def get_guitars(text_file, guitar_filename=None):
""" Module to find the most popular words from a text file"""
text_data = open(text_file, "r")
# Finding all the occurances of 'guitar' and its preceiding words
guitars = re.findall(r"\w+ guitar", text_data.read().lower())
guitars_no_duplication = set(guitars)
if guitar_filename:
guitar_file = open(guitar_filename, "w")
stop_words = get_stopwords()
_digits = re.compile("\d")
count = 0
for guitar in guitars_no_duplication:
# Ignore if the word preceiding guitar is a stop_word
guitar_type = guitar.split()[0]
if guitar_type in stop_words:
continue
if guitar_type in IGNORE_WORDS:
continue
# Ignore if the preceiding word has digits
if bool(_digits.search(guitar_type)):
continue
if guitar_filename:
guitar_file.write(guitar + "\n")
count += 1
print guitar
print "The total number of types of guitars are %d" % (count)
def store_stop_words(data_file):
""" Acquiring stop words from deals data"""
stop_words_list = get_stopwords()
data = open(data_file,'r')
data_read = data.readlines()
x2 = set()
for line in data_read:
for word in line.split():
if word in stop_words_list:
x2.add(word)
data.close()
print "writing"
output = open(STORE_WORDS_FILE,'w')
for elm in x2:
output.write( elm + '\n')
output.close()