shap
awesome-production-machine-learning
Our great sponsors
shap | awesome-production-machine-learning | |
---|---|---|
38 | 9 | |
21,580 | 15,947 | |
1.8% | 2.1% | |
9.4 | 7.4 | |
7 days ago | 3 days ago | |
Jupyter Notebook | ||
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.
shap
- Shap v0.45.0
-
[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.
-
What’s after model adequacy?
We use tools like SHAP to explain what the model is doing to stakeholders.
- Feature importance with feature engineering?
-
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.
-
SHAP Value Interpretation
See this closed topic for more detail: https://github.com/slundberg/shap/issues/29
-
Christoph Molnar on SHAP Library
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.
-
Random Forest Estimation Question
Option 4) create SHAP values https://github.com/slundberg/shap to better understand what the RF did.
-
Model explainability
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.
awesome-production-machine-learning
-
Exploring Open-Source Alternatives to Landing AI for Robust MLOps
One trove of treasures is the awesome-production-machine-learning repository on GitHub. This curated list provides a multitude of frameworks, libraries, and software designed to facilitate various stages of the ML lifecycle.
-
[P] We are building a curated list of open source tooling for data-centric AI workflows, looking for contributions.
There is a cool, gigantic list for MLOps that I can recommend: https://github.com/EthicalML/awesome-production-machine-learning
-
How much of a full DS project pipeline can I do for free?
There are a lot of frameworks and specific tools out there that try to make production ML projects viable; from specific like Airflow (orchestrating jobs) and MLflow (experiment tracking) to more complex ones like Kubeflow. You can have a grasp here.
-
Sqldiff: SQLite Database Difference Utility
https://github.com/EthicalML/awesome-production-machine-lear...
- [D] What are the best resources to crack M L system design interviews?
-
I'm looking for a tool that let's you visualize the models architecture like this. Any idea what it is called?
https://github.com/EthicalML/awesome-production-machine-learning I think you will find most of the tools to visualize the model on this link.
- Awesome production machine learning - curated list of awesome open source libraries that will help you deploy, monitor, version, scale, and secure your production machine learning [free] [website] [@all]
-
Crucial differences in MLOps for deep learning
2/ https://github.com/EthicalML/awesome-production-machine-learning
What are some alternatives?
shapash - 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
awesome-jax - JAX - A curated list of resources https://github.com/google/jax
Transformer-Explainability - [CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
netron - Visualizer for neural network, deep learning and machine learning models
captum - Model interpretability and understanding for PyTorch
awesome-mlops - :sunglasses: A curated list of awesome MLOps tools
lime - Lime: Explaining the predictions of any machine learning classifier
awesome-ml-for-cybersecurity - :octocat: Machine Learning for Cyber Security
interpret - Fit interpretable models. Explain blackbox machine learning.
datascience - Curated list of Python resources for data science.
anchor - Code for "High-Precision Model-Agnostic Explanations" paper
awesome-ocr