Skip to main content

numerai-tools

A collection of open-source tools to help interact with Numerai, model data, and automate submissions.

Installation

pip install numerai-tools

Structure

  • The scoring.py module contains critical functions used to score submissions. We use this code in our scoring system system. Leverage this to optimize your models for the tournaments.

    The Signals payout scores are built from two of its functions:

    • neutral_correlation ranks, gaussianizes, and neutralizes predictions against a neutralizer matrix, then correlates them with the target. Unlike numerai_corr it applies no 1.5 power, and unlike feature_neutral_corr it does not re-rank and re-power the predictions after neutralizing them.
    • neutral_contribution is correlation_contribution with that same neutralization step inserted after the rank/gaussianize step. It neutralizes both the submissions and the meta model against the same neutralizers before orthogonalizing. Predictions identical to the meta model have zero neutral contribution, up to floating-point precision.
  • The submissions.py module provides helper functions to ensure your submissions are valid and formatted correctly. Use this in your automated prediction pipelines to ensure uploads don't fail.

  • The signals.py module provides code specific to Numerai Signals such as churn and turnover. neutral_churn measures churn after applying each era's neutralizers, calculate_mean_neutral_churn averages that metric across the provided recent submissions, and neutral_churn_penalty calculates the positive-payout retention multiplier described by the Signals v3 churn penalty.

Metadata

Release files for numerai-tools 0.7.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for numerai-tools 0.7.2
File Size Uploaded Provenance Actions
numerai_tools-0.7.2.tar.gz 15.7 kB Without provenance Details for numerai_tools-0.7.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for numerai-tools 0.7.2
File Interpreter ABI Platform Actions
numerai_tools-0.7.2-py3-none-any.whl Python 3 none any Details for numerai_tools-0.7.2-py3-none-any.whl

Total release size: 34.2 kB

Release files / numerai_tools-0.7.2.tar.gz

Download URL numerai_tools-0.7.2.tar.gz
Size 15.7 kB
Tags Source
SHA-256 checksum
How to use checksums
cd61335834b76cdf8acac2c925a2e4383962e01cd85e32c3d737a92782b51f08
BLAKE2b-256 checksum
How to use checksums
00d8415a3fa9aa387dbd6c2e65530c1385749768ff15250ac70d24a6f79d0a68
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.4.3 CPython/3.14.7 Linux/6.17.0-1022-azure

Release files / numerai_tools-0.7.2-py3-none-any.whl

Download URL numerai_tools-0.7.2-py3-none-any.whl
Size 18.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
74389ba28029c48e9fb2ada6a4793c5795a4045ff02dc0f31b4fd14299053dce
BLAKE2b-256 checksum
How to use checksums
14da3395efd71f7e34a2645de6d7acb40847446b5cdaad496a3a39b601527c01
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.4.3 CPython/3.14.7 Linux/6.17.0-1022-azure

Security for numerai-tools 0.7.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.7.2 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page