In [1]:
from bigbang.archive import Archive
from bigbang.archive import load as load_archive
import os
In [2]:
ncuc_path = "../archives/http:/lists.ncuc.org/pipermail"
path = os.path.join(ncuc_path,"ncuc-discuss.csv")
arx = load_archive(path)
In [3]:
problems = ["greg shatan","err:510","lori schulman"]
In [4]:
problematic_emails = arx.data[arx.data['From'].apply(
lambda x: len([p
for p
in problems
if p
in x.lower()]) > 0)]
In [5]:
problematic_emails.to_csv("problematic_emails.csv")
In [ ]: