motifcluster 0.2.3

Motif-Based Spectral Clustering of Weighted Directed Networks

motifcluster

A Python package for motif-based spectral clustering of weighted directed networks.

Introduction

The motifcluster package provides implementations of motif-based spectral clustering of weighted directed networks in Python. These provide the capability for:

• Building motif adjacency matrices

• Sampling random weighted directed networks

• Spectral embedding with motif adjacency matrices

• Motif-based spectral clustering

The methods are all designed to run quickly on large sparse networks, and are easy to install and use. These methods are based on those described in [Underwood, Elliott and Cucuringu, 2020], which is available at arxiv:2004.01293.

Installation

From PyPI:

pip install motifcluster

With conda:

conda install -c conda-forge motifcluster

Dependencies

• Networkx

• Numpy

• Scipy

• Scikit-learn

Documentation

Documentation for the motifcluster package is available on Read the Docs.

Tutorial

A tutorial for the motifcluster package is available on Github in the tutorial directory.

Authors

• William George Underwood, Princeton University (maintainer)

• Andrew Elliott, The Alan Turing Institute

Links

• Source code repository on GitHub

• Package index page on PyPI

• Documentation on Read the Docs