Update data_processor.py

data_processor.py

@@ -55,22 +55,48 @@ class DataProcessor:
             print(f"Error converting series to datetime: {e}")
             return series
 
+    # def replace_student_names_with_initials(self, df):
+    #     updated_columns = []
+    #     for col in df.columns:
+    #         if col.startswith('Student Attendance'):
+    #             match = re.match(r'Student Attendance \[(.+?)\]', col)
+    #             if match:
+    #                 name = match.group(1)
+    #                 initials = ''.join([part[0] for part in name.split()])
+    #                 updated_columns.append(f'Student Attendance [{initials}]')
+    #             else:
+    #                 updated_columns.append(col)
+    #         else:
+    #             updated_columns.append(col)
+    #     df.columns = updated_columns
+    #     return df
+
     def replace_student_names_with_initials(self, df):
         updated_columns = []
         for col in df.columns:
-            if col.startswith('Student Attendance'):
-                match = re.match(r'Student Attendance \[(.+?)\]', col)
+            if 'Student Attendance' in col:
+                # Search for the last occurrence of text within square brackets at the end of the string
+                match = re.search(r'\[(.+?)\]$', col)
+                if not match:
+                    # Handle cases where the closing bracket might be missing
+                    match = re.search(r'\[(.+)$', col)
                 if match:
-                    name = match.group(1)
-                    initials = ''.join([part[0] for part in name.split()])
-                    updated_columns.append(f'Student Attendance [{initials}]')
+                    name = match.group(1).strip()
+                    # Remove any trailing closing bracket if it wasn't matched earlier
+                    name = name.rstrip(']')
+                    # Get initials
+                    initials = ''.join([part[0] for part in name.strip().split()])
+                    updated_col = f'Student Attendance [{initials}]'
+                    updated_columns.append(updated_col)
                 else:
+                    # If no match is found, keep the column name as is
                     updated_columns.append(col)
             else:
                 updated_columns.append(col)
         df.columns = updated_columns
         return df
 
+
     def find_intervention_column(self, df):
         for column in self.INTERVENTION_COLUMN_OPTIONS:
             if column in df.columns: