Metadata-Version: 2.4
Name: evoreason
Version: 1.0.0
Summary: Hybrid Intelligent AutoML: Rule-Based + LLM-Guided Reasoning - 100% Automatic
Home-page: https://github.com/evoreason/evoreason
Author: EvoReason Contributors
Author-email: LLMFE Contributors <contributors@llmfe.dev>
License: MIT
Project-URL: Homepage, https://github.com/llmfe/llmfe-automl
Project-URL: Documentation, https://llmfe-automl.readthedocs.io
Project-URL: Bug Tracker, https://github.com/llmfe/llmfe-automl/issues
Project-URL: Source Code, https://github.com/llmfe/llmfe-automl
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: pandas>=1.3.0
Requires-Dist: numpy>=1.20.0
Requires-Dist: scikit-learn>=1.0.0
Provides-Extra: automl
Requires-Dist: autogluon[tabular]>=1.0.0; extra == "automl"
Requires-Dist: optuna>=3.0.0; extra == "automl"
Requires-Dist: featuretools>=1.0.0; extra == "automl"
Requires-Dist: shap>=0.40.0; extra == "automl"
Provides-Extra: providers
Requires-Dist: openai>=1.0.0; extra == "providers"
Requires-Dist: anthropic>=0.7.0; extra == "providers"
Requires-Dist: huggingface-hub>=0.16.0; extra == "providers"
Requires-Dist: google-generativeai>=0.3.0; extra == "providers"
Provides-Extra: data
Requires-Dist: imbalanced-learn>=0.9.0; extra == "data"
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
Requires-Dist: black>=22.0.0; extra == "dev"
Requires-Dist: flake8>=4.0.0; extra == "dev"
Requires-Dist: mypy>=0.960; extra == "dev"
Provides-Extra: docs
Requires-Dist: sphinx>=4.5.0; extra == "docs"
Requires-Dist: sphinx-rtd-theme>=1.0.0; extra == "docs"
Provides-Extra: all
Requires-Dist: autogluon[tabular]>=1.0.0; extra == "all"
Requires-Dist: optuna>=3.0.0; extra == "all"
Requires-Dist: featuretools>=1.0.0; extra == "all"
Requires-Dist: shap>=0.40.0; extra == "all"
Requires-Dist: openai>=1.0.0; extra == "all"
Requires-Dist: anthropic>=0.7.0; extra == "all"
Requires-Dist: huggingface-hub>=0.16.0; extra == "all"
Requires-Dist: imbalanced-learn>=0.9.0; extra == "all"
Requires-Dist: pytest>=7.0.0; extra == "all"
Requires-Dist: pytest-cov>=4.0.0; extra == "all"
Requires-Dist: black>=22.0.0; extra == "all"
Requires-Dist: flake8>=4.0.0; extra == "all"
Requires-Dist: sphinx>=4.5.0; extra == "all"
Dynamic: author
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-python

# [TMLR 2026] LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
[![arXiv](https://img.shields.io/badge/arXiv-2503.14434-b31b1b.svg)](https://arxiv.org/abs/2503.14434)
[![Hugging Face](https://img.shields.io/badge/HuggingFace-LLMFE-yellow)](https://huggingface.co/papers/2503.14434)

Official implementation of  [LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers.](https://arxiv.org/abs/2503.14434)

![](llmfe.jpg)

## 📄 Overview
LLM-FE is a novel framework that leverages Large Language Models (LLMs) as evolutionary optimizers to automate feature engineering for tabular datasets.  LLM-FE iteratively generates and refines features using structured prompts, selecting high-impact transformations based on model performance. This approach enables the discovery of interpretable and high-quality features, enhancing the performance of various machine learning models across diverse classification and regression tasks.

## ⚙️ Installation
To run the code, create a conda environment and install the dependencies using `requirements.txt`:

```
conda create -n llmfe python=3.11.7
conda activate llmfe
pip install -r requirements.txt
```

## 🔧 Usage

In `run_llmfe.sh` file, set the OPENAI API key under 
```
export API KEY = <ENTER YOUR API KEY>
```

To run the LLM-FE pipeline on a sample dataset:
```
bash run_llmfe.sh
```

## ✅ Evaluation
- The **generated features** for each dataset are stored in the logs under the `samples/` folder.
- Install `caafe` into your environment before running the evaluation.
  
  ```
  conda activate llmfe
  pip install caafe
  ```
  
- To **run the evaluation**, open the `evaluation.ipynb` notebook and set the `pb_name` variable to the dataset name you want to evaluate (i.e., replace the existing dataset name in `pb_name` with your target dataset), then run the notebook cells.

## 📝 Citation
```
@article{
abhyankar2026llmfe,
title={{LLM}-{FE}: Automated Feature Engineering for Tabular Data with {LLM}s as Evolutionary Optimizers},
author={Nikhil Abhyankar and Parshin Shojaee and Chandan K. Reddy},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=qvI35hkpOO}
}
```

## 📄 License

This repository is licensed under MIT licence.

This work is built on top of other open source projects like [FunSearch](https://github.com/google-deepmind/funsearch) and [LLM-SR](https://github.com/deep-symbolic-mathematics/llm-sr). We thank the original contributors of these works for open-sourcing their valuable source codes.


## 📬 Contact Us
For any questions or issues, you are welcome to open an issue in this repo, or contact us at  [nikhilsa@vt.edu](nikhilsa@vt.edu) and [parshinshojaee@vt.edu](parshinshojaee@vt.edu).
