Skip to content

Latest commit

 

History

History
15 lines (12 loc) · 469 Bytes

README.md

File metadata and controls

15 lines (12 loc) · 469 Bytes

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning

This repo is the PyTorch code of our paper, which is accepted to ICML 2024.

Required packages

  • python == 3.8.10
  • torch == 2.0.0
  • numpy == 1.24.4
  • scikit-learn == 1.3.0
  • pandas == 2.0.3
  • openai == 0.28.0
  • tqdm == 4.66.1

To run the code

Check Main.ipynb for running the code. Changing the simulation parameters and data names is enough to run experiments