Skip to main content

Online autonomous time series prediction of near martingales

Project description

MidOne tests

Utilities to help build Attackers that detect small departures from martingality in time-series.

Crunch Mid-One Contest notebooks

Play the game! You might win some cash or even have ongoing upside.

Contest notebook Description
Mean reversion attacker Illustrates use of the Attacker class
Momentum attacker Illustrates use of running calculations
Regression Attacker Illustrates running regression pattern

About

This package is intended to make life simpler for those participating in an ongoing tournament at CrunchDAO.com, although it hopefully has independent interest. For instance, you might build on Attacker or examples herein to help find signal in your model residuals.

  • Standalone colab notebooks demonstrating Attacker class independently of the contest.
  • See the README in attacker.md.
  • It's also highly recommended to read the FAQ.md.

Install

Stable:

 pip install endersgame 

Latest:

 pip install git+https://github.com/microprediction/endersgame.git

Getting help

See the discord channel and CrunchDAO.com.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

midone-1.0.1.tar.gz (19.0 kB view details)

Uploaded Source

Built Distribution

midone-1.0.1-py3-none-any.whl (26.9 kB view details)

Uploaded Python 3

File details

Details for the file midone-1.0.1.tar.gz.

File metadata

  • Download URL: midone-1.0.1.tar.gz
  • Upload date:
  • Size: 19.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for midone-1.0.1.tar.gz
Algorithm Hash digest
SHA256 3a2cd91f9a91ce3be838c6676f57d1f1f57c3f9e437cc8796ef74e1fe67dff62
MD5 81e0fd1e1f5a6411b9a607d5373cbe55
BLAKE2b-256 92fd080f07c28ef11fed549cb59ac926996fe8266b683d07ac24a164cd30fd81

See more details on using hashes here.

File details

Details for the file midone-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: midone-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 26.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for midone-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 7e44a1ccd1900aeafe5ba77e0c032c862792c2969c8b4d1d598d05259a203761
MD5 47f4b634084a6b321af4ebed3a8c7689
BLAKE2b-256 c6f03af3d0f2cc61c027c4836271c0e76ea2021564f2faa0378c45f95f1b78b8

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page