Skip to main content

A package to perform ND Stepwise regression for multiclass problems.

Project description

multiclass-regression

Maxwell Dix-Matthews honours project in multicategory regression

TODO Project:

  1. Add hyperparameter tuning with the digits dataset - this would be a proper case study
  2. Run Kfolds for all datasets (5 results for ND and 5 result for other, try with multiple models too - this may make it more stable as it's got more options?)
  3. Look for more datasets to run it with

TODO Code:

  1. Look into R's official implementation of ND traversal
  2. Move the cutoff function from model_functions.py to model.py
  3. Make it possible to call a model in the exact same way as scikit
  4. Performance testing with and without threading
  5. Add unit tests
  6. Upgrade to python 3.14 to avoid GIL
  7. Add proper documentation around functions

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

ndstepwise-1.0.3.tar.gz (51.0 kB view details)

Uploaded Source

Built Distribution

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

ndStepwise-1.0.3-py3-none-any.whl (77.3 kB view details)

Uploaded Python 3

File details

Details for the file ndstepwise-1.0.3.tar.gz.

File metadata

  • Download URL: ndstepwise-1.0.3.tar.gz
  • Upload date:
  • Size: 51.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.10.0

File hashes

Hashes for ndstepwise-1.0.3.tar.gz
Algorithm Hash digest
SHA256 87aa1654e6fb4f69c247c60c99d62a710b6000efa78c27351ef71c65b646ce32
MD5 88f9c8c608797736506bca6106da39c6
BLAKE2b-256 3c7c10955d01e6e889ba583d1207a2e118027c2b89de9fb2c876872f9fca6096

See more details on using hashes here.

File details

Details for the file ndStepwise-1.0.3-py3-none-any.whl.

File metadata

  • Download URL: ndStepwise-1.0.3-py3-none-any.whl
  • Upload date:
  • Size: 77.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.10.0

File hashes

Hashes for ndStepwise-1.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 d864dbc422dca2b6f8b343418ed60c945180cd4ea69837f2c5ddba40d6f6850e
MD5 c4fd6132d1db457f2127aa07b73cd400
BLAKE2b-256 d428f7df219fd63dc51fab40bb47c6e41bc5006e777b7407a0ded0281b0bab59

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