Reverse Dependencies of lime

The following projects have a declared dependency on lime:

• aif360 — IBM AI Fairness 360
• aif360-fork2 — IBM AI Fairness 360
• alphaml — Build a CLETE Binary Classification Model
• antakia-core — Core modules for AntakIA
• argueview — ArgueView is a tool for generating text-based presentations for machine-learning predictions and feature-importance based explanation tools. The tool makes use of Toulmin's model of argumentation for structuring the text-based explanations.
• arthurai — Arthur Python SDK
• aucmedi — AUCMEDI - a framework for Automated Classification of Medical Images
• AuDoLab — With AuDoLab you can do LDA on highly imbalanced datasets.
• azureml-contrib-explain-model — no summary
• azureml-contrib-interpret — ML contrib interpret package contains experimental functionality to interpret ML models
• bem — Random forest for exoplanets
• calibrated-explanations — Extract calibrated explanations from machine learning models.
• carla-recourse — A library for counterfactual recourse
• cdt-test — This is a cdt test to assist doctor
• classification-text-email — compiled packages
• classmail — A simple framework for automatise mail classification task
• contextual-ai — Contextual AI
• d3m-interface — Library to use D3M AutoML Systems
• datto — Data Tools (Dat To)
• dianna — Deep Insight And Neural Network Analysis
• Djaizz — Artificial Intelligence (AI) in Django Applications
• dynamask — Dynamask - Explaining Time Series Predictions with Dynamic Masks
• easul — Embeddable AI and State-based Understandable Logic toolkit
• email-txt-classification — compiled packages
• emxps — Miscellanous Explanation Methods
• ESMValTool — ESMValTool: A community diagnostic and performance metrics tool for routine evaluation of Earth system models in CMIP.
• EtaML — An automated machine learning platform with a focus on explainability
• evalml — an AutoML library that builds, optimizes, and evaluates machine learning pipelines using domain-specific objective functions
• exlib — Toolkit for explainability by BrachioLab
• Explain-LISA-CNN-Research — Unified Explanation Provider For CNNs
• Explain-LISA-CNN-test-4 — Unified Explanation Provider For CNNs
• explainableai — A comprehensive package for Explainable AI and model interpretation
• expybox — Jupyter notebook toolbox for model interpretability/explainability
• fasttreeshap — A fast implementation of TreeSHAP algorithm.
• ferret-xai — A python package for benchmarking interpretability approaches.
• flass — Train Keras Convolutional Neural Network for image classification
• genomap — Genomap converts tabular gene expression data into spatially meaningful images.
• giotto-time — Toolbox for Time Series analysis and integration with Machine Learning.
• h1st — Human-First AI (H1st)
• h1st-contrib — Human-First AI (H1st)
• holistic — no summary
• holisticai — no summary
• insolver — Insolver is low-code machine learning library, initially created for the insurance industry.
• interpret-community — Microsoft Interpret Extensions SDK for Python
• interpret-core — Fit interpretable machine learning models. Explain blackbox machine learning.
• InterpretME — An interpretable machine learning pipeline over knowledge graphs
• IREX — no summary
• keras-explain — Explanation toolbox for Keras models.
• LASExplanation — This package is a brief wrap-up toolkit built based on 2 explanation packages: LIME and SHAP. The package contains 2 explainers: LIMEBAG and SHAP. It takes data and fitted models as input and returns explanations about feature importance ranks and/or weights. (etc. what attributes matter most within the prediction model).
• lime-stability — A package to evaluate Lime stability
• LISA-CNN-ExplainerV1 — Unified Explanation Provider For CNNs
• LISA-CNN-ExplainerV2 — Unified Explanation Provider For CNNs
• LISA-CNN-ExplainerV3 — Unified Explanation Provider For CNNs
• LISA-CNN-ExplainerV4 — Unified Explanation Provider For CNNs
• LISA-CNN-ExplainerV5 — Unified Explanation Provider For CNNs
• llama-lime — Explainable AI with Large Language Models
• lohrasb — This versatile tool streamlines hyperparameter optimization in machine learning workflows.It supports a wide range of search methods, from GridSearchCV and RandomizedSearchCVto advanced techniques like OptunaSearchCV, Ray Tune, and Scikit-Learn Tune.Designed to enhance model performance and efficiency, it's suitable for tasks of any scale.
• mdml — Application of Deep learning on molecular dymanamics trajectories
• MlTrackTool — Documetation and Ml tracking tool using jupyter extensions
• modelxplain — A package for enhancing model interpretability for machine learning models.
• neurojit — A Python package for calculating the commit understandability features of Java projects.
• oban-classifier — OBAN Classifier: A Skorch-based flexible neural network for binary and multiclass classification
• omnixai — OmniXAI: An Explainable AI Toolbox
• omnixai-community — OmniXAI: An Explainable AI Toolbox
• pear-xai — PEAR: Post-hoc Explainer Agreement Regularization
• PiML — A low-code interpretable machine learning toolbox in Python.
• pm4pybpmn — Process Mining for Python - BPMN support
• pou-shap — A unified approach to explain the output of any machine learning model.
• prolothar-rule-mining — algorithms for prediction and rule mining on event sequences
• punditkit — PunditKit: A GUI for Scikit-Learn Models
• pyreal — Library for evaluating and deploying human readable machine learning explanations.
• pytolemaic — Package for ML model analysis
• recsystem — The package for Home Assistant Integration
• RIM-interpret — Interpretability metrics for machine learning models
• RobustifyToolkit — Robustify:
• SAInTool — SAInT: An Interactive Tool for Sensitivity Analysis In The Loop
• sdqcpy — SDQCPy is a comprehensive Python package designed for synthetic data management, quality control, and validation.
• shap — A unified approach to explain the output of any machine learning model.
• shap-legacy — A unified approach to explain the output of any machine learning model.
• shapash — Shapash is a Python library which aims to make machine learning interpretable and understandable by everyone.
• shaperone — Shaperone is a fork of the SHAP library, fixing open issues to improve usability.
• singa-easy — The SINGA-EASY
• skift — scikit-learn wrappers for Python fastText
• smace — Semi-Model-Agnostic Contextual Explainer library
• smartpyml — smartpyml: A Comprehensive Machine Learning Library
• sparx-lib — Sparx Implementation
• sphynxml — no summary
• symbolic-pursuit — Learning outside the black-box: at the pursuit of interpretable models
• trelawney — Generic Interpretability package
• trustML — Trust for Machine Learning
• volkanoban — A powerful stacking classifier framework that integrates advanced machine learning techniques, overfitting prevention, and explainability features such as LIME, SHAP, and model interpretation dashboards.
• wxyz-notebooks — notebook demos for experimental Jupyter widgets
• xai-compare — This repository aims to provide tools for comparing different explainability methods, enhancing the interpretation of machine learning models.
• XaI-Ensemble-API — A library for do the explaination of data using a new ensenble of XAI methods
• XaI-Ensemble-VOCs-API — A library for do the explaination of data using a new ensenble of XAI methods
• xai-explainer — A package for explaining deep learning models
• xai-feature-selection — Feature selection using XAI
• XAI-Library — An integrated library for explanation methods.
• xai-metrics — A package for analysis and evaluating metrics for Explainable AI (XAI)
• XeroML — A data management platform