[Py3.5] Stemming words w/ NLTK

/*******************************************************************************************************************
-- Title : [Py3.5] Stemming words w/ NLTK
-- Reference : pythonprogramming.net
-- Key word : nlp nltk stemming stemmer 자연어 처리 포터 스태머 스태밍 porter stemmer stem
                  word_tokenize sent_tokenize word tokenize sent tokenize
*******************************************************************************************************************/

-- Python

from nltk.stem import PorterStemmer
from nltk.tokenize import sent_tokenize, word_tokenize
 
# -- 포터 스태머 선언
ps = PorterStemmer()
 
example_words = ["python", "pythoner", "pythoning", "pythoned", "pythonly"]
 
for w in example_words:
    print(ps.stem(w))
 
print("[1] ", "*" * 100, "\n")
 
# -- 단어 토큰에서 포터 스태머 적용
new_text = "It is important to by very pythonly while you are pythoning with python. All pythoners have pythoned poorly at least once."
 
words = word_tokenize(new_text)
 
for w in words:
    print(ps.stem(w))
 
print("[2] ", "&" * 100, "\n")
 
# -- 테스트
new_text2 = "installed packages failed: installing error occurred something."
 
words2 = word_tokenize(new_text2)
 
for w2 in words2:
    print(ps.stem(w2))
 
print("[3] ", "$" * 100, "\n")