Update preprocess.py

preprocess.py

@@ -7,6 +7,7 @@ def preprocess(data):
 
     pattern1 = r'\d{2}/\d{2}/\d{2}, \d{1,2}:\d{2}[ap]m -'
     pattern2 = r'\[\d{2}/\d{2}/\d{2}, \d{2}:\d{2}:\d{2}\]'
+    pattern3 = r'\d{2}/\d{2}/\d{2}, \d{1,2}:\d{2} -'
 
     # data = "30/06/21, 1:46pm - Gauri Mami turned off disappearing messages."
 
@@ -25,6 +26,12 @@ def preprocess(data):
         messages = re.split(pattern2, data)[1:]
         dates = re.findall(pattern2, data)
 
+    if re.search(pattern3, data):
+        result.append(data)
+        messages = re.split(pattern3, data)[1:]
+        dates = re.findall(pattern3, data)
+    
+
     if not result:
         result = None
 
@@ -36,33 +43,21 @@ def preprocess(data):
 
     # dates = re.findall(patt, data)
 
-    df = pd.DataFrame({'date': dates, 'message': messages})
+    df = pd.DataFrame({'date': dates, 'messageog': messages})
     
     df['date'] = df['date'].astype(str).str.replace('[', '', regex=False)
     df['date'] = df['date'].astype(str).str.replace(']', '', regex=False)
     df['date'] = df['date'].astype(str).str.replace('-', '', regex=False)
 
-
-#     group_name = df.loc[df['message'].str.contains('added you')]['message'].str.split(':').str[0]
-    # group_name = df.loc[df['message'].str.contains('added you') | df['message'].str.contains('Messages and calls are end-to-end encrypted')]['message'].str.split(':').str[0]
-
-    # group_name = group_name.values[0]
-    # group_name
-
-    # df['date'] = pd.to_datetime(df['date'], format = '%d/%m/%y, %H:%M:%S ')
     df['date'] = pd.to_datetime(df['date'])
     # df['date'][0]
     df = df[1:]
 
-    # df['sender'] = df.message.str.split(':').str[0]
-    # df['message'] = df.message.str.split(':').str[1]
+    df['messageog'] = df['messageog'].astype(str)  # Convert column to string type
+    df['messageog'] = df['messageog'].fillna('')
 
-    # df[['sender', 'message']] = df['message'].str.split(':', n=1, expand=True)
-    df['message'] = df['message'].astype(str)  # Convert column to string type
-    df[['sender', 'message']] = df['message'].str.split(':', n=1, expand=True)
+    df[['sender', 'message']] = df['messageog'].str.split(':', n=1, expand=True)
 
-
-    # df['message'] = df['message'].str.encode('utf-8')
     df = df[['date', 'sender', 'message']]
 
     df['year'] = df['date'].dt.year
@@ -84,7 +79,4 @@ def preprocess(data):
     
     df = df[['date', 'sender', 'message']]
 
-    # df = df.loc[df['sender'] != '\u202a+91\xa095456\xa017572\u202c']
-    # df = df.loc[df['sender'] != 'Haldi Mehendi -Dance prep']
-    
     return df