Last active
April 12, 2018 03:45
-
-
Save irfanandratama/72c4ae0963e2dafacba7c9d33691830e to your computer and use it in GitHub Desktop.
Tokenizer dengan Python
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#memisahkan berdasarkan kalimat | |
def senttoken(): #Bagi per kalimat | |
kalimat = input() #tambah .lower() untuk melakukan case folding sekaligus | |
kalimat = re.split(r'(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<![A-Z]\.)(?<=\.|\?|\!)\s', kalimat) | |
print(kalimat) | |
return kalimat |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def wordtoken(kaltoken): | |
listkalimat = kaltoken | |
listkata = [] | |
for kata in listkalimat: | |
#kata = re.findall(r'\w+|\S\w*', kata) #tokenize tanpa menghilangkan tanda baca | |
kata = re.findall(r'(?i)\b[a-z]+\b', kata) | |
#kata = re.findall(r'(?i)\b[a-z]+\b|\d+\.\d+|\d+', kata) gunakan ini untuk tf normalized | |
listkata.append(kata) | |
#print(len(listkata)) | |
print(listkata) | |
return listkata |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment