Light

zincware / symsuite Goto Github PK

View Code? Open in Web Editor NEW

8.0 1.0 0.0 4.47 MB

A python package using machine learning to study symmetry.

Home Page: https://symsuite.readthedocs.io/en/latest/

License: Eclipse Public License 2.0

Python 100.00%

machine-learning group-theory lie-algebra symmetry

symsuite's Introduction

SymSuite

A python package to perform symmetry detection and generator extraction on raw data. Follows the paper by Sven Krippendorf and Marc Syvaeri on Detecting symmetries with neural networks.

Notes

This project is under heavy development and is therefore not available on PyPi. I would not expect major API breaks but certainly addition of functionality.

Installation

There are several options for installing SymDet

PyPi

We host the code on PyPi and so it can be simply installed by:

pip3 install symdet

Install from source

pip installation

git clone https://github.com/zincware/SymSuite.git
cd SymDet
pip3 install . --user

conda installation

git clone https://github.com/zincware/SymSuite.git
cd SymDet
conda create -n SymDet python=3.8
conda activate SymDet
pip3 install .

Documentation

There is a live version of the documentation hosted here. Alternatively you can build it from source using

cd Symdet/docs
make html

You can then browse the documentation locally using your favourite browser.

Getting started

As a first step I would suggest looking at the examples directory and following along with some tutorials. From here you may get a better idea of what you can use this package for.

Comments

This is a really young project and any comments or contributions would be welcome. If you see issues in the documentation (particularly if you're a mathematician) I would always welcome the feedback.

symsuite's People

Contributors

Stargazers

Watchers

symsuite's Issues

License should be EPL not GNU

Describe the bug
Change the license information to EPL.

Add functionality for bridging symmetry group detection and Lie algebra extraction.

The goal of detecting and describing symmetries requires communication between the two modules. This also required developing a method wherein symmetry groups found in the symmetry detection phase are identified and passed to a generator extraction stage.

Clustering image does not work.

If one tries to export an image of cluster data on top of the raw function data the clustering will be performed but the raw data it is laid upon will be incorrect. It appears that the raw data is being plotted in the wrong order, therefore, when it is displayed, it looks terrible.

SO Example has error

Describe the bug
The imports in the SO example notebook fail

To Reproduce
Run the SO_example notebook

Allow for arbitrary data generator.

Is your feature request related to a problem? Please describe.
It would become a more generalization code if data could be parsed in a more arbitrary fashion through a generic data generator class.

Describe the solution you'd like
Change the input data parameter in the clustering class to a data generator object so that arbitrary data can be called. Also, move the data clustering image to the generator class.

nan failure in generator extraction.

Is your feature request related to a problem? Please describe.
The failure of generator extraction when a NaN is encountered should be pushed into a try except to as it is a common occurrence.

Finish unit tests.

Is your feature request related to a problem? Please describe.
Finish the unit tests for the code.

Add theory to the documentation.

All mathematics and method theory must be added to the documentation.

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.