Evaluate machine-learning models
Project description
audmetric includes several equations to estimate the performance of a machine learning prediction algorithm.
Some of the metrics are also available in sklearn, but we wanted to have a package which depends only on numpy. For those metrics we included tests that the results are identical to sklearn.
Changelog
All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
Version 1.1.4 (2022/07/05)
Fixed: accuracy formula in docstring
Version 1.1.3 (2022/02/16)
Added: reference for CCC formula
Fixed: support pandas series with datatype Int64
Version 1.1.2 (2022/01/11)
Fixed: typo in docstring of audmetric.mean_absolute_error()
Version 1.1.1 (2022/01/03)
Added: Python 3.9 support
Removed: Python 3.6 support
Version 1.1.0 (2021/07/29)
Added: audmetric.utils.infer_labels()
Added: audmetric.equal_error_rate()
Added: audmetric.detection_error_tradeoff()
Version 1.0.1 (2021/06/10)
Fixed: broken package due to missing __init_.py file
Version 1.0.0 (2021/06/09)
Added: initial public release
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file audmetric-1.1.4.tar.gz.
File metadata
- Download URL: audmetric-1.1.4.tar.gz
- Upload date:
- Size: 20.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.8.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | dbbf3927f107398203e033b2bcea1e6618c51567d6ce9a76f157c9c6621bbd31 |
|
| MD5 | 42a89736fb97fd8ed8482c22f62ab2d2 |
|
| BLAKE2b-256 | 3d3267cfc3e774cc176bdac9e51fc0934daa891e6b66d17921e18f3d6b57e254 |
File details
Details for the file audmetric-1.1.4-py3-none-any.whl.
File metadata
- Download URL: audmetric-1.1.4-py3-none-any.whl
- Upload date:
- Size: 12.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.8.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 9bdece91d9dd6c28d649f79e6aec7da972143ebe5a35fd82a1c20ae8d3c43102 |
|
| MD5 | 2f644a168219e9a9759c3cd7b409878a |
|
| BLAKE2b-256 | a5000b566119f2e69128bd325a5d25aef259c8fd1c9f924a6fb22e8d920c7e11 |
