def main():
"""Parse the graph file, and run both PageRank and HITS on it."""
print "Parsing text file."
(number_emails, graph) = graphs.process_file("data/graph.txt")
_dump_stats(number_emails, graph)
_run_pagerank(graph)
_run_hits(graph)
print "Finished!"
def main():
"""Parse the graph file, and run both PageRank and HITS on it."""
print "Parsing text file."
(number_emails, graph) = graphs.process_file("data/graph.txt")
_dump_stats(number_emails, graph)
_run_pagerank(graph)
_run_hits(graph)
print "Finished!"
def main():
"""Creates a graph.dot file with interesting information."""
print "Parsing wikipedia.txt"
wiki_words = get_wikipedia_words("data/wikipedia.txt")
# Parse the aliases.txt file.
print "Parsing aliases.txt"
(aliases, inverse_aliases) = get_aliases("data/aliases.txt")
# Parse the roles.txt file.
print "Parsing roles.txt"
employees_info = info.get_employees_map("data/roles.txt", inverse_aliases)
# Parse the graph.txt file to get the email graph.
print "Parsing graph.txt"
(_, email_graph) = graphs.process_file("data/graph.txt", inverse_aliases)
interesting_nodes = get_interesting_nodes(email_graph, aliases)
relations = get_relations(interesting_nodes, employees_info, wiki_words)
# Write the resultant graph.
print "Writing results."
with open("graph.dot", "w") as f:
f.write('digraph G {\n')
print "%s relations" % len(relations)
for (i, relation) in enumerate(sorted(relations)):
print "%s" % i
a = relation.from_info
b = relation.to_info
# Choose the most common word in the email subjects.
c = counter.Counter()
for email in relation.emails.emails:
if email.subject is not None:
c.update(email.subject)
if len(c) > 0:
best_word = c.most_common(1)[0][0]
else:
best_word = ""
f.write('"%s" -> "%s" [label = "%s"];\n' %
(a.description(), b.description(), best_word))
f.write('}\n')
def main():
"""Creates a graph.dot file with interesting information."""
print "Parsing wikipedia.txt"
wiki_words = get_wikipedia_words("data/wikipedia.txt")
# Parse the aliases.txt file.
print "Parsing aliases.txt"
(aliases, inverse_aliases) = get_aliases("data/aliases.txt")
# Parse the roles.txt file.
print "Parsing roles.txt"
employees_info = info.get_employees_map("data/roles.txt", inverse_aliases)
# Parse the graph.txt file to get the email graph.
print "Parsing graph.txt"
(_, email_graph) = graphs.process_file("data/graph.txt", inverse_aliases)
interesting_nodes = get_interesting_nodes(email_graph, aliases)
relations = get_relations(interesting_nodes, employees_info, wiki_words)
# Write the resultant graph.
print "Writing results."
with open("graph.dot", "w") as f:
f.write('digraph G {\n')
print "%s relations" % len(relations)
for (i, relation) in enumerate(sorted(relations)):
print "%s" % i
a = relation.from_info
b = relation.to_info
# Choose the most common word in the email subjects.
c = counter.Counter()
for email in relation.emails.emails:
if email.subject is not None:
c.update(email.subject)
if len(c) > 0:
best_word = c.most_common(1)[0][0]
else:
best_word = ""
f.write('"%s" -> "%s" [label = "%s"];\n' %
(a.description(), b.description(), best_word))
f.write('}\n')
