Skip to content

precise 1.0.0 — online covariance/correlation

Latest
Latest

Choose a tag to compare

View all tags
@microprediction microprediction released this 05 Jun 03:22
· 45 commits to main since this release
v1.0.0
3cb57c3
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

First stable release of the rewritten precise: a focused library for online (incremental) covariance and correlation estimation — the online complement to sklearn.covariance.

pip install precise

  • sklearn-style online estimators (partial_fit; covariance_/correlation_/precision_/location_); 14 via all_estimators()
  • keyed river-style adapters for dynamic universes (keyed, FixedUniverse, DynamicUniverse)
  • assessment layer (all_assessors()), incl. the Schur pseudo-likelihood
  • recommender (suggest) — frozen, numpy-only
  • numpy-only core (numpy>=1.21, tested on 1.26 & 2.x); optional [pandas]/[research]/[dev] extras; ships py.typed

Breaking vs 0.16.x: the functional "skater" API is removed (from precise.skaters… now raises a pointer to MIGRATING.md), and portfolio/allocation code moved to schur. See MIGRATING.md and CHANGELOG.md.

Assets 2
Loading