gihyeon/cointrader
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: enhance model training and deployment scripts with time-weighted sampling

Browse Source 
- Updated `train_model.py` and `train_mlx_model.py` to include a time weight decay parameter for improved sample weighting during training.
- Modified dataset generation to incorporate sample weights based on time decay, enhancing model performance.
- Adjusted deployment scripts to support new backend options and improved error handling for model file transfers.
- Added new entries to the training log for better tracking of model performance metrics over time.
- Included ONNX model export functionality in the MLX filter for compatibility with Linux servers.
This commit is contained in:
21in7
2026-03-01 21:25:06 +09:00
parent 301457ce57
commit db144750a3
10 changed files with 324 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
requirements.txt
View File

@@ -12,3 +12,4 @@ lightgbm>=4.3.0
scikit-learn>=1.4.0
joblib>=1.3.0
pyarrow>=15.0.0
onnxruntime>=1.18.0