Reverse Dependencies of shap

The following projects have a declared dependency on shap:

• Accuinsight — Model life cycle and monitoring library in Accuinsight+
• acv-dev — ACV is a library that provides robust and accurate explanations for machine learning models or data
• acv-exp — ACV is a library that provides robust and accurate explanations for machine learning models or data
• adhs — Adaptive Hierarchical Shrinkage
• aggmap — Jigsaw-like AggMap: A Robust and Explainable Omics Deep Learning Tool
• aiverify-shap-toolbox — AI Verify SHAP Toolbox provides SHAP (SHapley Additive exPlanations) methods to explain the output of machine learning models.
• al360-tai-test-utils — Common basic test utilities used across various RAI tools
• alibi — Algorithms for monitoring and explaining machine learning models
• alphaml — Build a CLETE Binary Classification Model
• AMLBID — Transparent and Auto-explainable AutoML
• AMLpp — Wrapper for ml library
• Amplo — Fully automated end to end machine learning pipeline
• anai-opensource — Automated ML
• anilv-interpret-text — Generates pickle for Encoder
• antakia-core — Core modules for AntakIA
• aprofs — "Package aprofs serves the purpose of streaming the feature selection using aproximate preditions"
• arfs — All Relevant Feature Selection and Maximal Relevant minimal redundancy FS
• arthurai — Arthur Python SDK
• atom-ml — A Python package for fast exploration of machine learning pipelines
• auto-shap — Calculate SHAP values in parallel and automatically detect what explainer to use
• autobmt — a modeling tool that automatically builds scorecards and tree models.
• autogluon.eda — AutoML for Image, Text, and Tabular Data
• autoprognosis — A system for automating the design of predictive modeling pipelines tailored for clinical prognosis.
• autoqtl — Automated Quantitative Trait Locus Analysis Tool
• autorad — Radiomics-related modules for extraction and experimenting
• autotreemodel — auto build a tree model
• autoviml — Automatically Build Variant Interpretable ML models fast - now with CatBoost!
• avicenna — AVICENNA: Semantic Debugging
• bacGWAStatLearn — A machine learning approach for conducting genome wide association studies (GWAS) on bacteria
• bad-phylo — Tool for the estimation of the difficulty of phylogenetic placements
• baseline-optimal — no summary
• Beat-ML1 — This package contains several methods for calculating Conditional Average Treatment Effects
• BEAT-TEST — This package contains several methods for calculating Conditional Average Treatment Effects
• BEATAALU — This package contains several methods for calculating Conditional Average Treatment Effects
• bezzanlabs.treemachine — An AutoML companion to fit tree models easily
• binn — A package to generate and interpret biologically informed neural networks.
• Blauwal3-Explain — 蓝鲸数据挖掘软件包的解释附加组件。
• bluecast — A lightweight and fast automl framework
• BorutaShap — A feature selection algorithm.
• bugbug — ML tools for Mozilla projects
• carom-sblab — An awesome package that does something
• catboost-extensions — Extensions for catboost models
• causalml — Python Package for Uplift Modeling and Causal Inference with Machine Learning Algorithms
• causalnlp — CausalNLP: A Practical Toolkit for Causal Inference with Text
• cefeste — Feature Selection and Elimination
• changtianml — no summary
• cherrypick — Some tools to help the process of feature selection
• china — description
• ciclops — Pipeline for building clinical outcome prediction models on training dataset and transfer learning on validation datasets.
• CIMLA — Counterfactual Inference by Machine Learning and Attribution Models
• classifier-toolkit — no summary
• climaticai — climaticai is a library that builds, optimizes, and evaluates machine learning pipelines
• clust-learn — A Python package for explainable cluster analysis
• cluster-shapley — Explaining dimensionality reduction using SHAP values
• clusterxplain — Provide feature relevance scores fo clustering.
• coipee — Demo of a Caipi-like system for explanatory interactive learning.
• combinatorial-gwas — A package for the final project of MIT's 6.874 class Deep Learning in Life Science
• contextual-ai — Contextual AI
• corr-shap — This package is an extension of the KernelExplainer of shap package that explains the output of any machine learning model, taking into account dependencies between features.
• cotkg-network-intrusion-detection — A network intrusion detection system using Chain of Thought, knowledge graphs and GraphSAGE
• credoai-lens — Lens: comprehensive assessment framework for AI systems
• crosspredict — package for easy crossvalidation
• csv2shap — 输入csv文件以及二分类的label名称，输出shap value图
• CTApy — Python package for the Conditional Topic Allocation (CTA)
• cv19index — COVID-19 Vulnerability Index
• cyc-pep-perm — Python package to predict membrane permeability of cyclic peptides.
• cytopy — Data centric algorithm agnostic cytometry analysis framework
• d3m-common-primitives — D3M common primitives
• da-viz — A package for visualizing data and machine learning model performance
• darts — A python library for easy manipulation and forecasting of time series.
• datto — Data Tools (Dat To)
• datupapi — Utility library to support Datup AI MLOps processes
• decima2 — Evaluation Toolkit for Machine Learning Models
• deep-xf — DEEPXF - An open-source, low-code explainable forecasting and nowcasting library with state-of-the-art deep neural networks and Dynamic Factor Model. Now available with additional addons like Denoising TS signals with ensembling of filters, TS signal similarity test with Siamese Neural Networks
• deepmol — DeepMol: a python-based machine and deep learning framework for drug discovery
• devcellpy — devCellPy -- hierarchical multilayered classification of cells based on scRNA-seq
• dianna — Deep Insight And Neural Network Analysis
• diff-predictor — diff_predictor: a prediciton package for multiple particle tracking data
• distil-primitives — Distil primitives as a single library
• dive-into-graphs — DIG: Dive into Graphs is a turnkey library for graph deep learning research.
• Djaizz — Artificial Intelligence (AI) in Django Applications
• dnattend — AutoML classifier for predicting patient non-attendance (DNA)
• dorkylever-lama-phenotype-detection — Phenotype detection pipeline for finding abnormalities in mouse embryos
• dpks — Data processing package for the analysis of omics data
• drexml — (DRExM³L) Drug REpurposing using and eXplainable Machine Learning and Mechanistic Models of signal transduction"
• drift-shield — A package to monitor and track data drift for ML models
• ds-core-sanpier — A package to automize some of the steps before modeling and in the modeling stage
• dsConteXAI — Contextualizing model's decisions with natural language explanations.
• e2eml — An end-to-end solution for automl
• eBoruta — Extended Boruta -- a flexible transparent sklearn-compatible python Boruta implementation
• econml — This package contains several methods for calculating Conditional Average Treatment Effects
• effector — A Python library for global and regional effects
• emodel-generalisation — Generalisation of neuronal electrical models with MCMC
• emxps — Miscellanous Explanation Methods
• 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
• exdpn — Tool to mine and evaluate explainable data Petri nets using different classification techniques.
• EXGEP — A framework for predicting genotype-by-environment interactions using ensembles of explainable machine-learning models
• exlib — Toolkit for explainability by BrachioLab
• Explain-LISA-CNN-Research — Unified Explanation Provider For CNNs