41 lines
1.1 KiB
Python
41 lines
1.1 KiB
Python
import pandas as pd
|
|
import datetime
|
|
|
|
from utils.documents_to_database import documents_to_database
|
|
|
|
# In[ ]:
|
|
linkedin_data_path = "data/LinkedIn/comments/Comments-FIX.csv"
|
|
|
|
# In[ ]:
|
|
raw_comments_csv = pd.read_csv(linkedin_data_path, encoding='utf-8')
|
|
raw_comments = raw_comments_csv[(raw_comments_csv['MessageFix'] != "")].drop_duplicates()
|
|
|
|
# In[ ]:
|
|
raw_comments['index'] = "rs_linkedin_comments"
|
|
raw_comments['type'] = "comments"
|
|
raw_comments['network'] = "LinkedIn"
|
|
raw_comments['chemin'] = linkedin_data_path
|
|
|
|
# In[ ]:
|
|
raw_comments["datepublication"] = raw_comments["Date"].apply(
|
|
lambda x: str(datetime.datetime.fromisoformat(str(x)).isoformat()))
|
|
del raw_comments["Date"]
|
|
|
|
# In[ ]:
|
|
raw_comments.rename(columns={"Link": "uri", "MessageFix": "texte"}, inplace=True)
|
|
|
|
# In[ ]:
|
|
raw_comments["chemin"] = linkedin_data_path
|
|
|
|
# In[ ]:
|
|
raw_comments.fillna(value="", inplace=True)
|
|
|
|
# In[ ]:
|
|
raw_comments.drop_duplicates(subset=['texte', 'datepublication'], inplace=True)
|
|
|
|
# In[ ]:
|
|
# Filter empty texte
|
|
raw_comments = raw_comments[~raw_comments['texte'].str.strip('\n').str.strip().eq('')]
|
|
|
|
# In[ ]:
|
|
documents_to_database(raw_comments)
|