OPA3communityTemplate for Coursera SNA class

OPA3communityTemplate.py

# Coursera SNA optional Programming Assignment 3 template

# see this blog post for a nice overview of community detection algorithms
# http://www.r-bloggers.com/summary-of-community-detection-algorithms-in-igraph-0-6/

# load the igraph library
# you may have to install this module if you haven't already
import igraph as ig
# read in the graph in GML format
# it is a sampled collection of pages from a strange set of seed categories:
# Math, Sociology, and Chemistry
# Change this to be your local file location
#  if you are using Windows, replace the \ in the path with a double \, e.g.
# g = read.graph("C:\\Users\\rool\\Documents\\My Dropbox\\Education\\Social Network Analysis\\Week 3\\wikipedia.gml",format="gml")

g = ig.read('wikipedia.gml',format='gml')
ug = g.as_undirected();

# obtain summary information about the graph
print g.summary()

# find the maximal k-core any vertex belongs to
coreness = ug.shell_index()

# find the largest clique using cliques(), also making sure the graph is treated as undirected

# fastgreedy community finding algorithm
fc = ug.community_fastgreedy().as_clustering()

# community sizes
print fc.sizes()

# membership in 30th community
print fc.subgraph(30).vs.get_attribute_values('label')

# InfoMap community finding algorithm (can be slow)
imc = ug.community_infomap().as_clustering()

# find the nodes in the largest clique
lc = ug.largest_cliques()
print ug.vs[lc[0]].get_attribute_values('label')

# use modularity() to find the modularity of any given partition