Metadata-Version: 2.1
Name: punppci
Version: 0.0.7
Summary: Neural network for insurance claims modelling
Home-page: https://github.com/JackyP/penalised-unexplainability-network-payments-per-claim-incurred
Author: Jacky Poon
Author-email: jackypn@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
Requires-Dist: pandas (>=0.24.1)
Requires-Dist: koalas (>=0.4.0)
Requires-Dist: numpy (>=1.14.2)
Requires-Dist: scikit-learn (>=0.20.3)
Requires-Dist: PDPbox (>=0.2.0)
Requires-Dist: ipython (>=6.4.0)
Requires-Dist: scikit-optimize (>=0.5.2)
Requires-Dist: python-dateutil (>=2.7.3)
Requires-Dist: torch (>=1.1.0)
Requires-Dist: hiddenlayer (>=0.2)
Requires-Dist: graphviz (>=0.10.1)
Requires-Dist: skorch (>=0.5.0)

# PUNPPCI: Penalising Unexplainability Network Payments per Claim Incurred

[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/python/black)

A package for processing insurance premiums and claims data, with scikit-learn compatible applications of the PUNPPCI risk pricing and reserving model, as well as implementations of chain ladder and PPCI.

**This package is a work in progress. Please check results carefully. PR's and feedback (via the issue tracker) welcome.**

## Installation:

```{sh}
pip install punppci
```

## Usage:

Refer to [Example.ipynb](https://github.com/JackyP/penalised-unexplainability-network-payments-per-claim-incurred/blob/master/Example.ipynb) for an example.


