multi-class-probabilistic-classification
Multi-class probabilistic classification using inductive and cross Venn–Abers predictors
https://github.com/valeman/multi-class-probabilistic-classification
Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 3 DOI reference(s) in README -
✓Academic publication links
Links to: zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.4%) to scientific vocabulary
Repository
Multi-class probabilistic classification using inductive and cross Venn–Abers predictors
Basic Info
- Host: GitHub
- Owner: valeman
- License: mit
- Language: Jupyter Notebook
- Default Branch: main
- Size: 25 MB
Statistics
- Stars: 48
- Watchers: 3
- Forks: 9
- Open Issues: 2
- Releases: 1
Metadata Files
README.md
Multi-class probabilistic classification using Venn-ABERS (Conformal) prediction
Please cite the code - BIBTEX citation
@misc{https://doi.org/10.5281/zenodo.6685149, doi = {10.5281/ZENODO.6685149}, url = {https://zenodo.org/record/6685149}, author = {{Valeman}}, title = {valeman/Multi-class-probabilistic-classification: v0.1.0}, publisher = {Zenodo}, year = {2022}, copyright = {Open Access} }
Implementation of multi-class probabilistic classification using inductive and cross Venn–Abers predictors described in Multi-class probabilistic classification using inductive and cross Venn–Abers predictors. This code has also been released on Papers with Code.
The VennABERS.py file is a pure Python implementation of the fast Venn-ABERS Predictor for binary classification implemented in https://github.com/ptocca/VennABERS/ as published in NeurIPS paper Large-scale probabilistic predictors with and without guarantees of validity
Unlike other methods such as Platt's scaler and Isotonic Regression Venn-ABERS predictors (being a form of conformal prediction) contain inbuilt mathematical guarantees of validity (lack of bias). In addition Venn-ABERS predictors are multi-output predictors that output two probability predictions of class 1. Such two probability prediction of assigning label 1 for each test objectc can be considered prediction interval. The interval width contains valuable information about degree of certainty of prediction, such information is not available when using other calibration methods such as Platt's and isotonic regression.
In addition Venn-ABERS is a more advanced and regularised form of isotonic regression that, unlike isotonic regression, does not suffer from overfitting in non-large size datasets.
The Venn-ABERS predictor can be viewed as a distribution-free calibration function that maps scores output by a scoring classifier to well-calibrated probabilities. A gentle introduction can be found in the tutorial by Paolo Toccaceli (2017) listed on Awesome Conformal Prediction https://github.com/valeman/awesome-conformal-prediction
Owner
- Name: valeman
- Login: valeman
- Kind: user
- Location: London, UK
- Company: Big Business
- Website: https://valerymanokhin.academia.edu
- Twitter: predict_addict
- Repositories: 5
- Profile: https://github.com/valeman
Machine Learning | Probabilistic Prediction | Time-series | Systematic Trading | Forecasting Innovation | Creator of Awesome Conformal Prediction
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: 'Multi-class probabilistic classification using Venn-ABERS (Conformal) prediction'
message: >-
"If you use Multi-class-probabilistic-classification, please
cite it as below."
type: dataset
authors:
- given-names: Valery
family-names: Manokhin
email: notch.shushes.07@icloud.com
orcid: 'https://orcid.org/0000-0003-4040-554X'
affiliation: Independent
GitHub Events
Total
- Watch event: 6
- Issue comment event: 1
Last Year
- Watch event: 6
- Issue comment event: 1
Issues and Pull Requests
Last synced: over 1 year ago
All Time
- Total issues: 2
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 2
- Total pull request authors: 0
- Average comments per issue: 0.0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- KlausGlueckert (1)
- jinha-hwang (1)