A network in space theme

PathpyG

An Open Source package facilitating next-generation network analytics and graph learning for time series data on graphs. PyG Logo

Get Started More Info
© #321341 / Colourbox.de

The New Pathpy

  • Easy to Use

    You can directly get started using PathpyG since it adapts the interfaces from commonly used frameworks. The graphs are based PyG and plotting works similar as in pandas.

  • Great with Jupyter Notebooks

    This package is built with excellent support for Jupyter Notebooks. It offers interactive HTML visualizations that enhance data analysis and exploration via D3.js.

  • GPU Accelerated

    Since PathpyG is based on Torch, you can run your computations on the GPU. Even computations that cannot run on the GPU are parallelized for optimal performance.

  • Optimal for Scientific Writing

    This package is ideal for scientific writing as it supports LaTeX as an export option. This allows for seamless integration of the network visualizations via PGF/TikZ in your documents.

  • Netzschleuder Support

    We provide easy access to over 250 real world datasets via Netzschleuder - a catalogue and repository of network datasets with the goal of aiding scientific research.

  • Open Source

    Our package is open source, promoting collaborative development and transparency. This allows anyone to contribute, modify, and distribute the software, fostering innovation and rapid improvement.

Our Partners

PathpyG is developed by an international team of researchers. Our key contributors are affiliated with:

You Want To Help?

We are always looking for contributors to help us improve the package. If you are interested, please check us out on GitHub or read more about how to contribute on our contributing page.

GitHub Read More