def parse_paperauthors(self):
# Update all journal/conference/coauthor information
print "Parsing PaperAuthors..."
f = open(data_io.get_paths()["paperauthor_processed_path"], "r")
titles = f.readline()
count = 0
for l in f:
count += 1
if count % 100000 == 0:
print count
res = l.strip().split(",")
if not res[0].isdigit():
continue
paper_id = int(res[0])
author_id = int(res[1])
raw_author_name = unidecode.unidecode(
unicode(res[2], encoding="utf-8"))
author_name = nlp.filter_title(raw_author_name)[0]
raw_author_affiliation = unidecode.unidecode(
unicode(res[3], encoding="utf-8"))
author_affiliation = nlp.filter_affiliation(raw_author_affiliation)
curr_paper = self.papers.get(paper_id)
curr_author = self.authors.get(author_id)
self.update_paperauthor(curr_paper, curr_author, author_id,
author_name, author_affiliation)
print "Done"
f.close()
def parse_authors(self):
# Create authors
print "Parsing Authors..."
f = open(data_io.get_paths()["author_processed_path"], "r")
titles = f.readline()
for l in f.readlines():
res = l.strip().split(",")
# Titles
raw_title = unidecode.unidecode(unicode(res[1], encoding="utf-8"))
(name, surname) = nlp.filter_title(raw_title)
try:
self.surnames[surname] = self.surnames[surname] + 1
except:
self.surnames[surname] = 1
#Affiliations
raw_affiliation = unidecode.unidecode(unicode(res[2], encoding="utf-8"))
affiliation = nlp.filter_affiliation(raw_affiliation)
try:
self.affiliations[affiliation] = self.affiliations[affiliation] + 1
except:
self.affiliations[affiliation] = 1
self.authors[int(res[0])] = author.Author(int(res[0]), name, surname, affiliation)
print "Done"
f.close()
def parse_authors(self):
# Create authors
print "Parsing Authors..."
f = open(data_io.get_paths()["author_processed_path"], "r")
titles = f.readline()
for l in f.readlines():
res = l.strip().split(",")
# Titles
raw_title = unidecode.unidecode(unicode(res[1], encoding="utf-8"))
(name, surname) = nlp.filter_title(raw_title)
try:
self.surnames[surname] = self.surnames[surname] + 1
except:
self.surnames[surname] = 1
#Affiliations
raw_affiliation = unidecode.unidecode(
unicode(res[2], encoding="utf-8"))
affiliation = nlp.filter_affiliation(raw_affiliation)
try:
self.affiliations[
affiliation] = self.affiliations[affiliation] + 1
except:
self.affiliations[affiliation] = 1
self.authors[int(res[0])] = author.Author(int(res[0]), name,
surname, affiliation)
print "Done"
f.close()
def parse_paperauthors(self):
# Update all journal/conference/coauthor information
print "Parsing PaperAuthors..."
f = open(data_io.get_paths()["paperauthor_processed_path"], "r")
titles = f.readline()
count = 0
for l in f:
count += 1
if count % 100000 == 0:
print count
res = l.strip().split(",")
if not res[0].isdigit():
continue
paper_id = int(res[0])
author_id = int(res[1])
raw_author_name = unidecode.unidecode(unicode(res[2], encoding="utf-8"))
author_name = nlp.filter_title(raw_author_name)[0]
raw_author_affiliation = unidecode.unidecode(unicode(res[3], encoding="utf-8"))
author_affiliation = nlp.filter_affiliation(raw_author_affiliation)
curr_paper = self.papers.get(paper_id)
curr_author = self.authors.get(author_id)
self.update_paperauthor(curr_paper, curr_author, author_id, author_name, author_affiliation)
print "Done"
f.close()
