Find cloned notebooks and find most cloned

find_clones.py

# $ cat nb_names.log | sort | uniq -c | sort -nrk1 | head

import os, re

# find cloned notebooks with parens
pattern = re.compile(r"\((\d+)\)")

with open('user_workspace.log', 'r') as fp, open('nb_names.log', 'w') as fp_w:
    for x in fp:
        nb_name = os.path.basename(x.rstrip())
        m = pattern.findall(nb_name)
        if m:
            clone_num = '({0})'.format(m[0])
            clone_indx = nb_name.find(clone_num)
            clean_nb_name = nb_name[:clone_indx].rstrip()
            fp_w.write(clean_nb_name + '\n')
        else:
            fp_w.write(nb_name + '\n')