def create_pagerank_features():
"""
We create a dataframe with some features extracted from the PageRank
algorithm
:return: pandas dataframe for train and test set
"""
# Load dataset
df_train, df_test = load_dataset()
def generate_qid_graph_table(row):
"""
Generating a graph of questions and their neighbors.
Appending nodes to the graph directly
:param row: dataframe row
"""
hash_key1 = hashlib.md5(row["question1"].encode('utf-8')).hexdigest()
hash_key2 = hashlib.md5(row["question2"].encode('utf-8')).hexdigest()
qid_graph.setdefault(hash_key1, []).append(hash_key2)
qid_graph.setdefault(hash_key2, []).append(hash_key1)
qid_graph = {}
_ = df_train.apply(generate_qid_graph_table, axis=1)
_ = df_test.apply(generate_qid_graph_table, axis=1)
pagerank_dict = get_pagerank(qid_graph)
X_train = df_train.apply(lambda x: get_pagerank_value(x, pagerank_dict),
axis=1)
# Empty garbage collector
del df_train
gc.collect()
X_test = df_test.apply(lambda x: get_pagerank_value(x, pagerank_dict),
axis=1)
return X_train, X_test
def process_item(self, item, spider):
if not isinstance(item, TaseItem):
return item
if item['url']:
rank = pagerank.get_pagerank(item['url'])
try:
pagerank = float(rank)
self.cur.execute(\
"insert into pagerank (sessionid, date_, symbol, pagerank) "
"values (%s, %s, %s, %s)",
(
global_time,
global_date.isoformat(),
item['symbol'],
pagerank
)
)
except ValueError:
pass
except MySQLdb.IntegrityError, e:
#print 'SQL integrity error: %s' % e
log.msg('SQL integrity error: %s' % e)
def execute_lookup(key):
rank = pagerank.get_pagerank(key)
if rank is None:
logger.debug('Error looking up pagerank for %s'%(key))
return ''
return rank
#!/usr/bin/env python
# Thanks to Corey Goldberg (http://code.google.com/p/corey-projects/) for his work on pagerank.py
import pagerank
sourceFile = open ('urlList.txt', 'r')
listDump = open ('PRdump.txt', 'w')
for line in sourceFile:
rank = pagerank.get_pagerank(line)
print >>listDump, rank, "\n",
#!/usr/bin/python
# -*- coding: utf-8 -*-
import pagerank
print pagerank.get_pagerank("http://www.fsf.org")
def printSortedPageRankList( pages ):
for page in sorted(pages ):
url = pages_dict[page]
rank = pagerank.get_pagerank(url)
print page + "'s pagerank is: " + rank
def get_pageranks(urls=list()):
prs = {}
for url in urls:
print "Processing url: %s" % url
prs[url] = pagerank.get_pagerank(url)
return prs
#!/usr/bin/env python
import pagerank
rank = pagerank.get_pagerank('http://www.google.com')
print 'google:', rank
print "baidu:", pagerank.get_pagerank('http://www.baidu.com')
print pagerank.get_pagerank('http://www.csdn.net')
print pagerank.get_pagerank('http://www.codeproject.com')
import csv
import pprint
import pagerank
f = csv.writer(open('articles_pr_2.csv', 'wb'))
for item in csv.reader(open('articles.csv')):
rank = pagerank.get_pagerank(item[1])
item.append(rank)
f.writerow(item)
print item
#!/usr/bin/env python
import pagerank
rank = pagerank.get_pagerank('http://www.google.com')
print 'google:',rank
print "baidu:", pagerank.get_pagerank('http://www.baidu.com')
print pagerank.get_pagerank('http://www.csdn.net')
print pagerank.get_pagerank('http://www.codeproject.com')
