PyTorch library for recommender systems
Project description
FreeRec is a personal repository designed for fast data pre-processing and model training. I am a beginner in the field of recommender systems, so much of FreeRec's design may not be as effective. In addition, you are free to specify your own framework based on FreeRec.
Requirements:
Python == 3.9 | PyTorch == 1.12.1 | TorchData == 0.4.1 | PyG
conda create --name=PyT12 python=3.9
conda activate PyT12
pip install torch==1.12.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113
pip install torchdata==0.4.1
- Linux
pip install torch_geometric==2.1.0.post1
pip install https://data.pyg.org/whl/torch-1.12.0%2Bcu116/torch_scatter-2.0.9-cp39-cp39-linux_x86_64.whl
pip install https://data.pyg.org/whl/torch-1.12.0%2Bcu116/torch_sparse-0.6.15%2Bpt112cu116-cp39-cp39-linux_x86_64.whl
- Windows
pip install torch_geometric==2.1.0.post1
pip install https://data.pyg.org/whl/torch-1.12.0%2Bcu116/torch_scatter-2.0.9-cp39-cp39-win_amd64.whl
pip install https://data.pyg.org/whl/torch-1.12.0%2Bcu116/torch_sparse-0.6.15%2Bpt112cu116-cp39-cp39-win_amd64.whl
Installation
pip install freerec
or (for latest)
pip install git+https://github.com/MTandHJ/freerec.git
Data Pipeline
Note: To make dataset, please download corresponding Atomic files from [RecBole]. Then, run `make_dataset.ipynb'.
Training Flow
Reference Code
- TorchRec: https://github.com/pytorch/torchrec
- DeepCTR-Torch: https://github.com/shenweichen/DeepCTR-Torch
- FuxiCTR: https://github.com/xue-pai/FuxiCTR
- BARS: https://github.com/openbenchmark/BARS
- RecBole: https://github.com/RUCAIBox/RecBole
Acknowledgements
Thanks to ChatGPT for the annotation of some code. For this reason, some of the comments may be illogical.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
freerec-0.3.5.tar.gz
(58.6 kB
view hashes)