Metadata-Version: 2.4
Name: relativities
Version: 0.3.0
Summary: Run EffectiveAI insurance raters locally and analyze the results in pandas
Keywords: insurance,actuarial,rating,pricing,ratemaking,rsl
Author: EffectiveAI
Author-email: EffectiveAI <support@effectiveailabs.com>
License-Expression: LicenseRef-Proprietary
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Financial and Insurance Industry
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Office/Business :: Financial
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Typing :: Typed
Requires-Dist: httpx>=0.28,<1
Requires-Dist: pandas>=2.2,<4
Requires-Dist: pydantic>=2.12,<3
Requires-Dist: rslc==0.3.1
Requires-Dist: numpy>=2,<3 ; extra == 'models'
Requires-Dist: scipy>=1.15,<2 ; extra == 'models'
Requires-Dist: statsmodels>=0.14.6,<0.15 ; extra == 'models'
Requires-Python: >=3.12
Project-URL: Documentation, https://docs.effectiveai.app
Project-URL: Homepage, https://effectiveai.app
Provides-Extra: models
Description-Content-Type: text/markdown

# Relativities

Run EffectiveAI raters on your own book, in Python.

Relativities brings insurance raters from EffectiveAI, including competitors'
rating plans rebuilt from their public rate filings, onto your machine and runs
them on a native Rust engine. Rate one policy or an entire book, get exact
premiums back, and keep every result to yourself.

## Install

```sh
pip install relativities
export EFFECTIVE_API_KEY=sk-eai-...
```

Python 3.12 or newer on macOS, Linux and Windows. Prebuilt wheels, no compiler.

## Rate your book

```python
from relativities import Dataset, Rater

rater = Rater.load("<rater-id>")                   # downloaded once, verified, cached
book = Dataset.from_pandas(policies, key="policy_id")
results = rater(book)                              # rated locally, on every core

premiums = results.to_pandas()                     # one row per policy: status, reason, outputs
premiums["premium"].mean()                         # then it's pandas
```

## What you get

- **Exact premiums.** Every premium is calculated in exact decimal arithmetic,
  with nothing rounded behind your back.
- **Every policy accounted for.** Each policy keeps its row. A policy the rater
  refuses comes back with the reason, never as a zero premium.
- **Private by design.** Raters run on your machine; your book and results are
  never uploaded.
- **Reproducible.** Pin a rater with `revision=` to rerun exactly, even offline.
- **Fast.** A whole book is rated in parallel on every core of your machine.
- **Every step visible.** `rater(policy, detailed=True).explain()` lists each
  intermediate value behind a premium.

## License and support

Relativities is proprietary software from EffectiveAI, licensed under the terms
in the `LICENSE` file included with the package. Catalog raters and data are
covered by separate agreements.

- Website: <https://effectiveai.app>
- Documentation: <https://docs.effectiveai.app>
- Support: [support@effectiveailabs.com](mailto:support@effectiveailabs.com)
