val['Riviews'] = val['Riviews'].str.replace("[^--가-히---he-he-he-he-")
val['Riviews'].replace('', np.nan, inplace=True)
val.head()
from konlpy.tag import Okt
okt = Okt()
I have to extract the disused term from here, and the review in the df is Riviews, but I want to find the disused term in here and remove it.
train['tokenized'] = train['Riviews'].apply(okt.morphs)
train['tokenized'] = train['tokenized'].apply(lambda x: [item for item in x if item not in stopwords])
I don't think we can extract terms from the data. I think I just have a survey that I already know, a pronoun that comes out too often, and so on. In the previous question, stop_words are just hardcoded. If there's any additional non-intercepts in the data, add them back and... It looks like this.
596 GDB gets version error when attempting to debug with the Presense SDK (IDE)
566 rails db:create error: Could not find mysql2-0.5.4 in any of the sources
603 Uncaught (inpromise) Error on Electron: An object could not be cloned
884 When building Fast API+Uvicorn environment with PyInstaller, console=False results in an error
© 2024 OneMinuteCode. All rights reserved.