def get_important_words(self, emails, path=None):
cleaner = Cleaner()
complete_email_text = ''
for email in emails:
email_header = cleaner.delete_tags(email.header)
email_body = cleaner.delete_tags(email.body)
topic_line = re.findall(r'Topic.*\n', email_header)[0]
topic_line = topic_line[6:].strip()
complete_email_text = complete_email_text + topic_line + '\n' + email_body + '\n'
# Cleaning the text
complete_email_text = re.sub('\n', ' ', complete_email_text)
complete_email_text = re.sub('\s', ' ', complete_email_text)
complete_email_text = re.sub(' +', ' ', complete_email_text)
complete_email_text = tb(complete_email_text)
bloblist = [complete_email_text]
words = []
# Test
# print(bloblist)
for i, blob in enumerate(bloblist):
scores = {word: self.tfidf(word, blob, bloblist) for word in blob.words}
sorted_words = sorted(scores.items(), key=lambda x: x[1], reverse=True)
for word, score in sorted_words:
words.append(word)
# Delete Stop-Words
words = self.delete_stopwords(words)
if path is not None:
with open(path, 'w') as current_file:
for word in words:
current_file.write('{}\n'.format(word))
return words
