Update preprocessor.py

preprocessor.py

@@ -1,15 +1,20 @@
 import re
 import pandas as pd
 
-def preprocess(data):
-    pattern = r'\d{1,2}/\d{1,2}/\d{2,4},\s\d{1,2}:\d{2}-\s'  # Capture date and time in separate groups
-    messages_and_dates = re.findall(pattern, data)
-
-    messages = [message_group[0] for message_group in messages_and_dates]
-    dates = [message_group[1] or "NA" for message_group in messages_and_dates]  # Assign "NA" for empty strings
-
-    df = pd.DataFrame({'user_message': messages, 'date': pd.to_datetime(dates, format='%d/%m/%Y, %H:%M - ')})
+import dateutil.parser
 
+def preprocess(data):
+    messages = []
+    dates = []
+    for line in data.splitlines():  # Assuming data is line-based
+        try:
+            date_obj = dateutil.parser.parse(line.split(',')[0])  # Assuming date is in first part
+            messages.append(line.split(',')[1])  # Assuming message is in second part
+            dates.append(date_obj.strftime("%d/%m/%Y %H:%M"))  # Format as desired
+        except (ValueError, IndexError):
+            pass  # Handle parsing errors or missing data silently (optional)
+    df = pd.DataFrame({'user_message': messages, 'date': dates})
+    
     users = []
     messages = []
     for message in df['user_message']: