CoFEH

CoFEH is a feature engineering and hyperparameter optimization framework based on LLMs and MCTS, designed to enhance automated machine learning workflows.

---

Installation

Install the required Python packages with:

pip install -r requirements.txt

Project Structure:

CoFEH_FE:mindware/modeules/llm_fe/mcts_evaluator.py CoFEH_FE_HPO:mindware/modeules/llm_fe/mcts_hpo_evaluator.py

Environment Setup

Before running any examples, make sure to export your OpenAI API key:

export OPENAI_API_KEY=your_api_key_here

Usage Examples

1. CoFEH Feature Engineering + HPO

python CoFEH_examples.py \
    --data_name rl \ 
    --ml_model llm_fe_xgboost \
    --times 10 \
    --task_model CoFEH_HPO_FE \
    --seed 1

2. CoFEH Feature Engineering Only

python CoFEH_examples.py \
    --data_name rl \
    --ml_model llm_fe_xgboost \
    --times 10 \
    --task_model CoFEH_FE \
    --seed 1