def process_question(question: str, nlp_toolkit: NLPToolkit) -> QPResult:
# start logging
Logger.info('started')
start = datetime.now()
# start question processing
clf_name = get_clf_name(question)
clf = get_clf_from_disk(clf_name)
label = get_predicted_label(question, clf)
keywords = nlp_toolkit.get_headwords(question)
# keywords = get_key_words(question)
# print(keywords)
# print(AnswerType[label.upper()])
# end logging
end = datetime.now()
diff = end - start
Logger.info('AnswerType: ' + str(AnswerType[label]))
Logger.info('finished (' + str(diff.seconds) + '.' +
str(diff.microseconds)[0:2] + ' s)')
Logger.small_seperator()
return QPResult(QuestionModel(keywords, question), AnswerType[label])
Logger.error('Dataset: ' + title)
for paragraph in dataset['paragraphs'][:5]:
for question_answer_set in paragraph['qas']:
Logger.error(
'####################################################')
Logger.error('Question ' + str(question_counter))
Logger.error('')
question_counter += 1
question = question_answer_set['question']
correct_answers = question_answer_set['answers']
Logger.error(question)
# answer = process_answer_question(question)
keywords = nlp.get_headwords(question)
Logger.error('Headwords: ' + ', '.join(keywords))
keywords.append(title_ext)
qm = QuestionModel(keywords, question)
# error("Keywords: " + ', '.join(keywords))
docs = receive_docs(qm, nlp)
Logger.error("Correct Doc: " + title_ext)
found = False
for idx, doc in enumerate(docs.docs[:5]):
if doc.title in title_ext:
correct_answer_dict[idx] += 1
found = True
break
if not found: