
DALEX - moDel Agnostic Language for Exploration and eXplanation
autogluon - Fast and Accurate ML in 3 Lines of Code
interpret - Fit interpretable models. Explain blackbox machine learning.
DiCE - Generate Diverse Counterfactual Explanations for any machine learning model.
CARLA - CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
awesome-shapley-value - Reading list for "The Shapley Value in Machine Learning" (JCAI 2022)
MindsDB - The platform for customizing AI from enterprise data
AIX360 - Interpretability and explainability of data and machine learning models
amazon-sagemaker-script-mode - Amazon SageMaker examples for prebuilt framework mode containers, a.k.a. Script Mode, and more (BYO containers and models etc.)
csle - A research platform to develop automated security policies using quantitative methods, e.g., optimal control, computational game theory, reinforcement learning, optimization, evolutionary methods, and causal inference.