Update data_preprocess.py

data_preprocess.py

@@ -21,6 +21,20 @@ import pipeline
 import tempfile
 import nltk
 nltk.download('punkt_tab')
+try:
+    nltk.data.find('corpora/stopwords')
+except LookupError:
+    try: 
+        nltk.download('stopwords')
+    except:
+        print("have to use our own created stopword")
+        STOPWORDS = {
+            "the","a","an","in","on","of","and","or","for","with","to","from",
+            "is","are","was","were","be","been","by","this","that","these","those",
+            "it","its","as","at","but","not","no","so","if","their","there","about",
+            "into","such","than","other","then","also","can","may","might","should"
+        }
+
 def download_excel_file(url, save_path="temp.xlsx"):
     if "view.officeapps.live.com" in url:
         parsed_url = urllib.parse.parse_qs(urllib.parse.urlparse(url).query)