def print_top_betweenness(component, size=10):
bc = nx.betweenness_centrality(component, weight='weight', normalized=True)
for node in sorted(bc, key=bc.get, reverse=True)[0:size]:
query = {'spec': {'user.id': int(node) }, 'fields':{'_id':0,'user.screen_name': 1} }
this_data = bf.query_mongo_get_list(query, limit=1)
print this_data['user']['screen_name'],'&', "{0:.4f}".format(bc[node]), '\\\\'
return bc
def get_range(query=bf.all_tweets):
tweets = bf.query_mongo_get_list(query)
times = []
for tweet in tweets:
tweet["created_at"] -= datetime.timedelta(hours=6) # Adjusting for TimeZone
times.append(tweet["created_at"])
times.sort()
return times
def get_data_list(time_step=60, just_count=True, limit=False):
"""Returns dictionary:
Keys: Time Steps
Values: #Tweets in TimeStep"""
tweets = bf.query_mongo_get_list(bf.all_tweets)
flood_days = {}
for tweet in tweets:
tweet["created_at"] -= datetime.timedelta(hours=6) # Adjusting for TimeZone
this_hour = f.roundTime(tweet["created_at"], roundTo=time_step)
if flood_days.has_key(this_hour):
flood_days[this_hour].append(tweet)
else:
flood_days[this_hour] = [tweet]
if just_count:
for i in flood_days.keys():
flood_days[i] = len(flood_days[i])
return flood_days
else:
return flood_days
plt.title('Out Degree vs. Reciprocity')
plt.ylabel("Reciprocity per Node")
plt.xlabel("Out Degree")
plt.show()
def print_top_betweenness(component, size=10):
bc = nx.betweenness_centrality(component, weight='weight', normalized=True)
for node in sorted(bc, key=bc.get, reverse=True)[0:size]:
query = {'spec': {'user.id': int(node) }, 'fields':{'_id':0,'user.screen_name': 1} }
this_data = bf.query_mongo_get_list(query, limit=1)
print this_data['user']['screen_name'],'&', "{0:.4f}".format(bc[node]), '\\\\'
return bc
if __name__ == '__main__':
"""First, get only geo_tagged_tweets"""
geo_tagged_user_mentions = bf.query_mongo_get_list(bf.only_geo_tagged)
print "Geo_Tagged found:", len(geo_tagged_user_mentions), "Making Graph..."
umg_geo = user_mentions_graph(geo_tagged_user_mentions)
print 'Users',len(umg_geo.nodes())
# connected_components = nx.weakly_connected_component_subgraphs(umg_geo)
# print "Number of Connected Components:", len(connected_components)
# for subgraph in connected_components[0:5]:
# print "Component has", len(subgraph.nodes())
# #f.draw_network_plt(connected_components[1])
print '\nreciprocity, weighted:', f.get_graph_reciprocity(umg_geo)
print 'reciprocity, unweighted:', f.get_graph_reciprocity(umg_geo, weighted=False)
#print f.reciprocity_by_degree(umg_geo, 'in')
print "self loops:"
f.print_top_self_loops(umg_geo, size=10)
plt.plot([0,0],[0,1000], 'k-')
#plt.plot([-.01,1],[],'r-')
plt.title('Number of Triangles vs. Clustering Coefficient')
plt.ylabel("Triangles")
plt.xlabel("Clustering Coefficient")
plt.xlim([0,.06])
plt.ylim([0,60])
return plt
############################## RUNTIME #######################################
if __name__ == '__main__':
# Get all retweets
retweets = bf.query_mongo_get_list(bf.retweets)
print "Number of Retweets: ", len(retweets)
retweets_graph = retweeted_graph(retweets)
print "Nodes: ", len(retweets_graph.nodes()), "Edges: ", len(retweets_graph.edges())
# Trim nodes to greater than 500
trimmed_retweets = f.trim_graph(retweets_graph,'weight', 500)
print "Trimmed to 500:",len(trimmed_retweets.nodes())
#f.write_network_gml(trimmed_retweets,'retweeted_hashtags_gt_500')
# Triangles Vs. Clustering Coefficient
make_triangle_cc_plot(trimmed_retweets, show_labels=True, threshold=60).show()
# Centralities:
#f.print_betweenness_centrality(trimmed_retweets)
