Update data_processor.py

data_processor.py

@@ -117,9 +117,86 @@ class DataProcessor:
         else:
             return 'Unknown'
     
+    # def compute_student_metrics(self, df):
+    #     intervention_column = self.get_intervention_column(df)
+    #     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')]
+    
+    #     student_metrics = {}
+    #     for col in student_columns:
+    #         student_name = col.replace('Student Attendance [', '').replace(']', '').strip()
+    #         student_data = intervention_df[[col]].copy()
+    #         student_data[col] = student_data[col].fillna('Absent')
+    
+    #         attendance_values = student_data[col].apply(lambda x: 1 if self.classify_engagement(x) in [
+    #             self.ENGAGED_STR,
+    #             self.PARTIALLY_ENGAGED_STR,
+    #             self.NOT_ENGAGED_STR
+    #         ] else 0)
+    
+    #         sessions_attended = attendance_values.sum()
+    #         attendance_pct = (sessions_attended / intervention_sessions_held * 100) if intervention_sessions_held > 0 else 0
+    #         attendance_pct = round(attendance_pct)
+    
+    #         engagement_counts = {
+    #             self.ENGAGED_STR: 0,
+    #             self.PARTIALLY_ENGAGED_STR: 0,
+    #             self.NOT_ENGAGED_STR: 0,
+    #             'Absent': 0
+    #         }
+    
+    #         for x in student_data[col]:
+    #             classified_engagement = self.classify_engagement(x)
+    #             if classified_engagement in engagement_counts:
+    #                 engagement_counts[classified_engagement] += 1
+    #             else:
+    #                 engagement_counts['Absent'] += 1  # Count as Absent if not engaged
+    
+    #         total_sessions = sum(engagement_counts.values())
+            
+    #         engaged_pct = (engagement_counts[self.ENGAGED_STR] / total_sessions * 100) if total_sessions > 0 else 0
+    #         engaged_pct = round(engaged_pct)
+    
+    #         partially_engaged_pct = (engagement_counts[self.PARTIALLY_ENGAGED_STR] / total_sessions * 100) if total_sessions > 0 else 0
+    #         partially_engaged_pct = round(partially_engaged_pct)
+    
+    #         not_engaged_pct = (engagement_counts[self.NOT_ENGAGED_STR] / total_sessions * 100) if total_sessions > 0 else 0
+    #         not_engaged_pct = round(not_engaged_pct)
+    
+    #         absent_pct = (engagement_counts['Absent'] / total_sessions * 100) if total_sessions > 0 else 0
+    #         absent_pct = round(absent_pct)
+    
+    #         # Engagement percentage is based on Engaged and Partially Engaged sessions
+    #         engagement_pct = ((engagement_counts[self.ENGAGED_STR] + engagement_counts[self.PARTIALLY_ENGAGED_STR]) / total_sessions * 100) if total_sessions > 0 else 0
+    #         engagement_pct = round(engagement_pct)
+    
+    #         # Determine if the student attended ≥ 90% of sessions
+    #         attended_90 = "Yes" if attendance_pct >= 90 else "No"
+    
+    #         # Determine if the student was engaged ≥ 80% of the time
+    #         engaged_80 = "Yes" if engagement_pct >= 80 else "No"
+    
+    #         # Store metrics in the required order
+    #         student_metrics[student_name] = {
+    #             'Attended ≥ 90%': attended_90,
+    #             'Engagement ≥ 80%': engaged_80,
+    #             'Attendance (%)': attendance_pct,
+    #             'Engagement (%)': engagement_pct,
+    #             f'{self.ENGAGED_STR} (%)': engaged_pct,
+    #             f'{self.PARTIALLY_ENGAGED_STR} (%)': partially_engaged_pct,
+    #             f'{self.NOT_ENGAGED_STR} (%)': not_engaged_pct,
+    #             'Absent (%)': absent_pct
+    #         }
+    
+    #     # Create a DataFrame from student_metrics
+    #     student_metrics_df = pd.DataFrame.from_dict(student_metrics, orient='index').reset_index()
+    #     student_metrics_df.rename(columns={'index': 'Student'}, inplace=True)
+    #     return student_metrics_df
+
     def compute_student_metrics(self, df):
         intervention_column = self.get_intervention_column(df)
-        intervention_df = df[df[intervention_column].str.strip().str.lower().isin(self.YES_RESPONSES)]  # Modified line
+        intervention_df = df[df[intervention_column].str.strip().str.lower().isin(self.YES_RESPONSES)]
         intervention_sessions_held = len(intervention_df)
         student_columns = [col for col in df.columns if col.startswith('Student Attendance')]
     
@@ -129,55 +206,70 @@ class DataProcessor:
             student_data = intervention_df[[col]].copy()
             student_data[col] = student_data[col].fillna('Absent')
     
-            attendance_values = student_data[col].apply(lambda x: 1 if self.classify_engagement(x) in [
-                self.ENGAGED_STR,
-                self.PARTIALLY_ENGAGED_STR,
-                self.NOT_ENGAGED_STR
-            ] else 0)
+            # Classify each entry
+            student_data['Engagement'] = student_data[col].apply(self.classify_engagement)
+    
+            # Calculate attendance
+            attendance_values = student_data['Engagement'].apply(
+                lambda x: 1 if x in [self.ENGAGED_STR, self.PARTIALLY_ENGAGED_STR, self.NOT_ENGAGED_STR] else 0
+            )
     
             sessions_attended = attendance_values.sum()
             attendance_pct = (sessions_attended / intervention_sessions_held * 100) if intervention_sessions_held > 0 else 0
             attendance_pct = round(attendance_pct)
     
+            # Engagement counts (excluding 'Absent')
             engagement_counts = {
                 self.ENGAGED_STR: 0,
                 self.PARTIALLY_ENGAGED_STR: 0,
-                self.NOT_ENGAGED_STR: 0,
-                'Absent': 0
+                self.NOT_ENGAGED_STR: 0
             }
     
-            for x in student_data[col]:
-                classified_engagement = self.classify_engagement(x)
-                if classified_engagement in engagement_counts:
-                    engagement_counts[classified_engagement] += 1
-                else:
-                    engagement_counts['Absent'] += 1  # Count as Absent if not engaged
+            # Count the engagement types, excluding 'Absent'
+            for x in student_data['Engagement']:
+                if x in engagement_counts:
+                    engagement_counts[x] += 1
+                # 'Absent' is not counted in engagement_counts
     
-            total_sessions = sum(engagement_counts.values())
-            
-            engaged_pct = (engagement_counts[self.ENGAGED_STR] / total_sessions * 100) if total_sessions > 0 else 0
+            total_present_sessions = sum(engagement_counts.values())
+    
+            engaged_pct = (
+                (engagement_counts[self.ENGAGED_STR] / total_present_sessions * 100)
+                if total_present_sessions > 0 else 0
+            )
             engaged_pct = round(engaged_pct)
     
-            partially_engaged_pct = (engagement_counts[self.PARTIALLY_ENGAGED_STR] / total_sessions * 100) if total_sessions > 0 else 0
+            partially_engaged_pct = (
+                (engagement_counts[self.PARTIALLY_ENGAGED_STR] / total_present_sessions * 100)
+                if total_present_sessions > 0 else 0
+            )
             partially_engaged_pct = round(partially_engaged_pct)
     
-            not_engaged_pct = (engagement_counts[self.NOT_ENGAGED_STR] / total_sessions * 100) if total_sessions > 0 else 0
+            not_engaged_pct = (
+                (engagement_counts[self.NOT_ENGAGED_STR] / total_present_sessions * 100)
+                if total_present_sessions > 0 else 0
+            )
             not_engaged_pct = round(not_engaged_pct)
     
-            absent_pct = (engagement_counts['Absent'] / total_sessions * 100) if total_sessions > 0 else 0
-            absent_pct = round(absent_pct)
-    
             # Engagement percentage is based on Engaged and Partially Engaged sessions
-            engagement_pct = ((engagement_counts[self.ENGAGED_STR] + engagement_counts[self.PARTIALLY_ENGAGED_STR]) / total_sessions * 100) if total_sessions > 0 else 0
+            engagement_pct = (
+                ((engagement_counts[self.ENGAGED_STR] + engagement_counts[self.PARTIALLY_ENGAGED_STR]) / total_present_sessions * 100)
+                if total_present_sessions > 0 else 0
+            )
             engagement_pct = round(engagement_pct)
     
+            # Absent percentage (for reference, not used in engagement calculation)
+            absent_sessions = student_data['Engagement'].value_counts().get('Absent', 0)
+            absent_pct = (absent_sessions / intervention_sessions_held * 100) if intervention_sessions_held > 0 else 0
+            absent_pct = round(absent_pct)
+    
             # Determine if the student attended ≥ 90% of sessions
             attended_90 = "Yes" if attendance_pct >= 90 else "No"
     
             # Determine if the student was engaged ≥ 80% of the time
             engaged_80 = "Yes" if engagement_pct >= 80 else "No"
     
-            # Store metrics in the required order
+            # Store metrics
             student_metrics[student_name] = {
                 'Attended ≥ 90%': attended_90,
                 'Engagement ≥ 80%': engaged_80,
@@ -193,7 +285,7 @@ class DataProcessor:
         student_metrics_df = pd.DataFrame.from_dict(student_metrics, orient='index').reset_index()
         student_metrics_df.rename(columns={'index': 'Student'}, inplace=True)
         return student_metrics_df
-
+    
     def compute_average_metrics(self, student_metrics_df):
         # Calculate the attendance and engagement average percentages across students
         attendance_avg_stats = student_metrics_df['Attendance (%)'].mean()  # Average attendance percentage