and v has vertex betweenness greater than the max edge
betweenness
"""
bests = []
for node in self.levels[level]:
node.calculate_v_betweenness()
if node.clone.viable_vertices:
for v in node.clone.viable_vertices:
bests.append((node, v))
node.clone.viable_vertices = []
return bests
def convert_to_circles(self):
"""
Returns:
-------
A dict mapping ints (levels) to a list of circles at that level of
splitting
"""
out = {}
for k, v in self.levels.iteritems():
out[k] = [[n.graph.vertices[uid].uid for uid in n.graph.adj_list.keys()] for n in v]
return out
def __str__(self):
return str(self.convert_to_circles())
if __name__ == "__main__":
ego_net_lists, features, circles = read_data(*argv[1:])
dendrogram = Dendrogram(ego_net_lists[1310])
from __future__ import print_function
from data_in import read_data
from sys import argv
from dendrogram import Dendrogram
from modularity import find_best_splits
if __name__ == "__main__":
"""
Finds the best clustering for each of the given ego network files.
Stores output to file called submission.csv
"""
ego_nets = read_data(argv[1])
# Good sets (small) to test on are 25708, and 1310
# Change this variable to change the egonet that it starts reading from
# start = 8338
# index = [k for k, v in tup_ls].index(start)
index = 0 # use the line above instead if not running from start
tup_ls = sorted(ego_nets.iteritems(), key=lambda t: t[1].size)
out = open("submission.csv", "w")
# out = open("out.txt", "a") # if not running from start, use append instead
while index < len(tup_ls):
uid, ego_net = tup_ls[index]
print("Analyzing ego network {0}".format(uid))
dendrogram = Dendrogram(ego_net)
size = ego_net.size
best_split = find_best_splits(dendrogram.levels, size)
circles = dendrogram.convert_to_circles()[best_split]
circ_str = str(uid) + "," + str(len(circles)) + ","
circ_str += ";".join([" ".join([str(fid) for fid in circle]) for circle in circles])
print(circ_str, file=out)
