mgaughan/mw-convo-collections
1
0
Fork 0
Code

updated cleaning/re-do for more characteristics

Browse Source
This commit is contained in:
Matthew Gaughan 2025-06-03 16:31:05 -05:00
parent 228a6b07ae
commit 2fd205a7bb
5 changed files with 3334187 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

192743
data_cleaning/060325_c1_ve_phab_comments.csv Normal file
View File

File diff suppressed because one or more lines are too long

917976
data_cleaning/060325_c2_https_phab_comments.csv Normal file
View File

File diff suppressed because one or more lines are too long

2201576
data_cleaning/060325_c3_http_phab_comments.csv Normal file
View File

File diff suppressed because one or more lines are too long

21915
data_cleaning/cleaning_phabricator.ipynb
View File

File diff suppressed because one or more lines are too long

18
data_collection/phab_get.py
View File

@ -165,10 +165,23 @@ def query_users(
after = cursor['after'] after = cursor['after']
return data return data
def query_task_id(
task_phid,
api_url_base = 'https://phabricator.wikimedia.org/api/user.search',
api_token = 'api-b7lr4rr2yo5kjyxwmkxqbsbelhyf',
sleep = 13,
limit = 100):
time.sleep(sleep)
to_query = 1
after = None
data = []
while to_query == 1:
if __name__ == "__main__": if __name__ == "__main__":
'''
# phab=Phabricator("https://phabricator.wikimedia.org/") # phab=Phabricator("https://phabricator.wikimedia.org/")
tags = [ tags = [
"http" "http"
@ -194,8 +207,9 @@ if __name__ == "__main__":
DATA_PREFIX = "/data/users/mgaughan/mw-repo-lifecycles/phab_data/" DATA_PREFIX = "/data/users/mgaughan/mw-repo-lifecycles/phab_data/"
with open(f"{DATA_PREFIX}{tag}_10-21-2013_12-5-2013_phab_data.json", "w") as outfile1: with open(f"{DATA_PREFIX}{tag}_10-21-2013_12-5-2013_phab_data.json", "w") as outfile1:
json.dump(p_data, outfile1) json.dump(p_data, outfile1)
'''
user = query_users() user = query_users()
with open(f"022825_wmf_master_phab_roster.json", "w") as outfile1: with open(f"022825_wmf_master_phab_roster.json", "w") as outfile1:
json.dump(user, outfile1) json.dump(user, outfile1)
''' '''