Skip to main content

Stress-test time-series forecasters: known dynamical systems, controlled shocks, calibrated noise titration (the AURA protocol). Placeholder release; 0.1.0 in preparation.

Project description

serie

Stress-test your forecaster before reality does.

serie will implement the AURA protocol (Artificial Uncertainty and Regime Alteration): take a clean reference series — a simulated dynamical system with exact ground truth, or a clean recording treated as the system — apply controlled non-stationary shocks, and inject calibrated Gaussian observation noise at chosen levels. Measure exactly when and how a forecaster breaks, instead of ranking models on one recorded history.

import serie

stock = serie.prepare("lorenz", seed=42)
for sigma in (0.0, 0.25, 1.0, 2.0):
    split = serie.titrate(stock, sigma=sigma)
    ...

This is a 0.0.1 name reservation — the API above ships in 0.1.0. Watch github.com/QilinWang for the release.

MIT license. Author: Qilin Wang.

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

serie-0.0.1.tar.gz (2.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

serie-0.0.1-py3-none-any.whl (3.0 kB view details)

Uploaded Python 3

File details

Details for the file serie-0.0.1.tar.gz.

File metadata

  • Download URL: serie-0.0.1.tar.gz
  • Upload date:
  • Size: 2.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.16 {"installer":{"name":"uv","version":"0.9.16","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"12","id":"bookworm","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for serie-0.0.1.tar.gz
Algorithm Hash digest
SHA256 a2eb003306fc05c5920b3af350045ce435b658c61228a319a04fe152486f0fb3
MD5 4803930845d0168bef5e1c4165538cb0
BLAKE2b-256 db1a351ba70629919c065dc6b6e022ed1c54d4e7b01f4eb9b6ce4d89352222d8

See more details on using hashes here.

File details

Details for the file serie-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: serie-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 3.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.16 {"installer":{"name":"uv","version":"0.9.16","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"12","id":"bookworm","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for serie-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 de12ecc1ca05936d5e0076084674dc6adf52e486466104362964390f7e8b3d3b
MD5 b01f539f938c8cd56fd12d6b63b05afe
BLAKE2b-256 056a2ffe37da08924989176841fa064239bc8ea71fce19f7b826e561e5fc1592

See more details on using hashes here.

Supported by

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