def getWords(data):
words_arr = []
for _def in data:
sentence = _def['sent']
sentence = data_helpers.preprocess_data(sentence)
words_arr += data_helpers.basic_tokenizer(sentence)
def_word = _def['def_word']
def_word = data_helpers.preprocess_data(def_word)
words_arr += [def_word]
return words_arr
def load_data_plain(data_path):
x_arr = []
y_arr = []
# sentence_id = -1
with open(data_path, 'r') as f:
lines = f.readlines()[1:]
for line in lines:
line = line.strip()
cols = line.split(' ')
# if sentence_id != cols[1]:
sent = cols[2]
sentiment = int(cols[3])
sentence_id = cols[1]
sent = data_helpers.preprocess_data(sent)
x_arr.append(sent)
y_arr.append(sentiment)
# else:
# continue
return x_arr, y_arr
def load_test_data_plain(data_path):
x_arr = []
phrase_arr = []
# sentence_id = -1
with open(data_path, 'r') as f:
lines = f.readlines()[1:]
for index, line in enumerate(lines):
line = line.strip()
cols = line.split(' ')
# if sentence_id != cols[1]:
# print(line)
# print(cols)
# print(index)
# print()
if len(cols) == 3:
sent = cols[2]
else:
sent = ""
sentence_id = cols[1]
phrase_id = cols[0]
sent = data_helpers.preprocess_data(sent)
x_arr.append(sent)
phrase_arr.append(phrase_id)
# else:
# continue
return x_arr, phrase_arr
