help='Damping factor (float)',
default=0.15,
type='float')
optparser.add_option('--decay_factor',
dest='decay_factor',
help='Decay factor (float)',
default=0.9,
type='float')
optparser.add_option('--iteration',
dest='iteration',
help='Iteration (int)',
default=500,
type='int')
(options, args) = optparser.parse_args()
file_path = options.input_file
iteration = options.iteration
damping_factor = options.damping_factor
decay_factor = options.decay_factor
result_dir = 'result'
fname = file_path.split('/')[-1].split('.')[0]
graph = init_graph(file_path)
sim = Similarity(graph, decay_factor)
output_HITS(iteration, graph, result_dir, fname)
output_PageRank(iteration, graph, damping_factor, result_dir, fname)
output_SimRank(iteration, graph, decay_factor, result_dir, fname)
from src.utils.utils import init_graph
def PageRank_one_iter(graph, d):
node_list = graph.nodes
for node in node_list:
node.update_pagerank(d, len(graph.nodes))
graph.normalize_pagerank()
# print(graph.get_pagerank_list())
# print()
def PageRank(graph, d, iteration=100):
for i in range(iteration):
PageRank_one_iter(graph, d)
if __name__ == '__main__':
iteration = 100
damping_factor = 0.15
graph = init_graph('./dataset/graph_4.txt')
PageRank(iteration, graph, damping_factor)
print(graph.get_pagerank_list())
for i in range(edge_num):
edge = random.choice(edge_pool)
edges.append(edge)
with open('dataset/node.txt', 'w') as f:
for edge in edges:
f.write(f'{edge[0]},{edge[1]}\n')
# create_graph(10)
time_list = []
for i in range(0, 100, 10):
print(i)
create_graph(i)
graph = init_graph('dataset/node.txt')
sim = Similarity(graph, 0.9)
prev_time = time.time()
SimRank(graph, sim)
time_list.append(time.time() - prev_time)
x = [2*i for i in range(0, 100, 10)]
plt.plot(x, time_list)
plt.title('SimRank computation time with different number of edges')
plt.xlabel('Edges')
plt.ylabel('Time (sec)')
plt.show()