Created
February 28, 2019 15:11
-
-
Save quanon/96c44080be280ab9b031c8b878d50057 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import MeCab as mc | |
from matplotlib import pyplot as plt | |
from wordcloud import WordCloud | |
def mecab_analysis(text): | |
t = mc.Tagger('-Ochasen -d /usr/local/lib/mecab/dic/mecab-ipadic-neologd/') | |
t.parse('') | |
node = t.parseToNode(text) | |
output = [] | |
while node: | |
word_type = node.feature.split(',')[0] | |
if word_type in ['形容詞', '動詞','名詞', '副詞']: | |
output.append(node.feature.split(',')[6]) | |
node = node.next | |
if node is None: | |
break | |
return output | |
def create_wordcloud(words): | |
font_path = '/Users/quanon/Library/Fonts/RictyDiminished-Regular.ttf' | |
stopwords = ['てる', 'いる', 'なる', 'れる', 'する', 'ある', 'こと', 'これ', 'さん', 'して', | |
'くれる', 'やる', 'くださる', 'そう', 'せる', 'した', '思う', | |
'それ', 'ここ', 'ちゃん', 'くん', '', 'て','に','を','は','の', 'が', 'と', 'た', 'し', 'で', | |
'ない', 'も', 'な', 'い', 'か', 'ので', 'よう', ''] | |
wordcloud = WordCloud(background_color='white', font_path=font_path, | |
width=900, height=500, stopwords=stopwords).generate(' '.join(words)) | |
plt.figure(figsize=(15, 12)) | |
plt.imshow(wordcloud) | |
plt.axis('off') | |
plt.show() | |
if __name__ == '__main__': | |
with open('flamingo.txt') as f: | |
text = f.read() | |
words = mecab_analysis(text.replace('\n','').replace('\u3000','')) | |
print(words) | |
create_wordcloud(words) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment