There are 4 repositories under shapley topic.
The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).
Explaining the output of machine learning models with more accurately estimated Shapley values
Reading list for "The Shapley Value in Machine Learning" (JCAI 2022)
Fast approximate Shapley values in R
ACV is a python library that provides explanations for any machine learning model or data. It gives local rule-based explanations for any model or data and different Shapley Values for tree-based models.
Amazon SageMaker Solution for explaining credit decisions.
Break Down with interactions for local explanations (SHAP, BreakDown, iBreakDown)
streamlit-shap provides a wrapper to display SHAP plots in Streamlit.
A lightweight implementation of removal-based explanations for ML models.
For calculating Shapley values via linear regression.
Shapley Values with H2O AutoML Example (ML Interpretability)
Counterfactual SHAP: a framework for counterfactual feature importance
This repository contains an example of how to implement the shap library to interpret a machine learning model.
Counterfactual Shapley Additive Explanation: Experiments
Jupyter Notebook Templates for quick prototyping of machine learning solutions
In this repository you will fine explainability of machine learning models.
Predicting Demand in Primary Health Care Centers in Lebanon: Insight from Syrian Refugees Crisis
Save thousands of API calls. Custom model & dataset aiming at predicting a game difficulty score ("lobby avg kd") without calling players' games history stats and profiles.
This is an official repository for "2D-Shapley: A Framework for Fragmented Data Valuation" (ICML2023).
Analytical computation of rolling and expanding Shapley values for time-series data.
Exploratory data analysis, model development and model explainability for the heart disease web application. Stack: Databricks, Pyspark, MLFlow, AutoML, Shapley, Docker.
Using data within first 24 hours of intensive care to develop a machine learning model that could improve the current patient survival probability prediction system (apache_4a) and is more generalized to patients outside of the US
Examines fairness metrics for models including gender stereotyping versus group differences due to appropriate predictors. Also explores feature bias mitigation
Trained a classifier by using labeled data and oversampling and undersampling techniques to predict if a borrower will default on a loan. The model is intended to be used as a reference tool to help investors make informed decisions about lending to potential borrowers based on their ability to repay. The purpose is to lower risk & maximize profit.
FastAPI for gathering LocationIQ bounding box and PurpleAir Sensor Data then creating interpolated GeoJson using KNN-Regression
This repository contains the code for machine learning models designed to predict the outcomes of horse races, with SHAP (SHapley Additive exPlanations) interpretation incorporated for enhanced model interpretability.
Flask app that predicts the risk of heart disease based on a GBT ML model, and shows the confidence in the prediction as well as the factors behind the prediction (explainability).