███████╗██╗ ██████╗ ███╗ ██╗ █████╗ ██╗ ███████╗
██╔════╝██║██╔════╝ ████╗ ██║██╔══██╗██║ ██╔════╝
███████╗██║██║ ███╗██╔██╗ ██║███████║██║ ███████╗
╚════██║██║██║ ██║██║╚██╗██║██╔══██║██║ ╚════██║
███████║██║╚██████╔╝██║ ╚████║██║ ██║███████╗███████║
╚══════╝╚═╝ ╚═════╝ ╚═╝ ╚═══╝╚═╝ ╚═╝╚══════╝╚══════╝
The official examples scripts for the Signals Tournament
pip install -U pip && pip install -r requirements.txt
python example_data_pipeline.py
python example_model.py
The example script model will produce an example_signal_upload.csv file which you can upload at https://signals.numer.ai/tournament to get model diagnostics.
If the current round is open (Saturday 18:00 UTC through Monday 14:30 UTC), you can submit your predictions and start getting results on live tournament data. You can create your submission by uploading the example_signal_upload.csv file at https://signals.numer.ai/tournament
The example model is a good baseline model, but we can do much better. There are three main paths for improving your Signals model: finding better data, improving your features, and improving your modeling.
The example_data_pipeline.py script shows how we use the Open Signals package
to easily get pricing data and use it to create technical features.
Open Signals is a repository created by
the Numerai Council of Elders. The goal is to create a single source for users to get
access to financial datasets and pre-made feature engineering.
The example model included in this model is very basic. Check out the forums for in depth discussions on model research.
You can upload your predictions directly to our GraphQL API or through the Python client.
To access the API, you must first create your API keys in your account page and provide them to the client:
import numerapi
example_public_id = "somepublicid"
example_secret_key = "somesecretkey"
napi = numerapi.SignalsAPI(example_public_id, example_secret_key)After instantiating the SignalsAPI client with API keys, you can then upload your submissions programmatically:
# upload predictions
model_id = napi.get_models()['your_model_name']
napi.upload_predictions("example_signal_upload.csv", model_id=model_id)The recommended setup for a fully automated submission process is to use Numerai Compute. Please see the Numerai CLI documentation for instructions on how to deploy your models to AWS.
If you need help or have any questions, please connect with us on our community chat or forums.
If something in this repo doesn't work, please file an issue.