Update data_processor.py

data_processor.py

@@ -8,6 +8,7 @@ class DataProcessor:
         'Did the intervention happen today?',
         'Did the intervention take place today?'
     ]
+    YES_RESPONSES = ['yes', 'assessment day']  # Added this line
     ENGAGED_STR = 'Engaged'
     PARTIALLY_ENGAGED_STR = 'Partially Engaged'
     NOT_ENGAGED_STR = 'Not Engaged'
@@ -55,22 +56,6 @@ 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:
@@ -112,7 +97,7 @@ class DataProcessor:
     def compute_intervention_statistics(self, df):
         intervention_column = self.get_intervention_column(df)
         total_days = len(df)
-        sessions_held = df[intervention_column].str.strip().str.lower().eq('yes').sum()
+        sessions_held = df[intervention_column].str.strip().str.lower().isin(self.YES_RESPONSES).sum()  # Modified line
         intervention_frequency = (sessions_held / total_days) * 100 if total_days > 0 else 0
         return pd.DataFrame({
             'Intervention Dosage (%)': [round(intervention_frequency, 0)],
@@ -134,7 +119,7 @@ class DataProcessor:
     
     def compute_student_metrics(self, df):
         intervention_column = self.get_intervention_column(df)
-        intervention_df = df[df[intervention_column].str.strip().str.lower() == 'yes']
+        intervention_df = df[df[intervention_column].str.strip().str.lower().isin(self.YES_RESPONSES)]  # Modified line
         intervention_sessions_held = len(intervention_df)
         student_columns = [col for col in df.columns if col.startswith('Student Attendance')]
     
@@ -151,7 +136,7 @@ class DataProcessor:
             ] else 0)
     
             sessions_attended = attendance_values.sum()
-            attendance_pct = (sessions_attended / intervention_sessions_held) * 100 if intervention_sessions_held > 0 else 0
+            attendance_pct = (sessions_attended / intervention_sessions_held * 100) if intervention_sessions_held > 0 else 0
             attendance_pct = round(attendance_pct)
     
             engagement_counts = {