def test_clustering_score(self):
"""
Test global clustering score with generalized formula
This is the average of the local clustering scores for each node v:
2 Nv where Kv = degree
C(v) = ---------- Nv = number of edges between
Kv (Kv - 1) the neighbors of v
"""
test_data_path = os.path.join(self._fixtures_dir, 'les-miserables.csv')
results = ctd.get_summary(test_data_path)
graph = ctd.get_graph(test_data_path)
local_scores = []
for v in graph.nodes():
k = graph.degree(v)
neighbor_links = []
for u in nx.all_neighbors(graph, v):
neighbor_links += [
tuple(sorted((u, w)))
for w in nx.common_neighbors(graph, u, v)
]
n = len(list(set(neighbor_links)))
local_scores.append(
2 * n / float(k *
(k - 1))) if k > 1 else local_scores.append(0)
self.assertAlmostEqual(results['clustering'],
sum(local_scores) / float(len(local_scores)))
def test_centrality_scores(self):
"""
Test betweenness centrality with generalized formula
For a node v and every other node pair (s, t), we take the proportion of shortest paths s => t that include
v and then normalize the sum of all the proportions by dividing (N - 1)(N - 2) / 2, the number of node pairs
"""
test_data_path = os.path.join(self._fixtures_dir, 'les-miserables.csv')
results = ctd.get_summary(test_data_path)
graph = ctd.get_graph(test_data_path)
table = results['table']
self.assertEqual(table[0]['id'], 'Valjean')
nodes = graph.nodes()
nodes.remove('Valjean')
betweenness_centrality = 0
visited_paths = []
for u in nodes:
for v in nodes:
current_path = tuple(sorted((u, v)))
if u == v or current_path in visited_paths:
continue
else:
visited_paths.append(current_path)
paths = list(nx.all_shortest_paths(graph, u, v))
total_paths = len(paths)
paths_with_valjean = reduce(
lambda n, path: n + 1
if 'Valjean' in path else n, paths, 0)
betweenness_centrality += paths_with_valjean / float(
total_paths)
node_pairs = len(nodes) * (len(nodes) - 1) / float(2)
normalized_score = betweenness_centrality / node_pairs
self.assertAlmostEqual(table[0]['centrality'], normalized_score)
def test_centrality_scores(self):
"""
Test betweenness centrality with generalized formula
For a node v and every other node pair (s, t), we take the proportion of shortest paths s => t that include
v and then normalize the sum of all the proportions by dividing (N - 1)(N - 2) / 2, the number of node pairs
"""
test_data_path = os.path.join(self._fixtures_dir, "les-miserables.csv")
results = ctd.get_summary(test_data_path)
graph = ctd.get_graph(test_data_path)
table = results["table"]
self.assertEqual(table[0]["id"], u"Valjean")
nodes = graph.nodes()
nodes.remove(u"Valjean")
betweenness_centrality = 0
visited_paths = []
for u in nodes:
for v in nodes:
current_path = tuple(sorted((u, v)))
if u == v or current_path in visited_paths:
continue
else:
visited_paths.append(current_path)
paths = list(nx.all_shortest_paths(graph, u, v))
total_paths = len(paths)
paths_with_valjean = reduce(lambda n, path: n + 1 if u"Valjean" in path else n, paths, 0)
betweenness_centrality += paths_with_valjean / float(total_paths)
node_pairs = len(nodes) * (len(nodes) - 1) / float(2)
normalized_score = betweenness_centrality / node_pairs
self.assertAlmostEqual(table[0]["centrality"], normalized_score)
def test_clustering_score(self):
"""
Test global clustering score with generalized formula
This is the average of the local clustering scores for each node v:
2 Nv where Kv = degree
C(v) = ---------- Nv = number of edges between
Kv (Kv - 1) the neighbors of v
"""
test_data_path = os.path.join(self._fixtures_dir, "les-miserables.csv")
results = ctd.get_summary(test_data_path)
graph = ctd.get_graph(test_data_path)
local_scores = []
for v in graph.nodes():
k = graph.degree(v)
neighbor_links = []
for u in nx.all_neighbors(graph, v):
neighbor_links += [tuple(sorted((u, w))) for w in nx.common_neighbors(graph, u, v)]
n = len(list(set(neighbor_links)))
local_scores.append(2 * n / float(k * (k - 1))) if k > 1 else local_scores.append(0)
self.assertAlmostEqual(results["clustering"], sum(local_scores) / float(len(local_scores)))
