Co-author mining for papers in the Brede Wiki

gistfile1.py

import matplotlib.pyplot as plt
import networkx as nx
from pysqlite2 import dbapi2

connection = dbapi2.Connection('bredewiki-templates.sqlite3')
sql = "SELECT DISTINCT pid FROM brede WHERE (template='paper' OR template='conference_paper');"
cursor = connection.cursor()
cursor.execute(sql)
pids = [ row[0] for row in cursor.fetchall() ]

g = nx.Graph()
sql = "SELECT value FROM brede WHERE pid=? AND field='author'";
for pid in pids:
    cursor.execute(sql, (pid,))
    authors = [ row[0] for row in cursor.fetchall() ]
    for n in range(len(authors)):
        for m in range(len(authors)):
	    g.add_edge(authors[n], authors[m])


nx.draw(nx.connected_component_subgraphs(g)[3])
plt.show()
plt.savefig('coauthors.png')