import numpy as np
input_file = 'karate'
node_embedding = io_utils.load_embedding(
path='../data',
file_name="{}_my_ComE_l1-0_l2-0_ds-0_it-0".format(input_file),
ext=".txt")
g = mixture.GaussianMixture(n_components=2,
reg_covar=0.000001,
covariance_type='full',
n_init=5)
g.fit(node_embedding)
centroid = np.float32(g.means_)
covariance_mat = np.float32(g.covariances_)
G = graph_utils.load_adjacencylist(
path_join("../data/", input_file, input_file + '.adjlist'), True)
node_color = plot_utils.graph_plot(G=G,
show=False,
graph_name="karate",
node_position_file=True,
node_position_path='../data')
plot_utils.node_space_plot_2D_elipsoid(node_embedding,
means=centroid,
covariances=covariance_mat,
color_values=node_color,
grid=False,
show=True)
if __name__ == "__main__":
num_walks = 10
walk_length = 20
window_size = 3
negative = 4
representation_size = 2
num_workers = 1
lr = 0.1
alpha = 1.0
beta = 1.0
batch_size = 20
input_file = "karate"
output_file = "karate_my"
G = graph_utils.load_adjacencylist(
'./data/' + input_file + '/' + input_file + '.adjlist', True)
model = ComEModel(G.degree(),
size=representation_size,
input_file=input_file + '/' + input_file,
path_labels="./data",
f_type=FloatTensor)
total_example = (G.number_of_nodes() * walk_length * num_walks *
(2 * (window_size - 1)))
num_iter = int(total_example / (G.number_of_nodes() * 2))
# neg_loss = Context2Emb(deprecated_model, negative)
o1_loss = Node2Emb(model, negative)
o2_loss = Context2Emb(model, negative)
o3_loss = Community2Emb(model, reg_covar=0.00001)
output_file = 'Karate' # name of the output file
batch_size = 10
window_size = 3 # windows size used to compute the context embedding
negative = 5 # number of negative sample
lr = 0.025 # learning rate
alpha_betas = [(1., 0.01)]
down_sampling = 0.0
k = 2
walks_filebase = os.path.join('data', output_file) # where read/write the sampled path
#CONSTRUCT THE GRAPH
G = graph_utils.load_adjacencylist(os.path.join('./data', input_file, input_file + '.adjlist'), undirected=True)
# Sampling the random walks for context
log.info("sampling the paths")
walk_files = graph_utils.write_walks_to_disk(G,
os.path.join(walks_filebase, "{}.walks".format(output_file)),
num_paths=number_walks,
path_length=walk_length,
alpha=0,
rand=random.Random(0),
num_workers=num_workers)
vertex_counts = graph_utils.count_textfiles(walk_files, num_workers)
model = Model(vertex_counts,
size=representation_size,
down_sampling=down_sampling,
table_size=5000000,
if __name__ == "__main__":
num_walks = 10
walk_length = 20
window_size = 3
negative = 4
representation_size = 2
num_workers = 1
lr = 0.1
alpha = 1.0
beta = 1.0
num_iter = 200
input_file = "karate"
output_file = "karate_my"
path = "../data"
G = graph_utils.load_adjacencylist(
os.path.join(path, input_file, input_file + '.adjlist'), True)
model = ComEModel(G.degree(),
size=representation_size,
input_file=input_file + '/' + input_file,
path_labels=path)
model.k = 2
o2_loss = Context2Emb(model, negative)
o3_loss = Community2Emb(model, reg_covar=0.00001)
node_color = plot_utils.graph_plot(G=G,
show=False,
graph_name="karate",
node_position_file=True,
node_position_path=path)
exmple_filebase = os.path.join(