b731f24a9f6a2f5547ebd6e642004adeacbe18da,ข้อความ/build_pythainlp.py,,,#,14

Before Change

listneg=[e.strip() for e in lines]
f.close() // ปิดไฟล์
// neutral.txt
with codecs.open("neutral.txt", "r", "utf-8") as f:
    lines = f.readlines()
listneutral=[e.strip() for e in lines]
f.close() // ปิดไฟล์
print(1)
pos1=["pos"]*len(listpos)

After Change

print(2)
training_data = list(zip(listpos,pos1)) + list(zip(listneg,neg1))
print(3)
vocabulary = set(chain(*[(set(word_tokenize(i[0]))-set(stopwords.words("thai"))) for i in training_data]))
//vocabulary = set(chain(*[x for x in a if x not in [list(set(word_tokenize(i[0]))) for i in training_data]]))
print(3.1)
feature_set = [({i:(i in word_tokenize(sentence)) for i in vocabulary},tag) for sentence, tag in training_data]

Instances