Skip to main content

Produces a low-dimensional representation of the input graph

Project description

Produces a low-dimensional representation of the input graph.

Calculates the ECTD [1] of the graph and reduces its dimension using PCA. The result is an embedding of the graph nodes as vectors in a low-dimensional space.

Graph data in this repository is courtesy of the mind-blowingly cool University of Florida Sparse Matrix Collection.

Python 3.x and 2.6+.

Usage

Draw a graph, including edges, from a mat file

>>> import scipy.io
>>> import networkx as nx
>>> import graphpca
>>> mat = scipy.io.loadmat('test/bcspwr01.mat')
>>> A = mat['Problem'][0][0][1].todense()  # that's just how the file came
>>> G = nx.from_numpy_matrix(A)
>>> graphpca.draw_graph(G)
output/bcspwr01-drawing.png

Get a 2D PCA of a high-dimensional graph and plot it.

>>> import networkx as nx
>>> import graphpca
>>> g = nx.erdos_renyi_graph(1000, 0.2)
>>> g_2 = graphpca.reduce_graph(g, 2)
>>> graphca.plot_2d(g_2)
output/erg-1000.png

Contributing

Issues and Pull requests are very welcome! [On GitHub](https://github.com/brandones/graphpca).

[1]https://www.info.ucl.ac.be/~pdupont/pdupont/pdf/ecml04.pdf

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

graphpca-1.0.0.tar.gz (6.7 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page