audmetric

Evaluate machine-learning models

These details have not been verified by PyPI

Project links

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 1.1.5 (2023/01/03)

Added: support for Python 3.10
Added: support for Python 3.11
Changed: split API documentation into sub-pages for each function

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

Project details

These details have not been verified by PyPI

Project links

Release history Release notifications | RSS feed

1.2.2

Jun 18, 2024

1.2.1

Feb 28, 2024

1.2.0

May 8, 2023

1.1.6

Jan 3, 2023

This version

1.1.5

Jan 3, 2023

1.1.4

Jul 5, 2022

1.1.3

Feb 16, 2022

1.1.2

Jan 11, 2022

1.1.1

Jan 3, 2022

1.1.0

Jul 29, 2021

1.0.1

Jun 10, 2021

1.0.0

Jun 9, 2021

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

audmetric-1.1.5.tar.gz (22.1 kB view details)

Uploaded Jan 3, 2023 Source

Built Distribution

audmetric-1.1.5-py3-none-any.whl (12.3 kB view details)

Uploaded Jan 3, 2023 Python 3

File details

Details for the file audmetric-1.1.5.tar.gz.

File metadata

Download URL: audmetric-1.1.5.tar.gz
Upload date: Jan 3, 2023
Size: 22.1 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/4.0.2 CPython/3.8.15

File hashes

Hashes for audmetric-1.1.5.tar.gz
Algorithm	Hash digest
SHA256	`66b242a2d75fd75b00f2ded8150c0229185e2da2216c3902535d390ad2d72215`
MD5	`6b1c6206cbf162c830826abdfc7e0a9c`
BLAKE2b-256	`104856d35db6a0f37535371c3e36a565039b3904d922eb94ea6550c3eccbdcbd`

See more details on using hashes here.

File details

Details for the file audmetric-1.1.5-py3-none-any.whl.

File metadata

Download URL: audmetric-1.1.5-py3-none-any.whl
Upload date: Jan 3, 2023
Size: 12.3 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/4.0.2 CPython/3.8.15

File hashes

Hashes for audmetric-1.1.5-py3-none-any.whl
Algorithm	Hash digest
SHA256	`6f7e5cc92e80d1b25264dd29d63f9614289657c1be8cd9966c5e7ccad294dc27`
MD5	`1d55152b06a6b1c3fb162311499683ec`
BLAKE2b-256	`043d84278f6457e80fd52d8c1c64408373c41b5057006962d1eb9a21e92cc22d`