lofo-importance
Feature evaluator
A tool to evaluate feature importance by iteratively removing each feature and evaluating model performance on validation sets.
Leave One Feature Out Importance
817 stars
13 watching
85 forks
Language: Python
last commit: 10 months ago
Linked from 3 awesome lists
data-scienceexplainable-aifeature-importancefeature-selectionmachine-learning
jphall663/awesome-machine-learning-interpretability
lopusz/awesome-interpretable-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
 giuseppec/featureimportance | A tool to assess feature importance in machine learning models | 33 |
 iancovert/sage | A Python package for calculating global feature importance using Shapley values in machine learning models | 253 |
 allenai/olmo-eval | An evaluation framework for large language models. | 310 |
 modeloriented/ingredients | Provides tools to assess and visualize the importance and effects of features in machine learning models | 37 |
 koalaverse/vip | A package that provides a consistent interface for computing feature importance in machine learning models from various R packages. | 186 |
 kundajelab/deeplift | A Python library implementing methods for visualizing and interpreting the importance of features in deep neural networks | 826 |
 yeolab/anchor | An algorithm to identify unimodal, bimodal, and multimodal features in data | 27 |
 chenllliang/mmevalpro | A benchmarking framework for evaluating Large Multimodal Models by providing rigorous metrics and an efficient evaluation pipeline. | 22 |
 h2oai/h2o-llm-eval | An evaluation framework for large language models with Elo rating system and A/B testing capabilities | 50 |
 ethicalml/xai | An eXplainability toolbox for machine learning that enables data analysis and model evaluation to mitigate biases and improve performance | 1,125 |
 referefref/aiocrioc | An automated tool that extracts and analyzes indicators of compromise from text data using natural language processing and OCR techniques. | 31 |
 freedomintelligence/mllm-bench | Evaluates and compares the performance of multimodal large language models on various tasks | 55 |
 huggingface/lighteval | A toolkit for evaluating Large Language Models across multiple backends | 804 |
 openai/simple-evals | A library for evaluating language models using standardized prompts and benchmarking tests. | 1,939 |
 koraykv/fex | A Lua-based library for feature extraction in computer vision applications using the SIFT algorithm | 10 |