def main():
# Check cmd args
if len(argv) != 3:
print("ERROR: wrong number of parameters")
print("Usage: prep_data_prune.py <facebook_path> <webspam_path>")
exit(-1)
# Extract the dataset names and paths
fb_path, fb_name = os.path.split(argv[1])
ws_path, ws_name = os.path.split(argv[2])
# Preprocess FB graph
G1 = prep_fb(argv[1])
# Store FB graph to a file
pp.save_graph(G1,
output_path=fb_path + "/prep_graph_slfloops.edgelist",
delimiter=',',
write_stats=True)
# Preprocess WS graph
G2 = prep_ws(argv[2])
# Store preprocessed graph to a file
pp.save_graph(G2,
output_path=ws_path + "/prep_graph_slfloops.edgelist",
delimiter=',',
write_stats=True)
print("Preprocessing finished.")
def test_split():
# Variables
dataset_path = "./data/"
output_path = "./data/"
test_name = "network.edgelist"
subgraph_size = 1000
# Load a graph
G = pp.load_graph(dataset_path + test_name,
delimiter="\t",
comments='#',
directed=True)
# Restrict graph to a sub-graph of 'subgraph_size' nodes
SG = G.subgraph(random.sample(G.nodes, subgraph_size)).copy()
# Preprocess the graph
SG, ids = pp.prep_graph(SG, relabel=True, del_self_loops=True)
# Get stats of the preprocessed subgraph
pp.save_graph(SG, output_path + "prep_graph.edgelist", delimiter=",")
# Alternatively, train/test splits can be computed one at a time
train_E, test_E = stt.split_train_test(SG, train_frac=0.51, seed=99)
print(train_E)
# Compute set of false edges
train_E_false, test_E_false = stt.generate_false_edges_owa(
SG,
train_E=train_E,
test_E=test_E,
num_fe_train=None,
num_fe_test=None,
seed=99)
def preprocess(setup, i):
"""
Graph preprocessing rutine.
"""
if setup.verbose:
print('Preprocesing graph...')
# Load a graph
G = pp.load_graph(setup.inpaths[i],
delimiter=setup.separators[i],
comments=setup.comments[i],
directed=setup.directed[i])
# Preprocess the graph
G, ids = pp.prep_graph(G,
relabel=setup.relabel,
del_self_loops=setup.del_selfloops)
if setup.prep_nw_name is not None:
# Store preprocessed graph to a file
pp.save_graph(G,
output_path=setup.outpaths[i] + setup.prep_nw_name,
delimiter=setup.delimiter,
write_stats=setup.write_stats)
# Return the preprocessed graph
return G
def save_tr_graph(self,
output_path,
delimiter,
write_stats=False,
write_weights=False,
write_dir=True):
"""
Saves the graph to a file.
Parameters
----------
output_path : file or string
File or filename to write. If a file is provided, it must be opened in 'wb' mode.
delimiter : string, optional
The string used to separate values. Default is .
write_stats : bool, optional
Sets if graph statistics should be added to the edgelist or not. Default is False.
write_weights : bool, optional
If True data will be stored as weighted edgelist (e.g. triplets src, dst, weight) otherwise as normal
edgelist. If the graph edges have no weight attribute and this parameter is set to True,
a weight of 1 will be assigned to each edge. Default is False.
write_dir : bool, optional
This option is only relevant for undirected graphs. If False, the train graph will be stored with a single
direction of the edges. If True, both directions of edges will be stored. Default is True.
"""
pp.save_graph(self._TG,
output_path=output_path,
delimiter=delimiter,
write_stats=write_stats,
write_weights=write_weights,
write_dir=write_dir)
def test():
# Variables
dataset_path = "./data/"
output_path = "./data/"
test_name = "network.edgelist"
# Load a graph
G = pp.load_graph(dataset_path + test_name,
delimiter=',',
comments='#',
directed=True)
# Print some stats
print("")
print("Original graph stats:")
print("-----------------------------------------")
pp.get_stats(G)
# Save the graph
pp.save_graph(G, output_path + "orig_graph.edgelist", delimiter=",")
# Load the saved graph
G2 = pp.load_graph(output_path + "orig_graph.edgelist",
delimiter=",",
comments='#',
directed=True)
# Stats comparison
print("Has the same stats after being loaded?:")
print("-----------------------------------------")
pp.get_stats(G2)
# Preprocess the graph
GP, ids = pp.prep_graph(G2, del_self_loops=False, relabel=True)
print("Preprocessed graph stats (restricted to main cc):")
print("-----------------------------------------")
pp.get_stats(GP)
pp.save_graph(GP, output_path + "prep_graph.edgelist", delimiter=",")
print("Sample of 10 (oldNodeID, newNodeID):")
print("-----------------------------------------")
print(ids[0:10])
pp.get_redges_false(GP, output_path + "redges_false.csv")
def save_tr_graph(self, output_path, delimiter, write_stats=False):
"""
Saves the graph to a file.
Parameters
----------
output_path : file or string
File or filename to write. If a file is provided, it must be opened in 'wb' mode.
delimiter : string, optional
The string used to separate values. Default is .
write_stats : bool, optional
Sets if graph statistics should be added to the edgelist or not. Default is False.
"""
pp.save_graph(self._TG,
output_path=output_path,
delimiter=delimiter,
write_stats=write_stats)
def preprocess(inpath, outpath, delimiter, directed):
"""
Graph preprocessing routine.
"""
print('Preprocessing graph...')
# Load a graph
G = pp.load_graph(inpath, delimiter=delimiter, comments='#', directed=directed)
# Preprocess the graph
G, ids = pp.prep_graph(G, relabel=True, del_self_loops=True)
# Store preprocessed graph to a file
pp.save_graph(G, output_path=outpath + "prep_graph.edgelist", delimiter=',', write_stats=True)
# Return the preprocessed graph
return G
# Get some graph statistics
pp.get_stats(G)
# Or store them to a file
pp.get_stats(G, output_path + "stats.txt")
# Preprocess the graph
SG, ids = pp.prep_graph(G, relabel=True, del_self_loops=True)
# Get non-edges so that the reversed edge exists in the graph
if directed:
redges = pp.get_redges_false(SG, output_path=output_path + "redges.csv")
# Store the graph to a file
pp.save_graph(SG,
output_path=output_path + "network_prep.edgelist",
delimiter=',',
write_stats=True)
# ----------------
# Split train test
# ----------------
# Compute train/test splits and false edges in parallel
stt.compute_splits_parallel(SG,
output_path +
"lp_train_test_splits/network_prep_51",
owa=True,
train_frac=0.51,
num_fe_train=None,
num_fe_test=None,
num_splits=5)