mirror of
http://git.nowherejezfoltodf4jiyl6r56jnzintap5vyjlia7fkirfsnfizflqd.onion/nihilist/darknet-lantern.git
synced 2025-07-02 11:56:40 +00:00
fiex 4 and 10, sorting csv's now and making sure the origin of duplication is always local instance if compared
This commit is contained in:
parent
50f6a637cd
commit
d78ed2bc86
5 changed files with 43 additions and 15 deletions
|
@ -69,6 +69,8 @@ def clean_csv(df, blacklist):
|
|||
|
||||
try:
|
||||
if not df.empty:
|
||||
df = utils.sort_instances(df, 'Instance', conf.LOCAL_INSTANCE)
|
||||
|
||||
df = utils.remove_duplications(df)
|
||||
|
||||
df = df[~df.apply(lambda row: any(word in str(value) for word in blacklist for value in row), axis=1)]
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue