#!/usr/bin/env python
# Script to verify the enhanced group statistics

import pandas as pd
import os

def check_enhanced_group_stats():
    print("=== ENHANCED GROUP STATISTICS VERIFICATION ===")
    print()

    # Check if output directory exists
    if not os.path.exists('output'):
        print("Output directory not found!")
        return

    # Check if group_statistics.csv exists
    group_stats_path = os.path.join('output', 'group_statistics.csv')
    if not os.path.exists(group_stats_path):
        print(f"Group statistics file not found at {group_stats_path}")
        return

    # Load the enhanced group statistics
    group_stats_df = pd.read_csv(group_stats_path)
    
    print("Enhanced Group Statistics Columns:")
    print(list(group_stats_df.columns))
    print()

    # Verify the new columns exist
    required_columns = [
        'Total_Sensors_In_Group', 
        'Percentage_Monitoring_Points_Alarmed', 
        'Alarm_Time_Percentage'
    ]
    
    missing_columns = [col for col in required_columns if col not in group_stats_df.columns]
    if missing_columns:
        print(f"ERROR: Missing columns: {missing_columns}")
        return
    else:
        print("All required enhanced columns are present")
        print()

    # Display sample of the enhanced data
    print("Sample of Enhanced Group Statistics (Top 10 by Alarm Count):")
    print(group_stats_df[['Sensor_Group', 'Total_Alarm_Count', 'Unique_Sensors', 
                         'Total_Sensors_In_Group', 'Percentage_Monitoring_Points_Alarmed', 
                         'Alarm_Time_Percentage']].head(10))
    print()

    # Show some key statistics
    print("=== ENHANCED ANALYSIS SUMMARY ===")
    
    # Groups with highest percentage of monitoring points alarmed
    print("Top 5 groups with highest percentage of monitoring points that experienced alarms:")
    top_alarm_percent = group_stats_df.nlargest(5, 'Percentage_Monitoring_Points_Alarmed')[['Sensor_Group', 'Percentage_Monitoring_Points_Alarmed', 'Unique_Sensors', 'Total_Sensors_In_Group']]
    print(top_alarm_percent)
    print()

    # Groups with highest alarm time percentage
    print("Top 5 groups with highest percentage of time spent in alarm condition:")
    top_time_percent = group_stats_df.nlargest(5, 'Alarm_Time_Percentage')[['Sensor_Group', 'Alarm_Time_Percentage', 'Total_Duration', 'Total_Sensors_In_Group']]
    print(top_time_percent)
    print()

    # Groups with the most difference between total sensors and unique sensors that alarmed
    print("Groups with the highest number of total sensors but lower alarm activity:")
    group_stats_df['Sensors_Not_Alarming'] = group_stats_df['Total_Sensors_In_Group'] - group_stats_df['Unique_Sensors']
    top_inactive = group_stats_df.nlargest(5, 'Sensors_Not_Alarming')[['Sensor_Group', 'Sensors_Not_Alarming', 'Total_Sensors_In_Group', 'Unique_Sensors', 'Percentage_Monitoring_Points_Alarmed']]
    print(top_inactive)
    print()

    print("Enhanced group statistics analysis completed successfully!")
    print()
    print("New metrics added:")
    print("- Total_Sensors_In_Group: Total number of sensors in the group according to sensor report")
    print("- Percentage_Monitoring_Points_Alarmed: Percentage of sensors in the group that experienced alarms")
    print("- Alarm_Time_Percentage: Percentage of total possible sensor-time that was spent in alarm condition")

if __name__ == "__main__":
    check_enhanced_group_stats()