https://github.com/iepathos/hello-numerai
Organizes the numer.ai hello first submission with Poetry installation and a script for downloading the models, training, and generating the first predict.pkl upload.
https://github.com/iepathos/hello-numerai
machine-learning numerai tutorial
Last synced: about 4 hours ago
JSON representation
Organizes the numer.ai hello first submission with Poetry installation and a script for downloading the models, training, and generating the first predict.pkl upload.
- Host: GitHub
- URL: https://github.com/iepathos/hello-numerai
- Owner: iepathos
- Created: 2024-01-11T12:13:19.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-01-17T02:03:32.000Z (over 2 years ago)
- Last Synced: 2025-10-09T20:03:13.301Z (9 months ago)
- Topics: machine-learning, numerai, tutorial
- Language: Python
- Homepage:
- Size: 115 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# hello-numerai
An organized repository for the numer.ai Hello tutorial. This is an alternative to the notebook numer.ai provides which isn't 100% working. This repo uses Poetry for dependency management, works on Ubuntu and Macos, and will train and output the first predictions to Numer.ai.
Usage:
```
./install.sh
./run.sh
```
First Upload (Step 1/3 of Tutorial)
Upload the output predict.pkl to Numer.ai
Feature Neutralization (Step 2/3 of Tutorial)
Upload the output predict_neutral.pkl to Numer.ai
Target Ensemble (Step 3/3 of Tutorial)
Upload the output predict_ensemble.pkl to Numer.ai