8-1.텍스트 전처리

Text Tokenization

문장 토큰화

from nltk import sent_tokenize
text_sample = 'The Matrix is everywhere its all around us, here even in this room.  \
              You can see it out your window or on your television. \
               You feel it when you go to work, or go to church or pay your taxes.'
sentences = sent_tokenize(text=text_sample)
print(type(sentences),len(sentences))
print(sentences)



<class 'list'> 3
['The Matrix is everywhere its all around us, here even in this room.', 'You can see it out your window or on your television.', 'You feel it when you go to work, or go to church or pay your taxes.']

 

단어 토큰화

from nltk import word_tokenize

sentence = "The Matrix is everywhere its all around us, here even in this room."
words = word_tokenize(sentence)
print(type(words), len(words))
print(words)



<class 'list'> 15
['The', 'Matrix', 'is', 'everywhere', 'its', 'all', 'around', 'us', ',', 'here', 'even', 'in', 'this', 'room', '.']

 

여러 문장들에 대한 단어 토큰화

from nltk import word_tokenize, sent_tokenize

#여러개의 문장으로 된 입력 데이터를 문장별로 단어 토큰화 만드는 함수 생성
def tokenize_text(text):
    
    # 문장별로 분리 토큰
    sentences = sent_tokenize(text)
    # 분리된 문장별 단어 토큰화
    word_tokens = [word_tokenize(sentence) for sentence in sentences]
    return word_tokens

#여러 문장들에 대해 문장별 단어 토큰화 수행. 
word_tokens = tokenize_text(text_sample)
print(type(word_tokens),len(word_tokens))
print(word_tokens)



<class 'list'> 3
[['The', 'Matrix', 'is', 'everywhere', 'its', 'all', 'around', 'us', ',', 'here', 'even', 'in', 'this', 'room', '.'], ['You', 'can', 'see', 'it', 'out', 'your', 'window', 'or', 'on', 'your', 'television', '.'], ['You', 'feel', 'it', 'when', 'you', 'go', 'to', 'work', ',', 'or', 'go', 'to', 'church', 'or', 'pay', 'your', 'taxes', '.']]

 

n-gram

from nltk import ngrams

sentence = "The Matrix is everywhere its all around us, here even in this room."
words = word_tokenize(sentence)

all_ngrams = ngrams(words, 2)
ngrams = [ngram for ngram in all_ngrams]
print(ngrams)



[('The', 'Matrix'), ('Matrix', 'is'), ('is', 'everywhere'), ('everywhere', 'its'), ('its', 'all'), ('all', 'around'), ('around', 'us'), ('us', ','), (',', 'here'), ('here', 'even'), ('even', 'in'), ('in', 'this'), ('this', 'room'), ('room', '.')]

 

Stopwords 제거

import nltk
nltk.download('stopwords')


[nltk_data] Downloading package stopwords to
[nltk_data]     C:\Users\KwonChulmin\AppData\Roaming\nltk_data...
[nltk_data]   Unzipping corpora\stopwords.zip.
True

 

print('영어 stop words 갯수:',len(nltk.corpus.stopwords.words('english')))
print(nltk.corpus.stopwords.words('english')[:40])



영어 stop words 갯수: 179
['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've", "you'll", "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', "she's", 'her', 'hers', 'herself', 'it', "it's", 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this']

 

import nltk

stopwords = nltk.corpus.stopwords.words('english')
all_tokens = []
# 위 예제의 3개의 문장별로 얻은 word_tokens list 에 대해 stop word 제거 Loop
for sentence in word_tokens:
    filtered_words=[]
    # 개별 문장별로 tokenize된 sentence list에 대해 stop word 제거 Loop
    for word in sentence:
        #소문자로 모두 변환합니다. 
        word = word.lower()
        # tokenize 된 개별 word가 stop words 들의 단어에 포함되지 않으면 word_tokens에 추가
        if word not in stopwords:
            filtered_words.append(word)
    all_tokens.append(filtered_words)
    
print(all_tokens)


[['matrix', 'everywhere', 'around', 'us', ',', 'even', 'room', '.'], ['see', 'window', 'television', '.'], ['feel', 'go', 'work', ',', 'go', 'church', 'pay', 'taxes', '.']]

 

Stemming과 Lemmatization

from nltk.stem import LancasterStemmer
stemmer = LancasterStemmer()

print(stemmer.stem('working'),stemmer.stem('works'),stemmer.stem('worked'))
print(stemmer.stem('amusing'),stemmer.stem('amuses'),stemmer.stem('amused'))
print(stemmer.stem('happier'),stemmer.stem('happiest'))
print(stemmer.stem('fancier'),stemmer.stem('fanciest'))



work work work
amus amus amus
happy happiest
fant fanciest

 

from nltk.stem import WordNetLemmatizer

lemma = WordNetLemmatizer()
print(lemma.lemmatize('amusing','v'),lemma.lemmatize('amuses','v'),lemma.lemmatize('amused','v'))
print(lemma.lemmatize('happier','a'),lemma.lemmatize('happiest','a'))
print(lemma.lemmatize('fancier','a'),lemma.lemmatize('fanciest','a'))



amuse amuse amuse
happy happy
fancy fancy