Awesome GitHub RepositoriesFeature Interaction Visualizations

SHAP is a machine learning explainer that uses a game-theoretic framework to estimate the contribution of each feature to a model prediction. It provides a set of tools for quantifying how individual input features push a specific output away from a baseline value. The project includes specialized explainers for different architectures, including high-speed implementations for decision trees and ensemble models, linearization algorithms for deep learning networks, and covariance integration for linear models. It also features a model-agnostic interpretability tool that uses a kernel method to

This project is an agnostic model interpretability framework and explainability tool designed to provide local interpretable explanations for individual predictions. It functions as a local surrogate model that approximates the behavior of any machine learning classifier or regression model to identify the most influential features for a specific instance. The framework is designed to be model-agnostic, meaning it can explain predictions across tabular, text, and image data regardless of the underlying architecture. It employs local linear approximations and feature importance visualization t

This project is a collection of supervised and unsupervised machine learning algorithms implemented from scratch using Python. It serves as an educational resource for studying model training, parameter optimization, and the implementation of core predictive models. The library provides a variety of supervised learning tools, including linear and logistic regression, decision trees, and support vector machines. It also features unsupervised learning capabilities for discovering patterns in unlabeled datasets through clustering algorithms. Broad capability areas include ensemble learning thro

Interpret is an interpretable machine learning library and glassbox model framework. It provides toolkits for training inherently transparent models and applying post-hoc explanation techniques to make machine learning predictions human-understandable. The framework distinguishes itself by integrating differential privacy into the training of interpretable models to prevent sensitive data from leaking through explanations. It also features a visualization tool for rendering interactive decision paths and model behavior. The library covers model explainability through feature importance calcu

Dieses Projekt ist eine umfassende Bildungsressource und ein technisches Handbuch, das sich auf interpretierbares Machine Learning und erklärbare KI konzentriert. Es dient als Lehrbuch und Referenz für die Implementierung von Techniken, die komplexe Machine-Learning-Modelle für Menschen transparent und verständlich machen. Die Ressource bietet Anleitungen sowohl zum Aufbau inhärent transparenter Modelle, wie Entscheidungsbäumen und dünnbesetzten linearen Modellen, als auch zur Anwendung von Post-hoc-Erklärungsmethoden auf Black-Box-Systeme. Sie beschreibt spezifische Methoden zur Quantifizierung der Merkmalswichtigkeit, zur Generierung von Begründungen für individuelle Vorhersagen und zur Verwendung von Surrogat-Modellen zur Approximation komplexer Entscheidungsprozesse. Der Inhalt deckt ein breites Spektrum analytischer Funktionen ab, einschließlich der Analyse des globalen und lokalen Merkmalseinflusses, der Interpretierbarkeit von Computer Vision und der Verwendung spieltheoretischer Beiträge wie Shapley-Werten. Er befasst sich zudem mit der Modellevaluierung durch Interpretierbarkeitsbewertungen, Debugging-Workflows zur Identifizierung von Modell-Shortcuts und dem Design transparenter Algorithmusstrukturen. Das Projekt ist als Sammlung von Jupyter Notebooks implementiert.

Lit is a machine learning interpretability framework and model debugging tool designed to analyze model behavior and performance. It serves as an interpretability dashboard for large language models and a general performance analyzer for text, image, and tabular datasets. The project distinguishes itself through a comprehensive suite of interpretability tools, including salience map generation for feature attribution, the creation of synthetic and counterfactual examples to test robustness, and the projection of high-dimensional embeddings into visual spaces via UMAP or PCA. It further enable