kBAD_ANSWERS = ["", "red river", "the", "figaro", "normal", "s", "p"]
if __name__ == "__main__":
args = argparse.ArgumentParser('Interactive assign pages to questions')
args.add_argument('--database', type=str, default='data/questions.db',
help='sqlite3 database of questions')
args.add_argument('--titles', type=str, default='data/wiki_index.pkl',
help='page title candiates')
args.add_argument('--labels', type=str, default='data/map/ans_to_wiki',
help='write page assignment answers')
args = args.parse_args()
# Open up the database
d = QuestionDatabase(args.database)
page_diversity = d.answer_map(normalize)
# Set up the active learner for writing assignments
al = ActiveLearner(None, args.labels)
existing_labels = set(x[0] for x in al.human_labeled())
# get the candidates we want to assign to pages
answers = d.unmatched_answers(existing_labels)
print(answers.keys()[:10])
# Open up the title finder
tf = TitleFinder(open(args.titles))
for ans, count in sorted(answers.items(), key=lambda x: sum(x[1].values()),
reverse=True):
if ans in kBAD_ANSWERS:
title, rest = rest.split('"', 1)
self.topics[int(id)] = title
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(description='Import questions')
parser.add_argument('--naqt_path', type=str)
parser.add_argument('--db', type=str, default='data/questions.db')
flags = parser.parse_args()
qdb = QuestionDatabase(flags.db)
conn = qdb._conn
answer_map = qdb.answer_map()
# Find existing naqt questions
c = conn.cursor()
command = 'SELECT naqt FROM questions WHERE naqt >= 0;'
c.execute(command)
existing = set(int(x[0]) for x in c)
num_skipped = 0
last_id = kNAQT_START
if flags.naqt_path:
for qq in naqt_reader(flags.naqt_path):
if qq.answer in answer_map and len(answer_map[qq.answer]) == 1:
page = answer_map[qq.answer].keys()[0]
else:
page = ""
title, rest = rest.split('"', 1)
self.topics[int(id)] = title
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(description='Import questions')
parser.add_argument('--naqt_path', type=str)
parser.add_argument('--db', type=str, default='data/questions.db')
flags = parser.parse_args()
qdb = QuestionDatabase(flags.db)
conn = qdb._conn
answer_map = qdb.answer_map()
# Find existing naqt questions
c = conn.cursor()
command = 'SELECT naqt FROM questions WHERE naqt >= 0;'
c.execute(command)
existing = set(int(x[0]) for x in c)
num_skipped = 0
last_id = kNAQT_START
if flags.naqt_path:
for qq in naqt_reader(flags.naqt_path):
if qq.answer in answer_map and len(answer_map[qq.answer]) == 1:
page = answer_map[qq.answer].keys()[0]
else:
page = ""
type=str,
default='data/questions.db',
help='sqlite3 database of questions')
args.add_argument('--titles',
type=str,
default='data/wiki_index.pkl',
help='page title candiates')
args.add_argument('--labels',
type=str,
default='data/map/ans_to_wiki',
help='write page assignment answers')
args = args.parse_args()
# Open up the database
d = QuestionDatabase(args.database)
page_diversity = d.answer_map(normalize)
# Set up the active learner for writing assignments
al = ActiveLearner(None, args.labels)
existing_labels = set(x[0] for x in al.human_labeled())
# get the candidates we want to assign to pages
answers = d.unmatched_answers(existing_labels)
print(answers.keys()[:10])
# Open up the title finder
tf = TitleFinder(open(args.titles))
for ans, count in sorted(answers.items(),
key=lambda x: sum(x[1].values()),
reverse=True):