data_processor.py

# import pandas as pd
# import os
# import re
# from huggingface_hub import InferenceClient
# # from graphviz import Digraph

# class DataProcessor:
#     INTERVENTION_COLUMN = 'Did the intervention happen today?'
#     ENGAGED_STR = 'Engaged (Respect, Responsibility, Effort)'
#     PARTIALLY_ENGAGED_STR = 'Partially Engaged (about 50%)'
#     NOT_ENGAGED_STR = 'Not Engaged (less than 50%)'

#     def __init__(self, student_metrics_df=None):
#         self.hf_api_key = os.getenv('HF_API_KEY')
#         if not self.hf_api_key:
#             raise ValueError("HF_API_KEY not set in environment variables")
#         self.client = InferenceClient(api_key=self.hf_api_key)
#         self.student_metrics_df = student_metrics_df

#     def read_excel(self, uploaded_file):
#         return pd.read_excel(uploaded_file)

#     def format_session_data(self, df):
#         # Look for "Date of Session" or "Date" column
#         date_column = next((col for col in df.columns if col in ["Date of Session", "Date"]), None)
#         if date_column:
#             df[date_column] = pd.to_datetime(df[date_column], errors='coerce').dt.date
#         else:
#             print("Warning: Neither 'Date of Session' nor 'Date' column found in the dataframe.")
        
#         df['Timestamp'] = self.safe_convert_to_datetime(df['Timestamp'], '%I:%M %p')
#         df['Session Start Time'] = self.safe_convert_to_time(df['Session Start Time'], '%I:%M %p')
#         df['Session End Time'] = self.safe_convert_to_time(df['Session End Time'], '%I:%M %p')
#         return df

#     def safe_convert_to_time(self, series, format_str='%I:%M %p'):
#         try:
#             converted = pd.to_datetime(series, format='%H:%M:%S', errors='coerce')
#             if format_str:
#                 return converted.dt.strftime(format_str)
#             return converted
#         except Exception as e:
#             print(f"Error converting series to time: {e}")
#             return series

#     def safe_convert_to_datetime(self, series, format_str=None):
#         try:
#             converted = pd.to_datetime(series, errors='coerce')
#             if format_str:
#                 return converted.dt.strftime(format_str)
#             return converted
#         except Exception as e:
#             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 compute_intervention_statistics(self, df):
#         total_days = len(df)
#         sessions_held = df[self.INTERVENTION_COLUMN].str.strip().str.lower().eq('yes').sum()
#         intervention_frequency = (sessions_held / total_days) * 100 if total_days > 0 else 0
#         return pd.DataFrame({
#             'Intervention Dosage (%)': [round(intervention_frequency, 0)],
#             'Intervention Sessions Held': [sessions_held],
#             'Intervention Sessions Not Held': [total_days - sessions_held],
#             'Total Number of Days Available': [total_days]
#         })

#     def compute_student_metrics(self, df):
#         intervention_df = df[df[self.INTERVENTION_COLUMN].str.strip().str.lower() == 'yes']
#         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 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 = {
#                 'Engaged': 0,
#                 'Partially Engaged': 0,
#                 'Not Engaged': 0,
#                 'Absent': 0
#             }
    
#             for x in student_data[col]:
#                 if x == self.ENGAGED_STR:
#                     engagement_counts['Engaged'] += 1
#                 elif x == self.PARTIALLY_ENGAGED_STR:
#                     engagement_counts['Partially Engaged'] += 1
#                 elif x == self.NOT_ENGAGED_STR:
#                     engagement_counts['Not Engaged'] += 1
#                 else:
#                     engagement_counts['Absent'] += 1  # Count as Absent if not engaged
    
#             # Calculate percentages for engagement states
#             total_sessions = sum(engagement_counts.values())
            
#             # Engagement (%)
#             engagement_pct = (engagement_counts['Engaged'] / total_sessions * 100) if total_sessions > 0 else 0
#             engagement_pct = round(engagement_pct)
    
#             engaged_pct = (engagement_counts['Engaged'] / total_sessions * 100) if total_sessions > 0 else 0
#             engaged_pct = round(engaged_pct)
    
#             partially_engaged_pct = (engagement_counts['Partially Engaged'] / total_sessions * 100) if total_sessions > 0 else 0
#             partially_engaged_pct = round(partially_engaged_pct)
    
#             not_engaged_pct = (engagement_counts['Not Engaged'] / 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)
    
#             # 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 engaged_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,
#                 # 'Attendance #': sessions_attended,
#                 'Engagement (%)': engagement_pct,
#                 'Engaged (%)': engaged_pct,
#                 'Partially Engaged (%)': partially_engaged_pct,
#                 'Not Engaged (%)': 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_average_metrics(self, student_metrics_df):
#         # Calculate the attendance and engagement average percentages across students
#         attendance_avg_stats = student_metrics_df['Attendance (%)'].mean()  # Calculate the average attendance percentage
#         engagement_avg_stats = student_metrics_df['Engagement (%)'].mean()  # Calculate the average engagement percentage
        
#         # Round the averages to make them whole numbers
#         attendance_avg_stats = round(attendance_avg_stats)
#         engagement_avg_stats = round(engagement_avg_stats)
        
#         return attendance_avg_stats, engagement_avg_stats
    
#     def evaluate_student(self, row, attendance_threshold=90, engagement_threshold=80):
#         if row["Attended ≥ 90%"] == "No":
#             return "Address Attendance"
#         elif row["Engagement ≥ 80%"] == "No":
#             return "Address Engagement"
#         return "Consider barriers, fidelity, and progress monitoring"

        

import re
import pandas as pd
import os
from huggingface_hub import InferenceClient

class DataProcessor:
    INTERVENTION_COLUMN_OPTIONS = [
        'Did the intervention happen today?',
        'Did the intervention take place today?'
    ]
    ENGAGED_STR = 'Engaged'
    PARTIALLY_ENGAGED_STR = 'Partially Engaged'
    NOT_ENGAGED_STR = 'Not Engaged'

    def __init__(self, student_metrics_df=None):
        self.hf_api_key = os.getenv('HF_API_KEY')
        if not self.hf_api_key:
            raise ValueError("HF_API_KEY not set in environment variables")
        self.client = InferenceClient(api_key=self.hf_api_key)
        self.student_metrics_df = student_metrics_df
        self.intervention_column = None  # Will be set when processing data

    def read_excel(self, uploaded_file):
        return pd.read_excel(uploaded_file)

    def format_session_data(self, df):
        date_column = next((col for col in df.columns if col in ["Date of Session", "Date"]), None)
        if date_column:
            df[date_column] = pd.to_datetime(df[date_column], errors='coerce').dt.date
        else:
            print("Warning: Neither 'Date of Session' nor 'Date' column found in the dataframe.")
        
        df['Timestamp'] = self.safe_convert_to_datetime(df['Timestamp'], '%I:%M %p')
        df['Session Start Time'] = self.safe_convert_to_time(df['Session Start Time'], '%I:%M %p')
        df['Session End Time'] = self.safe_convert_to_time(df['Session End Time'], '%I:%M %p')
        return df

    def safe_convert_to_time(self, series, format_str='%I:%M %p'):
        try:
            converted = pd.to_datetime(series, format='%H:%M:%S', errors='coerce')
            if format_str:
                return converted.dt.strftime(format_str)
            return converted
        except Exception as e:
            print(f"Error converting series to time: {e}")
            return series

    def safe_convert_to_datetime(self, series, format_str=None):
        try:
            converted = pd.to_datetime(series, errors='coerce')
            if format_str:
                return converted.dt.strftime(format_str)
            return converted
        except Exception as e:
            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 find_intervention_column(self, df):
        for column in self.INTERVENTION_COLUMN_OPTIONS:
            if column in df.columns:
                self.intervention_column = column
                return column
        raise ValueError("No intervention column found in the dataframe.")

    def get_intervention_column(self, df):
        if self.intervention_column is None:
            self.intervention_column = self.find_intervention_column(df)
        return self.intervention_column

    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()
        intervention_frequency = (sessions_held / total_days) * 100 if total_days > 0 else 0
        return pd.DataFrame({
            'Intervention Dosage (%)': [round(intervention_frequency, 0)],
            'Intervention Sessions Held': [sessions_held],
            'Intervention Sessions Not Held': [total_days - sessions_held],
            'Total Number of Days Available': [total_days]
        })

    def classify_engagement(self, engagement_str):
        engagement_str = str(engagement_str).lower()
        if engagement_str.startswith(self.ENGAGED_STR.lower()):
            return self.ENGAGED_STR
        elif engagement_str.startswith(self.PARTIALLY_ENGAGED_STR.lower()):
            return self.PARTIALLY_ENGAGED_STR
        elif engagement_str.startswith(self.NOT_ENGAGED_STR.lower()):
            return self.NOT_ENGAGED_STR
        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() == 'yes']
        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_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
        engagement_avg_stats = student_metrics_df['Engagement (%)'].mean()  # Average engagement percentage
        
        # Round the averages to whole numbers
        attendance_avg_stats = round(attendance_avg_stats)
        engagement_avg_stats = round(engagement_avg_stats)
        
        return attendance_avg_stats, engagement_avg_stats
    
    def evaluate_student(self, row, attendance_threshold=90, engagement_threshold=80):
        if row["Attended ≥ 90%"] == "No":
            return "Address Attendance"
        elif row["Engagement ≥ 80%"] == "No":
            return "Address Engagement"
        else:
            return "Consider barriers, fidelity, and progress monitoring"