Skip to main content
PyUoI logo

codecov Documentation Status PyPI Anaconda-Server Badge DOI

PyUoI contains implementations of Union of Intersections framework for a variety of penalized generalized linear models as well as dimensionality reductions techniques such as column subset selection and non-negative matrix factorization. In general, UoI is a statistical machine learning framework that leverages two concepts in model inference:

  1. Separating the selection and estimation problems to simultaneously achieve sparse models with low-bias and low-variance parameter estimates.
  2. Stability to perturbations in both selection and estimation.

PyUoI is designed to function similarly to scikit-learn, as it often builds upon scikit-learn's implementations of the aforementioned algorithms.

Further details on the UoI framework can be found in the NeurIPS paper (Bouchard et al., 2017).

Installation

PyUoI is available for Python 3 on PyPI:

pip install pyuoi

and through conda-forge:

conda install pyuoi -c conda-forge

Requirements

Runtime

PyUoI requires

  • numpy>=1.14
  • h5py>=2.8
  • scikit-learn>=0.24

and optionally

  • pycasso
  • mpi4py

to run.

Develop

To develop PyUoI you will additionally need

  • cython

to build from source and

  • pytest
  • flake8

to run the tests and check formatting.

Features

PyUoI is split up into two modules, with the following UoI algorithms:

  • linear_model (generalized linear models)
    • Lasso penalized linear regression UoILasso.
    • Elastic-net penalized linear regression (UoIElasticNet).
    • Logistic regression (Bernoulli and multinomial) (UoILogistic).
    • Poisson regression (UoIPoisson).
  • decomposition (dimensionality reduction)
    • Column subset selection (UoICSS).
    • Non-negative matrix factorization (UoINMF).

Similar to scikit-learn, each UoI algorithm has its own Python class.

Documentation

Please see our ReadTheDocs page for an introduction to Union of Intersections, usage of PyUoI, and the API.

Copyright

PyUoI Copyright (c) 2019, The Regents of the University of California, through Lawrence Berkeley National Laboratory (subject to receipt of any required approvals from the U.S. Dept. of Energy). All rights reserved.

If you have questions about your rights to use or distribute this software, please contact Berkeley Lab's Innovation & Partnerships Office at IPO@lbl.gov referring to " PyUoI" (LBNL Ref 2019-157)."

NOTICE. This software was developed under funding from the U.S. Department of Energy. As such, the U.S. Government has been granted for itself and others acting on its behalf a paid-up, nonexclusive, irrevocable, worldwide license in the Software to reproduce, prepare derivative works, and perform publicly and display publicly. The U.S. Government is granted for itself and others acting on its behalf a paid-up, nonexclusive, irrevocable, worldwide license in the Software to reproduce, prepare derivative works, distribute copies to the public, perform publicly and display publicly, and to permit others to do so.

Metadata

Release files for pyuoi 1.1.1

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

Source distribution (sdist)

Source distribution for pyuoi 1.1.1
File Size Uploaded Provenance Actions
pyuoi-1.1.1.tar.gz 93.2 kB Without provenance Details for pyuoi-1.1.1.tar.gz

Release files / pyuoi-1.1.1.tar.gz

Download URL pyuoi-1.1.1.tar.gz
Size 93.2 kB
Tags Source
SHA-256 checksum
How to use checksums
9ea2267beff5dc2d11d4f5dec6ea2669ed360c239eb223250b3d0f78b4621602
BLAKE2b-256 checksum
How to use checksums
2cff643cbc1bdee960db2647b764f75ffe7ec78e9e40ee3f7b2baf922f3531c7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.8 tqdm/4.63.0 importlib-metadata/4.11.3 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.8.12

Security for pyuoi 1.1.1

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.

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