Co-author mining with shortest path in the Brede Wiki

gistfile1.py

# wget http://neuro.imm.dtu.dk/services/bredewiki/download/bredewiki-templates.sqlite3
import matplotlib.pyplot as plt
import networkx as nx
from pysqlite2 import dbapi2

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

g = nx.Graph()
sql = "SELECT value FROM brede WHERE tid=? AND field='author'";
for tid in tids:
    cursor.execute(sql, (tid,))
    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])


path = nx.shortest_path(g, u"Finn Årup Nielsen", "Natalie Herslag")
for author in path: print(author)