I'm trying to run Independent Cascade Model for my Twitter graph to see who I have to stimulate to get the maximum cascade. This code is inspired by http://php.scripts.psu.edu/hxc249/code_segments/independent_cascade.py which uses Networkx. However, I modified a bit to be able to run with iGraph.
I create my network just OUT degree which corresponds to who I follow in Twitter. However, as far as I understand in order for a node to get infected, that node has to see the information. For example, only my followers would see that I tweeted something and if that node decided to retweeted my status that means the node is infected and the followers of that node can keep retweeting.
So, should I build my graph based on my followers instead of who I follow?
So, if I use G.successors(mynode)
that would be all the nodes that potentially might be infected of the tweet I tweeted?
Here's my code
def independent_cascade_igraph(G, seeds, steps=0):
# init activation probabilities
for e in G.es():
if 'act_prob' not in e.attributes():
e['act_prob'] = 0.1
elif e['act_prob'] > 1:
raise Exception("edge activation probability:", e['act_prob'], "cannot be larger than 1")
# perform diffusion
A = copy.deepcopy(seeds) # prevent side effect
if steps <= 0:
# perform diffusion until no more nodes can be activated
return _diffuse_all(G, A)
# perform diffusion for at most "steps" rounds
return _diffuse_k_rounds(G, A, steps)
def _diffuse_k_rounds(G, A, steps):
tried_edges = set()
layer_i_nodes = [ ]
layer_i_nodes.append([i for i in A])
while steps > 0 and len(A) < G.vcount():
len_old = len(A)
(A, activated_nodes_of_this_round, cur_tried_edges) = _diffuse_one_round(G, A, tried_edges)
layer_i_nodes.append(activated_nodes_of_this_round)
tried_edges = tried_edges.union(cur_tried_edges)
if len(A) == len_old:
break
steps -= 1
return layer_i_nodes
def _diffuse_one_round(G, A, tried_edges):
activated_nodes_of_this_round = set()
cur_tried_edges = set()
for s in A:
for nb in G.successors(s):
if nb in A or (s, nb) in tried_edges or (s, nb) in cur_tried_edges:
continue
if _prop_success(G, s, nb):
activated_nodes_of_this_round.add(nb)
cur_tried_edges.add((s, nb))
activated_nodes_of_this_round = list(activated_nodes_of_this_round)
A.extend(activated_nodes_of_this_round)
return A, activated_nodes_of_this_round, cur_tried_edges
def _prop_success(G, src, dest):
'''
act_prob = 0.1
for e in G.es():
if (src, dest) == e.tuple:
act_prob = e['act_prob']
break
'''
return random.random() <= 0.1
independent_cascade_igraph(twitter_igraph, ['121817564'], steps=1)