graph-embeddings 0.1.0

Graph embeddings for downstream tasks

Graph-Embeddings

Graph embeddings for downstream tasks

Installation:

It’s advised to install graph-embeddings using a virtual env, inside the env use:

pip install graph-embeddings

Algorithms:

StackedNode2Vec

Computes the Node2Vec representation of each node in a set of graphs.

Example:

import networkx as nx
from graph_embeddings.algorithms import StackedNode2Vec

g1 = nx.DiGraph()
g2 = nx.DiGraph()
g1.add_edges_from([("A", "B"), ("B", "C"), ("C", "B"), ("B", "E")])
g2.add_edges_from([("A", "B"), ("B", "D"), ("D", "C"), ("C", "D")])

graphs = [g1, g2]
embedding_model = StackedNode2Vec()
embedding_model.fit(graphs)

embedding_model.get_embeddings()  # ndarray with shape (2, 5, 128) - graphs, nodes, embedding_size
embedding_model.get_dense_embeddings()  # ndarray with shape (2, 640) - graphs, nodes*embedding_size

Changelog

See the changelog for notes on the changes of graph-embeddings

Important links

• Official source code repo: https://github.com/rodrigo-arenas/graph-embeddings/

• Download releases: https://pypi.org/project/graph-embeddings/

• Issue tracker: https://github.com/rodrigo-arenas/graph-embeddings/issues

• Stable documentation: https://graph-embeddings.readthedocs.io/

Source code

You can check the latest development version with the command:

git clone https://github.com/rodrigo-arenas/graph-embeddings.git

Install the development dependencies:

pip install -r dev-requirements.txt

Check the latest in-development documentation: https://graph-embeddings.readthedocs.io/en/latest/

Contributing

Contributions are more than welcome! There are several opportunities on the ongoing project, so please get in touch if you would like to help out. Make sure to check the current issues and also the Contribution guide.