def load_dms(removed_nodes: List[int],
save_info: sl.MemoryAccess,
num_iterations: int,
use_specific_iter: int = None):
if num_iterations == 1:
assert (use_specific_iter is not None)
if save_info.has_distance_matrix(removed_nodes=removed_nodes,
iteration=use_specific_iter):
yield save_info.load_distance_matrix(removed_nodes=removed_nodes,
iteration=use_specific_iter)
else:
emb = save_info.load_embedding(removed_nodes=removed_nodes,
iteration=use_specific_iter)
dm = cdm.calc_distances(model=emb,
save_info=save_info,
removed_nodes=removed_nodes,
iteration=use_specific_iter)
yield dm
else:
for i in range(num_iterations):
if save_info.has_distance_matrix(removed_nodes=removed_nodes,
iteration=i):
yield save_info.load_distance_matrix(
removed_nodes=removed_nodes, iteration=i)
else:
emb = save_info.load_embedding(removed_nodes=removed_nodes,
iteration=i)
dm = cdm.calc_distances(model=emb,
save_info=save_info,
removed_nodes=removed_nodes,
iteration=i)
yield dm
def __calc_dm(graph: gc.Graph, removed_nodes: [int],
save_info: sl.MemoryAccess, i: int) -> (int, pd.DataFrame):
if save_info.has_distance_matrix(removed_nodes=removed_nodes, iteration=i):
# print("Distance matrix for removed nodes", removed_nodes, "and iteration", i, "is already trained")
return i, save_info.load_distance_matrix(removed_nodes=removed_nodes,
iteration=i)
else:
# print(f'Calculate distance matrix for removed nodes {removed_nodes} iteration {i}')
# model = embedding_function(graph=graph, save_info=save_info, removed_nodes=removed_nodes, iteration=i)
# thows error if embedding does not exist
model = save_info.load_embedding(removed_nodes=removed_nodes,
iteration=i)
dm = cd.calc_distances(model=model,
graph=graph,
save_info=save_info,
removed_nodes=removed_nodes,
iteration=i,
save=False)
save_info.save_distance_matrix(removed_nodes=removed_nodes,
iteration=i,
dm=dm)
return i, dm
def train_node2vec_embedding(edge_list_path: str,
graph: Graph,
save_info: sl.MemoryAccess,
removed_nodes: [int],
iteration: int,
epochs: int,
dim: int,
walk_length: int,
num_of_walks_per_node: int,
window_size: int,
alpha: float,
return_embedding: bool = False,
check_for_existing: bool = True):
target = save_info.get_embedding_name(removed_nodes=removed_nodes,
iteration=iteration)
if check_for_existing and os.path.exists(target + ".emb"):
#print('Embedding for removed nodes {} and iteration {} already exists'.format(removed_nodes, iteration))
if return_embedding:
return save_info.load_embedding(removed_nodes=removed_nodes,
iteration=iteration)
else:
target_path = os.path.abspath(target + "_path.emb")
# create walks
# execute path training
wd = os.getcwd()
os.chdir(config.NODE2VEC_SNAP_DIR)
subprocess.call('./node2vec \
-i:"' + edge_list_path + '" \
-o:"' + target_path + '" \
-e:' + str(epochs) + " -d:" + str(dim) + " -l:" +
str(walk_length) + " -r:" +
str(num_of_walks_per_node) + " -k:" +
str(window_size) + " -ow",
shell=True) # output random walks only
os.chdir(wd)
# end create paths
class Walks:
def __init__(self, file):
self.file = file
def __iter__(self):
with open(target_path, "r") as f:
for line in f:
line = line.strip("\n").split(" ")
# assert (all(list(map(lambda node: node in graph.nodes(), list(map(int, line))))))
yield line
walks = Walks(target_path)
# train word2vec
emb_result = gensim.models.Word2Vec(walks,
size=dim,
iter=epochs,
window=window_size,
min_count=1,
sg=1,
workers=config.NUM_CORES,
alpha=alpha)
os.remove(target_path)
save_info.save_embedding(removed_nodes, iteration, emb_result)
if return_embedding:
return emb_result