#!/usr/local/bin/python
# -*- coding: utf-8 -*-
import ast
import preprocess.sentence as sentence
import question_item as question_item
import choices.word_item as word_item
import choices.wordnet.wn_thai as wordnet_thai
import choices.choice_generator as choice_gen
_cg = choice_gen.choice_generator()
def find_blank_index(word_list, text):
for i in range(len(word_list)):
word = word_list[i]
if word == text[0:len(word)]:
text = text[len(word):]
else:
return i
else:
return None
def get_question_item(question_file, pos_file):
sentences = []
sentence_with_pos = []
with open(pos_file) as f:
for line in f:
read_list = ast.literal_eval(line.strip())
for a_sentence in read_list:
sentences.append("".join([word for (word, _) in a_sentence]))
sentence_with_pos.append(a_sentence)
# initialize - train model
all_questions = []
with open("ranking/test-globalwarming.out", "r") as f:
for line in f:
a_question_item = _qui.question_item(from_str=line.strip())
all_questions.append(a_question_item)
# print_sentence_cut_results(all_questions)
_ev.read_eval_file("ranking/evaluation/sheet1.csv", all_questions)
_ev.read_eval_file("ranking/evaluation/sheet2.csv", all_questions)
_ev.read_eval_file("ranking/evaluation/sheet3.csv", all_questions)
qr = qrank.question_ranker(question_set=all_questions)
# qr.test_kfolds(all_questions)
choice_rank = chrank.choice_ranker(training_set=all_questions, wordnet=wnth)
chg = _chg.choice_generator(wnth, choice_rank)
# ranked_question, ranked_scores = qr.rank_question(generated_questions)
args = sys.argv
custom_dict = dict()
if len(args) >= 2:
if len(args) >= 3:
custom_dict = read_custom_dict(args[2])
ss.set_custom_dict(custom_dict)
wnth.set_custom_dict(custom_dict)
generated_questions = main_process(args[1])
display.display(generated_questions, percent=100)
# f = open("bank-choice2.dict", "w")
# for question in generated_questions:
# ranked_choices, choice_with_scores = choice_rank.rank_choices(question)
