def main(data_set_name):
dimensions = 1
input_file = './graph/' + data_set_name + '.tsv'
output_file = '../data/' + data_set_name + '.emb'
# Instatiate the embedding method with hyperparameters
lle = LocallyLinearEmbedding(dimensions)
# Load graph
# graph = graph_util.loadGraphFromEdgeListTxt(input_file)
graph = networkx.read_weighted_edgelist(input_file)
# Learn embedding - accepts a networkx graph or file with edge list
embeddings_array, t = lle.learn_embedding(graph, edge_f=None, is_weighted=True, no_python=True)
embeddings = pandas.DataFrame(embeddings_array)
embeddings.to_csv(output_file, sep=' ', na_rep=0.1)
def get_embeddings(graph,
embedding_algorithm_enum,
dimension_count,
hyperparameter,
lower=None,
higher=None):
"""Generate embeddings. """
if embedding_algorithm_enum is EmbeddingType.LocallyLinearEmbedding:
embedding_alg = LocallyLinearEmbedding(d=dimension_count)
elif embedding_algorithm_enum is EmbeddingType.Hope:
embedding_alg = HOPE(d=dimension_count, beta=0.01)
elif embedding_algorithm_enum is EmbeddingType.GF:
embedding_alg = GraphFactorization(d=dimension_count,
max_iter=100000,
eta=1 * 10**-4,
regu=1.0)
elif embedding_algorithm_enum is EmbeddingType.LaplacianEigenmaps:
embedding_alg = LaplacianEigenmaps(d=dimension_count)
elif embedding_algorithm_enum is EmbeddingType.DegreeNeigDistributionWithout:
A = np.array([
np.histogram([graph.degree(neig) for neig in graph.neighbors(i)],
bins=dimension_count,
density=True,
range=(lower, higher))[0] for i in graph.nodes()
])
A = (A - A.mean(axis=0)) / A.std(axis=0)
return A
elif embedding_algorithm_enum is EmbeddingType.DegreeNeigDistribution:
A = np.array([
np.concatenate([
np.array([graph.degree(i) / (higher * dimension_count)]),
np.histogram(
[graph.degree(neig) for neig in graph.neighbors(i)],
bins=dimension_count - 1,
density=True,
range=(lower, higher))[0]
],
axis=0) for i in graph.nodes()
])
A = (A - A.mean(axis=0)) / A.std(axis=0)
return A
elif embedding_algorithm_enum is EmbeddingType.DegreeNeigNeigDistribution:
bin_length = int(dimension_count / 2)
A = np.array([
np.concatenate([
np.array([graph.degree(i) / (higher)]),
np.histogram(
[graph.degree(neig) for neig in graph.neighbors(i)],
bins=bin_length,
density=True,
range=(lower, higher))[0],
np.histogram([
graph.degree(neigneig) for neig in graph.neighbors(i)
for neigneig in graph.neighbors(neig)
],
bins=bin_length,
density=True,
range=(lower, higher))[0]
],
axis=0) for i in graph.nodes()
])
A = (A - A.mean(axis=0)) / A.std(axis=0)
A[:, 0] = A[:, 0]
A[:, 1:1 + bin_length] = A[:, 1:1 + bin_length]
A[:, 2 + bin_length:] = A[:, 2 + bin_length:] * hyperparameter
A = np.nan_to_num(A)
return A
else:
raise NotImplementedError
A, t = embedding_alg.learn_embedding(graph=graph, no_python=True)
A = np.dot(A, np.diag(np.sign(np.mean(A, axis=0))))
A = (A - A.mean(axis=0)) / A.std(axis=0)
return A