fix nltk resources

preprocessing.py

@@ -8,10 +8,11 @@ from nltk import word_tokenize, sent_tokenize
 from nltk.corpus import stopwords
 from nltk.stem import LancasterStemmer, WordNetLemmatizer
 
-download_path = os.path.join(os.getcwd(), 'nltk_packages')
-nltk.data.path.append(download_path)
-nltk.download('wordnet', download_dir=download_path)
-nltk.download('stopwords', download_dir=download_path)
+# download_path = os.path.join(os.getcwd(), 'nltk_packages')
+# nltk.data.path.append(download_path)
+nltk.download('wordnet')
+nltk.download('stopwords')
+nltk.download('punkt')
 
 def remove_non_ascii(words):
     """Remove non-ASCII characters from list of tokenized words"""