def make_vocab_files(opt, filename, ques_or_ans):
save_path = os.path.join(root_path, "vocab/%s_vocab.json" % ques_or_ans)
# load data
if (ques_or_ans == "question"):
_, sentence_ls, _ = VQADataProvider.load_raw_iqa(filename)
elif (ques_or_ans == "answer"):
_, _, sentence_ls = VQADataProvider.load_raw_iqa(filename)
else:
sentence_ls = None
vocab_dict = make_vocab(sentence_ls)
# save to json file
with open(save_path, "w") as f:
json.dump(vocab_dict, f)
print("%s-%s vocabulary saved" % (filename, ques_or_ans))
def gen_txt():
with open(q_voc_path, "r") as f:
q_dic = json.load(f)
word_list = []
exc_list = ["<break>", "<END>", "<START>", "<UNKNOWN>", "<UNK>"]
for k, _ in q_dic.items():
# exclude <break>, <END>, <START>, <UNKNOWN>
if (k not in exc_list):
word_list.append(k)
sent_list = []
_, raw_ques, _ = VQADataProvider.load_raw_iqa(q_a_i_path)
for ques in raw_ques:
sent_list.append(VQADataProvider.text_to_list(ques))
# with open(q_a_i_path, "r") as csvfile:
# # QA = csv.reader(csvfile, delimiter="\t", quotechar='\n')
# for row in QA:
# sent_list.append(data_provider.VQADataProvider.seq_to_list(row[2]))
sent_idx_list = []
for sent in sent_list:
sent_idx_list.append(
[word_list.index(x) for x in sent if x not in exc_list])
with open(wordlist_path, "w") as f:
for item in word_list:
f.write("%s\n" % item)
with open(doc_path, "w") as f:
for sent in sent_idx_list:
f.write(" ".join([str(i) for i in sent]) + "\n")
def make_ans_vocab_file(opt, filename):
save_path = os.path.join(root_path, "vocab/answer_vocab.pkl")
# loada data
_, _, sentence_ls = VQADataProvider.load_raw_iqa(filename)
vocab_ls = make_vocab_ans(sentence_ls)
with open(save_path, "wb") as f:
pickle.dump(vocab_ls, f)
#for debug
print(vocab_ls[:10])
return len(vocab_ls)
def check_ans_vocab(filename):
_, _, sentence_ls = VQADataProvider.load_raw_iqa(filename)
word_fre_dict = {}
for sent in sentence_ls:
word_ls = VQADataProvider.text_to_list(sent)
for word in word_ls:
if (word in word_fre_dict):
word_fre_dict[word] += 1
else:
word_fre_dict[word] = 1
# sort
word_fre_dict = sorted(word_fre_dict.items(),
key=lambda kv: kv[1],
reverse=True)
return word_fre_dict
