adstk

adstk

ADSTK aims to bundle together relevant actuarial models, tools and code simplifications to enrich the Actuarial / Insurance Data Science experience in the Python ecosystem.

Features

ADSTK currently ships with a limited number of methods and use cases:

• Partial dependence display with support for individual conditional expectation curves (ICE)

Dependencies

adstk requires:

• Python (>= 3.10)
• NumPy (>= 1.24)
• SciPy (>= 1.10)

Optional requirements for plotting etc.

• matplotlib ()
• plotly ()

User installation

The easiest way to install adstk will using pip once we publish on PyPi:

pip install -U adstk

Changelog

See the changelog for a history of notable changes to adstk.

Development

We welcome human contributors of all experience levels. The adstk community goals are to be helpful, welcoming, and effective. The Contributing guide has detailed information about contributing code, documentation, tests, and more. Please also note our AI contribution policy before submitting anything.

Important links

• Official source code repo: https://codeberg.org/ftranschel/adstk
• Download releases: https://pypi.org/project/adstk/
• Issue tracker: https://codeberg.org/ftranschel/adstk/issues

Source code

You can check the latest sources with the command:

git clone https://codeberg.org/ftranschel/adstk.git

Contributing

To learn more about making a contribution to adstk, please see our Contributing guide.

Testing

After installation, you can launch the test suite from the source directory (you will need pytest installed):

pytest

Submitting a Pull Request

Before opening a pull request, please read the Contributing guide and our AI policy to make sure your submission complies with our guidelines.