And this one too

This commit is contained in:
Crista Lopes
2014-03-14 10:34:01 -07:00
parent b5b606cbbd
commit ccbd13c268
12 changed files with 0 additions and 0 deletions

View File

@@ -0,0 +1,14 @@
import sys, re, string
def extract_words(path_to_file):
with open(path_to_file) as f:
str_data = f.read()
pattern = re.compile('[\W_]+')
word_list = pattern.sub(' ', str_data).lower().split()
with open('../stop_words.txt') as f:
stop_words = f.read().split(',')
stop_words.extend(list(string.ascii_lowercase))
return [w for w in word_list if not w in stop_words]