data_processor.py

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

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):
        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)

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

    def format_session_data(self, df):
        df['Date of Session'] = self.safe_convert_to_datetime(df['Date of Session'], '%m/%d/%Y')
        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')
        df = df[['Date of Session', 'Timestamp'] + [col for col in df.columns if col not in ['Date of Session', 'Timestamp']]]
        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)
                    name_parts = name.split()
                    if len(name_parts) == 1:
                        initials = name_parts[0][0]
                    else:
                        initials = ''.join([part[0] for part in name_parts])
                    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()
        sessions_not_held = df[self.INTERVENTION_COLUMN].str.strip().str.lower().eq('no').sum()
        intervention_frequency = (sessions_held / total_days) * 100 if total_days > 0 else 0
        intervention_frequency = round(intervention_frequency, 0)

        stats = {
            'Intervention Frequency (%)': [intervention_frequency],
            'Intervention Sessions Held': [sessions_held],
            'Intervention Sessions Not Held': [sessions_not_held],
            'Total Number of Days Available': [total_days]
        }
        return pd.DataFrame(stats)

    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

            total_sessions = sum(engagement_counts.values())
            engagement_pct = (engagement_counts['Engaged'] / total_sessions * 100) if total_sessions > 0 else 0
            engagement_pct = round(engagement_pct)

            student_metrics[student_name] = {
                'Attendance (%)': attendance_pct,
                'Attendance #': sessions_attended,
                'Engagement (%)': engagement_pct
            }

        return pd.DataFrame.from_dict(student_metrics, orient='index').reset_index().rename(columns={'index': 'Student'})

    def compute_average_metrics(self, student_metrics_df):
        attendance_avg_stats = student_metrics_df['Attendance (%)'].mean()
        engagement_avg_stats = student_metrics_df['Engagement (%)'].mean()
        return round(attendance_avg_stats), round(engagement_avg_stats)