import networkx as nx
import gravlearn as gn
import torch
# Load data
G = nx.karate_club_graph()
A = nx.adjacency_matrix(G)
labels = [G.nodes[i]["club"] for i in G.nodes]
# Generate the sequence for demo
sampler = gn.RandomWalkSampler(A, walk_length=40, p=1, q=1)
walks = [sampler.sampling(i) for _ in range(10) for i in range(A.shape[0])]
# Training
model = gravlearn.Word2Vec(A.shape[0], 32) # Embedding based on set
dist_metric = gravlearn.DistanceMetrics.EUCLIDEAN
model = gravlearn.train(model, walks, device = device, bags =A ,window_length=5, dist_metric=dist_metric)
# Embedding
emb = model.forward(torch.arange(A.shape[0]))
1 maintainer
Release files for gravlearn 0.0.10
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| gravlearn-0.0.10-py3-none-any.whl | Python 3 | none | any | Details |
Release files / gravlearn-0.0.10-py3-none-any.whl
| Download URL | gravlearn-0.0.10-py3-none-any.whl |
|---|---|
| Size | 13.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0a3d0fcdf27ce8534b07a506e99fb18fed8594beb1502b3b1be38cfb4af4dc9a
|
|
BLAKE2b-256 checksum How to use checksums |
ff722f6c6647c7547eff841f2cca6bc827b01db0ec7393d3b8523ee2baf9ad0b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.9.13
|
