워드클라우드(WordCloud, Colab) – 텍스트 시각화 (한글)

!pip install konlpy
!apt-get -qq install fonts-nanum

!pip install konlpy
!apt-get -qq install fonts-nanum

from google.colab import auth
auth.authenticate_user()

import gspread
from google.auth import default
creds, _ = default()

gc = gspread.authorize(creds)

# gc.open('구글시트이름- 왼쪽상단').worksheet("구글시트 탭이름 - 아래쪽 하단")
worksheet = gc.open('WordCloud').worksheet("Comments")

# get_all_values gives a list of rows.
df = worksheet.get_all_values()
print(df)

# Convert to a DataFrame and render.
import pandas as pd

df = pd.DataFrame.from_records(df)

from google.colab import auth
auth.authenticate_user()

import gspread
from google.auth import default
creds, _ = default()

gc = gspread.authorize(creds)

# gc.open('구글시트이름- 왼쪽상단').worksheet("구글시트 탭이름 - 아래쪽 하단")
worksheet = gc.open('WordCloud').worksheet("Comments")

# get_all_values gives a list of rows.
df = worksheet.get_all_values()
print(df)

# Convert to a DataFrame and render.
import pandas as pd

df = pd.DataFrame.from_records(df)

new_header = df.iloc[0] #grab the first row for the header
df = df.iloc[1:] #take the data less the header row
df.columns = new_header #set the header row as the df header

new_header = df.iloc[0] #grab the first row for the header
df = df.iloc[1:] #take the data less the header row
df.columns = new_header #set the header row as the df header

import pandas as pd
from konlpy.tag import Okt
from collections import Counter
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import matplotlib.font_manager as fm

okt = Okt()
# 불용어(stopwords) 제거 - 한글은 아직 수동으로 불용어를 제거 한다. 
stopwords = ['만', '발', '좀', '수', '터', '제', '달', '칼', '요', '사려', '안', '소', '를', '개', '저', '왜', '나', '역', '퍼', '방', '트', '욥', '무']

# okt library 를 통해 한글 명사화 및 불용어 제거 (Stopwords)
nouns = []
for comment in df['Comments']:
   extracted_nouns = okt.nouns(comment)
   filtered_nouns = [noun for noun in extracted_nouns if noun not in stopwords]
   nouns.extend(filtered_nouns)

noun_counts = Counter(nouns)

# Wordcloud 에 사용할 한글 폰트 추가
font_path = '/usr/share/fonts/truetype/nanum/NanumMyeongjoBold.ttf'

wordcloud = WordCloud(font_path=font_path, background_color='white', colormap='Pastel1',
                     width=800, height=800, max_words=200)
wordcloud.generate_from_frequencies(noun_counts)

plt.figure(figsize=(10, 6))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.show()

import pandas as pd
from konlpy.tag import Okt
from collections import Counter
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import matplotlib.font_manager as fm

okt = Okt()
# 불용어(stopwords) 제거 - 한글은 아직 수동으로 불용어를 제거 한다. 
stopwords = ['만', '발', '좀', '수', '터', '제', '달', '칼', '요', '사려', '안', '소', '를', '개', '저', '왜', '나', '역', '퍼', '방', '트', '욥', '무']

# okt library 를 통해 한글 명사화 및 불용어 제거 (Stopwords)
nouns = []
for comment in df['Comments']:
   extracted_nouns = okt.nouns(comment)
   filtered_nouns = [noun for noun in extracted_nouns if noun not in stopwords]
   nouns.extend(filtered_nouns)

noun_counts = Counter(nouns)

# Wordcloud 에 사용할 한글 폰트 추가
font_path = '/usr/share/fonts/truetype/nanum/NanumMyeongjoBold.ttf'

wordcloud = WordCloud(font_path=font_path, background_color='white', colormap='Pastel1',
                     width=800, height=800, max_words=200)
wordcloud.generate_from_frequencies(noun_counts)

plt.figure(figsize=(10, 6))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.show()