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:
continue
choices = list(tf.query(ans))
print("--------- (%i)" % sum(count.values()))
print(ans)
if sum(page_diversity[ans].values()) >= 5 and len(page_diversity[ans]) == 1:
page = page_diversity[ans].keys()[0]
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:
continue
choices = list(tf.query(ans))
print("--------- (%i)" % sum(count.values()))
print(ans)
if sum(page_diversity[ans].values()) >= 5 and len(
