Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -5,7 +5,6 @@ from sklearn.feature_extraction.text import CountVectorizer
|
|
| 5 |
from sklearn.decomposition import LatentDirichletAllocation
|
| 6 |
from konlpy.tag import Okt
|
| 7 |
import re
|
| 8 |
-
from hanspell import spell_checker
|
| 9 |
import warnings
|
| 10 |
|
| 11 |
# 경고 메시지 무시
|
|
@@ -16,8 +15,6 @@ default_stopwords = set(["있다", "없다", "것", "그", "이", "하는", "하
|
|
| 16 |
|
| 17 |
@st.cache_data
|
| 18 |
def preprocess_text(text, user_stopwords):
|
| 19 |
-
text = spell_checker.check(text).checked # 맞춤법 검사
|
| 20 |
-
|
| 21 |
okt = Okt()
|
| 22 |
text = re.sub(r'[^\w\s]', '', text) # 특수 문자 제거
|
| 23 |
nouns = okt.nouns(text) # 명사 추출
|
|
@@ -36,7 +33,7 @@ def topic_modeling(texts, n_components):
|
|
| 36 |
return topics
|
| 37 |
|
| 38 |
def generate_wordcloud(text, color):
|
| 39 |
-
wordcloud = WordCloud(width=800, height=400, background_color=color).generate(text)
|
| 40 |
fig, ax = plt.subplots(figsize=(10, 5))
|
| 41 |
ax.imshow(wordcloud, interpolation='bilinear')
|
| 42 |
ax.axis("off")
|
|
|
|
| 5 |
from sklearn.decomposition import LatentDirichletAllocation
|
| 6 |
from konlpy.tag import Okt
|
| 7 |
import re
|
|
|
|
| 8 |
import warnings
|
| 9 |
|
| 10 |
# 경고 메시지 무시
|
|
|
|
| 15 |
|
| 16 |
@st.cache_data
|
| 17 |
def preprocess_text(text, user_stopwords):
|
|
|
|
|
|
|
| 18 |
okt = Okt()
|
| 19 |
text = re.sub(r'[^\w\s]', '', text) # 특수 문자 제거
|
| 20 |
nouns = okt.nouns(text) # 명사 추출
|
|
|
|
| 33 |
return topics
|
| 34 |
|
| 35 |
def generate_wordcloud(text, color):
|
| 36 |
+
wordcloud = WordCloud(width=800, height=400, background_color=color, font_path='/usr/share/fonts/truetype/nanum/NanumGothic.ttf').generate(text)
|
| 37 |
fig, ax = plt.subplots(figsize=(10, 5))
|
| 38 |
ax.imshow(wordcloud, interpolation='bilinear')
|
| 39 |
ax.axis("off")
|