Metadata-Version: 2.2
Name: torchcast
Version: 0.1
Summary: A simple PyTorch library for time series analysis
Author: Mark Lowell
Author-email: Mark Lowell <MarkLowell@theorem-engine.org>
Project-URL: Homepage, https://github.com/TheoremEngine/torchcast
Project-URL: Issues, https://github.com/TheoremEngine/torchcast/issues
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Classifier: License :: OSI Approved :: MIT License
Description-Content-Type: text/markdown
Dynamic: author

## What is torchcast? <img align="right" src="docs/source/_static/torchcast_logo.png" width="100" height="100">

torchcast is a library for time series forecasting, classification, and regression in PyTorch. It focuses primarily on making it easy to fetch, preprocess, and iterate over time series datasets. **It is still under heavy construction.**

## Installation

torchcast includes C++ code that must be compiled to be used. To install torchcast, first make sure that you have g++ installed, along with Python, including its development headers. Then, run:

```
git clone https://github.com/TheoremEngine/torchcast.git
cd torchcast
python3 setup.py install
```
