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 main(args):
# Load edgelist
G = graph_util.loadGraphFromEdgeListTxt(args.input, directed=args.directed)
G = G.to_directed()
# Preprocess the graph
# G, _ = prep_graph(G)
if args.method == 'gf':
# GF takes embedding dimension (d), maximum iterations (max_iter), learning rate (eta),
# regularization coefficient (regu) as inputs
model = GraphFactorization(d=args.dimension,
max_iter=args.max_iter,
eta=args.eta,
regu=args.regu)
elif args.method == 'hope':
# HOPE takes embedding dimension (d) and decay factor (beta) as inputs
model = HOPE(d=args.dimension, beta=args.beta)
elif args.method == 'lap':
# LE takes embedding dimension (d) as input
model = LaplacianEigenmaps(d=args.dimension)
elif args.method == 'lle':
# LLE takes embedding dimension (d) as input
model = LocallyLinearEmbedding(d=args.dimension)
elif args.method == 'sdne':
encoder_layer_list = ast.literal_eval(args.encoder_list)
# SDNE takes embedding dimension (d), seen edge reconstruction weight (beta), first order proximity weight
# (alpha), lasso regularization coefficient (nu1), ridge regreesion coefficient (nu2), number of hidden layers
# (K), size of each layer (n_units), number of iterations (n_ite), learning rate (xeta), size of batch (n_batch)
# location of modelfile and weightfile save (modelfile and weightfile) as inputs
model = SDNE(d=args.dimension,
beta=args.beta,
alpha=args.alpha,
nu1=args.nu1,
nu2=args.nu2,
K=len(encoder_layer_list),
n_units=encoder_layer_list,
n_iter=args.max_iter,
xeta=args.learning_rate,
n_batch=args.bs)
# , modelfile=['enc_model.json', 'dec_model.json'], weightfile=['enc_weights.hdf5', 'dec_weights.hdf5'])
else:
raise ValueError('The requested method does not exist!')
# Learn the node embeddings
Y, t = model.learn_embedding(graph=G,
edge_f=None,
is_weighted=args.weighted,
no_python=True)
Z = np.real_if_close(Y, tol=1000)
# Save the node embeddings to a file
np.savetxt(args.output, Z, delimiter=',', fmt='%f')
def __init__(self, dim=4, models=[]):
# Initialize set of possible models
# see "Graph Embedding Techniques, Applications, and Performance: A Survey" by
# Goyal and Ferrera (2017) for a taxonomy of graph embedding methods
if not models: # if no models specified, create some default ones
# Presently all methods are "factorization based methods"
# first method very expensive, unless C++ version installed
# models.append(GraphFactorization(d=2, max_iter=100000, eta=1*10**-4, regu=1.0))
models.append(HOPE(d=dim, beta=0.01))
models.append(LaplacianEigenmaps(d=dim))
models.append(LocallyLinearEmbedding(d=dim))
# The following "random walk based" and "deep learning based" methods will be enabled in the future
# models.append(node2vec(d=2, max_iter=1, walk_len=80, num_walks=10, con_size=10, ret_p=1, inout_p=1))
# models.append(SDNE(d=2, beta=5, alpha=1e-5, nu1=1e-6, nu2=1e-6, K=3,n_units=[50, 15,], rho=0.3, n_iter=50, xeta=0.01,n_batch=500,
# modelfile=['./intermediate/enc_model.json', './intermediate/dec_model.json'],
# weightfile=['./intermediate/enc_weights.hdf5', './intermediate/dec_weights.hdf5']))
self.models = models
def _get_embeddings(self, embedding_space):
# You can comment out the methods you don't want to run
models = list()
for embed_method in self.embeddings:
## if embed_method == EMEDDINGS.GRAPH_FACTORIZATIONE_MBEDDINGS:
## models.append(GraphFactorization(embedding_space, 100000, 1 * 10 ** -4, 1.0))
if embed_method == EMEDDINGS.LAPLACIAN_EIGENMAPS_EMBEDDINGS:
models.append(LaplacianEigenmaps(embedding_space))
if embed_method == EMEDDINGS.LOCALLY_LINEAR_EMBEDDING:
models.append(LocallyLinearEmbedding(embedding_space))
if embed_method == EMEDDINGS.HOPE_EMBEDDING:
models.append(HOPE(2 + 1, 0.01))
if embed_method == EMEDDINGS.NODE2VEC_EMBEDDING_EMBEDDINGS:
models.append(node2vec(2, 1, 80, 10, 10, 1, 1))
# Embeddings I was unable to get working yet - it seems that HOPE converts k to k+1 for some reason....
# if embed_method == EMEDDINGS.SDNE_EMBEDDING_EMBEDDINGS:
# models.append(SDNE(d=2, beta=5, alpha=1e-5, nu1=1e-6, nu2=1e-6, K=3,n_units=[50, 15,], rho=0.3, n_iter=50, xeta=0.01,n_batch=500,
# modelfile=[base_path + '/intermediate/enc_model.json', base_path + '/intermediate/dec_model.json'],
# weightfile=[base_path + '/intermediate/enc_weights.hdf5', base_path + '/intermediate/dec_weights.hdf5']))
return models
def locallyLinearEmbedding(netData, **kwargs):
d = kwargs.get('d', 2)
from gem.embedding.lle import LocallyLinearEmbedding
emb = LocallyLinearEmbedding(d=d)
return attMethods.GEMexport(netData, emb)
