def prep_ws(inpath):
"""
Preprocess web spam graph.
"""
# Create an empty digraph
G = nx.DiGraph()
# Read the file and create the graph
src = 0
f = open(inpath, 'r')
for line in f:
if src != 0:
arr = line.split()
for dst in arr:
dst_id = int(dst.split(':')[0])
# We consider the graph unweighted
G.add_edge(src, dst_id)
src += 1
# G.add_node(src-2)
# Preprocess the graph
G, ids = pp.prep_graph(G, relabel=True, del_self_loops=False)
# Return the preprocessed graph
return G
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 prep_fb(inpath):
"""
Preprocess facebook wall post graph.
"""
# Load a graph
G = pp.load_graph(inpath, delimiter='\t', comments='#', directed=True)
# The FB graph is stores as destination, origin so needs to be reversed
G = G.reverse()
# Preprocess the graph
G, ids = pp.prep_graph(G, relabel=True, del_self_loops=False)
# Return the preprocessed graph
return G
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 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
# ---------------
# Preprocess data
# ---------------
# Load the data as a directed graph
G = pp.load_graph(dataset_path, delimiter=",", comments='#', directed=directed)
# 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
# ----------------
#!/usr/bin/env python # -*- coding: utf-8 -*- # Author: Mara Alexandru Cristian # Contact: [email protected] # Date: 18/12/2018 # This simple example is the one presented in the README.md file. from evalne.evaluation import evaluator from evalne.preprocessing import preprocess as pp # Load and preprocess the network G = pp.load_graph('../evalne/tests/data/network.edgelist') G, _ = pp.prep_graph(G) # Create an evaluator and generate train/test edge split nee = evaluator.Evaluator() _ = nee.traintest_split.compute_splits(G) # Set the baselines methods = ['random_prediction', 'common_neighbours', 'jaccard_coefficient'] # Evaluate baselines nee.evaluate_baseline(methods=methods) try: # Check if OpenNE is installed import openne # Set embedding methods from OpenNE methods = ['node2vec', 'deepwalk', 'GraRep']