Train model with safety constraints

Project description

FairML library

An easy to use Python Library to train and develop new Machine Learning models within some fairness constraints. This is an implementation of this Science paper.

Installation

Currently, you can install the library only from source using pip:

pip install https://github.com/hannanabdul55/seldonian-fairness/archive/master.zip

Usage

Use this notebook as a reference to train a basic Logistic Regression Model.

A quickstart tutorial on how to get quickly get started with developing your own model is present here. Alternatively, you could use the LogisticRegressionSeldonianModel to train a Logistic Regression model with any scipy.optimize.minimize method by specifying it when calling the fit method.

Project details

Release history Release notifications | RSS feed

This version

0.0.3.dev0 pre-release

Nov 19, 2020

0.0.2.dev0 pre-release

Nov 18, 2020

0.0.1.dev0 pre-release

Nov 18, 2020

Download files

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

Source Distribution

seldonian-0.0.3.dev0.tar.gz (11.7 kB view details)

Uploaded Nov 19, 2020 Source

Built Distribution

seldonian-0.0.3.dev0-py3-none-any.whl (14.2 kB view details)

Uploaded Nov 19, 2020 Python 3

File details

Details for the file seldonian-0.0.3.dev0.tar.gz.

File metadata

Download URL: seldonian-0.0.3.dev0.tar.gz
Upload date: Nov 19, 2020
Size: 11.7 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.25.0 setuptools/47.1.0 requests-toolbelt/0.9.1 tqdm/4.52.0 CPython/3.7.9

File hashes

Hashes for seldonian-0.0.3.dev0.tar.gz
Algorithm	Hash digest
SHA256	`9e8c3db30818ef9707f32a93b545953d9a471c28946f2ad9d50d08f614c3f612`
MD5	`d22f764f5d25d30b961074cf71954fca`
BLAKE2b-256	`33549a7e0323fee607da98b36a1189e794ecec53dfbb3a979a24bd36b6304077`

See more details on using hashes here.

File details

Details for the file seldonian-0.0.3.dev0-py3-none-any.whl.

File metadata

Download URL: seldonian-0.0.3.dev0-py3-none-any.whl
Upload date: Nov 19, 2020
Size: 14.2 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.25.0 setuptools/47.1.0 requests-toolbelt/0.9.1 tqdm/4.52.0 CPython/3.7.9

File hashes

Hashes for seldonian-0.0.3.dev0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`895eef583a5c68000902deeea445c091627b4a8db103277de234b056f143c437`
MD5	`2061cfce39061f46fe4e83d9ed720f1f`
BLAKE2b-256	`7435d47e8a6296a626420688829d115920add194dafe15b1db7ba7e2b63e548e`