Very informative, thank you.

It's a function specific to the site notebook, it allows you to load a dataset inside the script, you can see it as an on site Jupyter Notebook

import sys

def main():

namez = '{}'.format(sys.argv[1])

with open(namez, 'r') as file_object:

textoun = ""

for line in file_object:

textoun += line # populate a long string

cle = ''

for n in textoun:

if n not in ['.', '"', '_', '`', '=', '+', '(', ')', '/', '{', '}', ';', ':', ']', '[', ',', '!', '?', '|', '<', '>', '*']:

cle += n.lower() #filter out the non words