def get_color(i, r_off=1, g_off=1, b_off=1):
n = 16
low, high = 0.1, 0.9
span = high - low
r = low + span * (((i + r_off) * 4) % n) / (n - 1)
g = low + span * (((i + g_off) * 8) % n) / (n - 1)
b = low + span * (((i + b_off) * 12) % n) / (n - 1)
return (r, g, b)
G = nx.read_gexf('../../dataset/graph-small/graph.gexf')
# Remove social media accounts and isolates from the dataset
G = remove_unnecessary_data(G)
communities = girvan_newman(G)
node_groups = []
for community in next(communities):
node_groups.append(list(community))
node_colors = []
for ng in range(len(node_groups)):
for node in G:
if node in node_groups[ng]:
node_colors.append(get_color(ng))
nx.draw(G, node_color=node_colors)
plt.show()
# print(adjmat)
# Construct a networkx graph from the adjacency matrix
# (Singleton nodes are excluded from the graph)
G = make_graph(adjmat, labels=Config.labels)
# nx.draw(G, with_labels=True)
"""---
# ##Community detection using Girvan-Newman
# """
from networkx.algorithms.community.centrality import girvan_newman
# from networkx.algorithms.community import k_clique_communities
comp = girvan_newman(G)
max_shown = 1
shown_count = 1
possibilities = []
for communities in itertools.islice(comp, max_shown):
# print(communities) # a tuple
# print("Possibility", shown_count, ": ", end='')
# print(communities)
possibilities.append(communities)
color_map = ["" for x in range(len(G))]
color = 0
for c in communities:
indices = [i for i, x in enumerate(G.nodes) if x in c]
for i in indices:
color_map[i] = Config.colors[color]
def main():
# Load data
nodes = pd.read_csv("../data/nodes.csv", sep='\t', index_col=0)
# Data in nice form
headers = list(nodes.columns)
nodes = np.asarray(nodes)
# Load social network accordingly
edges = pd.read_csv("../data/edges.csv", sep='\t', index_col=0)
edges = np.asarray(edges).astype(int)
G = nx.Graph()
G.add_nodes_from(range(nodes.shape[0]))
G.add_edges_from(list(map(tuple, edges)))
#first compute the best partition
print("Computing Girvan Newman Algorithm")
start = timeit.default_timer()
comp = girvan_newman(G)
print(tuple(sorted(c) for c in next(comp)))
'''
max_iterations = 100
for i in range(max_iterations):
print(gir[i])
'''
stop = timeit.default_timer()
# Computing modularity
'''
num_cmtys = len(set(partition.values()))
num_edges = edges.shape[0]
cmtys = [[] for _ in range(num_cmtys)]
for node in partition.keys():
cmtys[partition[node]].append(node)
# Load social network accordingly
if path.exists("../data/youtube.graph"):
FIn = snap.TFIn("../data/youtube.graph")
social_network = snap.TNGraph.Load(FIn)
else:
social_network = data2dag(edges, nodes.shape[0])
'''
'''
modularity = 0
for cmty in cmtys:
Nodes = snap.TIntV()
for elem in cmty:
Nodes.Add(int(elem))
modularity += snap.GetModularity(social_network, Nodes, num_edges)
'''
'''
print("Calculating Modularity")
assert(is_partition(G, cmtys))
modul = modularity(G, cmtys)
print("Results from Louvain:")
print("Modularity:",modul)
print("Number of clusters:",num_cmtys)
print("Time elapsed:",stop - start)
'''
#drawing
'''
def get_network_partitions(self, matrix, num_groups, threshold=0.5):
first_array = matrix.nonzero()[0]
second_array = matrix.nonzero()[1]
# print("num edges before filter: " + str(len(first_array)))
graph = nx.Graph()
nodes = set()
weights_dict = {}
# print(len(first_array))
for i in range(len(first_array)):
if first_array[i] < second_array[i] and matrix[first_array[i], second_array[i]] > threshold:
weights_dict[i] = matrix[first_array[i], second_array[i]]
num_edges = 0
sorted_weights = [i for i in sorted(weights_dict, key=weights_dict.get, reverse=True)]
limit = min(len(sorted_weights), 1000)
for i in sorted_weights[0: limit]:
nodes.add(first_array[i])
nodes.add(second_array[i])
graph.add_edge(first_array[i], second_array[i])
num_edges += 1
#print("num nodes after filter: " + str(len(nodes)))
graph.add_nodes_from(list(nodes))
nodes = list(nodes)
nodes_to_remove = []
for sub_graph in connected_components(graph):
if len(sub_graph) < 4:
for node_id in sub_graph:
nodes_to_remove.append(node_id)
del nodes[nodes.index(node_id)]
# print("num nodes after cliques: " + str(len(nodes)))
for node_id in nodes_to_remove:
graph.remove_node(node_id)
comp = girvan_newman(graph)
partition = ()
for communities in comp:
partition = tuple(sorted(c) for c in communities)
if len(partition) >= num_groups:
break
elif len(partition) > num_groups:
partition = self.reduce_partition(partition, num_groups)
break
else:
continue
parts = [-1] * len(nodes)
for group_id, group in enumerate(partition):
for index in group:
parts[nodes.index(index)] = group_id
modified_parts = []
modified_nodes = []
for i, part in enumerate(parts):
if part >= 0:
modified_parts.append(part)
modified_nodes.append(nodes[i])
return modified_nodes, modified_parts, graph
import networkx as nx
import pandas as pd
import matplotlib.pyplot as plt
import itertools
from networkx.algorithms.community.centrality import girvan_newman
B = pd.read_csv('dm-graphtask-adj.txt', header=None)
G = nx.from_numpy_matrix(B.values)
comp = girvan_newman(G, most_valuable_edge=None)
k = 4
counter = 0
clusters = []
for communities in itertools.islice(comp, k):
if counter == 3:
for c in communities:
nodelist = list(c)
clusters.append(nodelist)
print (nodelist)
counter += 1
pos = nx.spring_layout(G)
# nodes
colors = ['r', 'g', 'b', 'y', 'm']
elif (partition[node] == 3):
color_list.append("Blue")
elif (partition[node] == 4):
color_list.append("Purple")
elif (partition[node] == 5):
color_list.append("Green")
elif (partition[node] == 6):
color_list.append("Brown")
drawGraph(G, color_list, False)
'''
#######################################################################
Step 10 output: Girvan-Newman
a) Output the number of communities, the size of largest community, size of smallest community, and modularity of this partitioning
#######################################################################'''
components = c.girvan_newman(G)
i = 0
for row in components:
if (i == 0):
finalResult = row
# print(row)
i += 1
minCommunity = len(list(G.nodes)) + 1
maxCommunity = 0
ctr = 0
partitions = dict()
L = list(finalResult)
p = 0
for comp in L:
for entry in comp:
# and add some random noise.
centrality = {e: c / max_cent for e, c in centrality.items()}
# Add some random noise.
centrality = {e: c + random() for e, c in centrality.items()}
return max(centrality, key=centrality.get)
G = nx.path_graph(10)
if len(sys.argv) < 2:
sys.stderr.write("Usage: %s <input graph>\n" % (argv[0], ))
sys.exit(1)
graph_fn = sys.argv[1]
G = nx.Graph() #let's create the graph first
buildG(G, graph_fn, '\t')
comp = girvan_newman(G, most_valuable_edge=most_central_edge)
com = 0
thisdict = {}
# Populating the items of the dictionary
for c in next(comp):
list = sorted(c)
for i in range(len(list)):
if list[i] in thisdict:
print('already found')
else:
thisdict.update({list[i]: com})
i += 1
com += 1
dict_nodes_girvan = {}