def detect_events(cand_trees, K):
nodes_of_trees = [set(t.nodes()) for t in cand_trees]
selected_ids = argmax_k_coverage(nodes_of_trees, K)
trees = [cand_trees[id_] for id_ in selected_ids]
return trees
def detect_events(cand_trees, K):
nodes_of_trees = [set(t.nodes()) for t in cand_trees]
selected_ids = argmax_k_coverage(nodes_of_trees, K)
trees = [cand_trees[id_] for id_ in selected_ids]
return trees
def k_best_trees(cand_trees, k):
# print('removing self-talking event')
# print('before, len(cand_trees):', len(cand_trees))
# cand_trees = [t for t in cand_trees
# if len(set(t.node[n]['sender_id']
# for n in t.nodes_iter())) > 1]
# print('after, len(cand_trees):', len(cand_trees))
nodes_of_trees = [set(t.nodes()) for t in cand_trees]
selected_ids = argmax_k_coverage(nodes_of_trees, k)
return [cand_trees[id_] for id_ in selected_ids]
def k_best_trees(cand_trees, k):
# print('removing self-talking event')
# print('before, len(cand_trees):', len(cand_trees))
# cand_trees = [t for t in cand_trees
# if len(set(t.node[n]['sender_id']
# for n in t.nodes_iter())) > 1]
# print('after, len(cand_trees):', len(cand_trees))
nodes_of_trees = [set(t.nodes()) for t in cand_trees]
selected_ids = argmax_k_coverage(nodes_of_trees, k)
return [cand_trees[id_] for id_ in selected_ids]
# name path name path
# names = [name for i, name in enumerate(sys.argv[1:]) if i % 2 == 0]
# paths = [path for i, path in enumerate(sys.argv[1:]) if i % 2 == 1]
paths = glob("tmp/lda-25-topics/result-*U=5*interactions=False*.pkl")
names = map(lambda n:
n.replace('tmp/lda-25-topics/result-', '').replace('.pkl', ''),
paths)
K = 5
table = []
for name, path in zip(names, paths):
trees = pickle.load(open(path))
nodes_of_trees = [set(t.nodes()) for t in trees]
selected_ids = argmax_k_coverage(nodes_of_trees, K)
selected_trees = [trees[i] for i in selected_ids]
nodes_list = [t.nodes() for t in selected_trees]
unique_nodes = reduce(lambda acc, nodes: acc | set(nodes),
nodes_list,
set())
row = [name]
row += [len(nodes) for nodes in nodes_list]
row.append(len(unique_nodes))
table.append(row)
df = pds.DataFrame(table, columns=['', '#1', '#2', '#3', '#4', '#5', 'total'])
print(tabulate(df.sort(['total'], ascending=False),
