카테고리 없음

워드 클라우드

오기오기 2021. 9. 8. 00:45
728x90
반응형
# 워드 클라우드 생성을 도와주는 패키지를 가져옵니다.
try:
    from wordcloud import WordCloud, STOPWORDS
except:
    !pip install wordcloud
    from wordcloud import WordCloud, STOPWORDS

 

# 문법적인 성분들을 배제하기 위해 stopwords들을 따로 저장해둡니다.
set(STOPWORDS)

{'a', 'about', 'above', 'after', 'again', 'against', 'all', 'also', 'am', 'an', 'and', 'any', 'are', "aren't", 'as', 'at', 'be', 'because', 'been', 'before', 'being', 'below', 'between', 'both', 'but', 'by', 'can', "can't", 'cannot', 'com', 'could', "couldn't", 'did', "didn't", 'do', 'does', "doesn't", 'doing', "don't", 'down', 'during', 'each', 'else', 'ever', 'few', 'for', 'from', 'further', 'get', 'had', "hadn't", 'has', "hasn't", 'have', "haven't", 'having', 'he', "he'd", "he'll", "he's", 'hence', 'her', 'here', "here's", 'hers', 'herself', 'him', 'himself', 'his', 'how', "how's", 'however', 'http', 'i', "i'd", "i'll", "i'm", "i've", 'if', 'in', 'into', 'is', "isn't", 'it', "it's", 'its', 'itself', 'just', 'k', "let's", 'like', 'me', 'more', 'most', "mustn't", 'my', 'myself', 'no', 'nor', 'not', 'of', 'off', 'on', 'once', 'only', 'or', 'other', 'otherwise', 'ought', 'our', 'ours', 'ourselves', 'out', 'over', 'own', 'r', 'same', 'shall', "shan't", 'she', "she'd", "she'll", "she's", 'should', "shouldn't", 'since', 'so', 'some', 'such', 'than', 'that', "that's", 'the', 'their', 'theirs', 'them', 'themselves', 'then', 'there', "there's", 'therefore', 'these', 'they', "they'd", "they'll", "they're", "they've", 'this', 'those', 'through', 'to', 'too', 'under', 'until', 'up', 'very', 'was', "wasn't", 'we', "we'd", "we'll", "we're", "we've", 'were', "weren't", 'what', "what's", 'when', "when's", 'where', "where's", 'which', 'while', 'who', "who's", 'whom', 'why', "why's", 'with', "won't", 'would', "wouldn't", 'www', 'you', "you'd", "you'll", "you're", "you've", 'your', 'yours', 'yourself', 'yourselves'}

 

# 해당하는 열의 값들을 중복 제거한 뒤 모두 이어붙여서 text라는 문자열로 저장합니다.
text = ""

for c in df.cause.drop_duplicates():
    text += c

text[:100]

 

wc1 = WordCloud(max_font_size=200, stopwords=spwords, background_color='white', width=800, height=800)
wc1.generate(text)

plt.figure(figsize=(10, 8))
plt.imshow(wc1)
plt.tight_layout(pad=0)
plt.axis('off')
plt.show()

728x90
반응형