folder = os.path.join('data', dataset, 'graphs')

res = {}

nodes = {}

stats = {}

links_to_scc = {}

for N in Ns:

print(' ', N)

gt_file = os.path.join(folder, '%s_%d.gt' % (rec_type, N))

graph = gt.load_graph(gt_file, fmt='gt')

# # DEBUG

# title2dataset_id = {v: k for k, v in dataset_id2title.items()}

# dataset_id2node = {graph.vp['name'][n]: n for n in graph.vertices()}

# title2node = {title: dataset_id2node[title2dataset_id[title]] for title in dataset_id2title.values()}

# #/DEBUG

dataset_id2bow_tie = {graph.vp['name'][n]: graph.vp['bowtie'][n]

for n in graph.vertices()}

bt2ratings = {l: [] for l in bt_labels}

bt2nodes = {l: [] for l in bt_labels}

for did, bt in dataset_id2bow_tie.items():

bt2ratings[bt].append(dataset_id2rating_count[did])

bt2nodes[bt].append(dataset_id2title[did])

res[N] = {k: [np.mean(v), np.median(v)] for k, v in bt2ratings.items()}

res[N] = {k: v for k, v in res[N].items() if not np.isnan(v[0])}

stats[N] = graph_stats(graph)

links_to_scc[N] = get_links_to_scc(graph)

nodes[N] = bt2nodes

clustering_coefficient = 0

neighbors = {int(node): set([int(n) for n in node.out_neighbours()])

for node in graph.vertices()}

for idx, node in enumerate(graph.vertices()):

node = int(node)

if len(neighbors[node]) < 2:

continue

edges = sum(len(neighbors[int(n)] & neighbors[node])

for n in neighbors[node])

cc = edges / (len(neighbors[node]) * (len(neighbors[node]) - 1))

clustering_coefficient += cc

component, histogram = gt.label_components(graph)

return [

clustering_coefficient / graph.num_vertices(),

len(histogram),

count = 0

count_scc = 0

for node in graph.vertices():

if not graph.vp['bowtie'][node] == 'IN':

continue

for nb in node.out_neighbours():

count += 1

if graph.vp['bowtie'][nb] == 'SCC':

count_scc += 1

if count == 0:

return -1