import pandas as pd
import glob
import os

main_df = pd.read_csv('../your_output_file.csv')

final_columns = main_df.columns.tolist()

def process_archetype_file(filepath):
    filename = os.path.basename(filepath)
    base_name = filename.replace('_Results.csv', '')
    parts = base_name.split('_', 1)
    usage = parts[0]
    vintage = parts[1] if len(parts) > 1 else ''

    df = pd.read_csv(filepath, encoding='latin-1')

    column_mapping = {
        'Heating Demand [kWh/m²]': 'Heating',
        'Cooling Demand [kWh/m²]': 'Cooling',
        'SHW Demand [kWh/m²]': 'DHW',
        'Electricity Demand [kWh/m²]': 'Equipment and lighting',
        'Superficie [m²]': 'Surface'
    }

    for old_col, new_col in column_mapping.items():
        if old_col in df.columns:
            df.rename(columns={old_col: new_col}, inplace=True)

    if 'Date/Time' in df.columns:
        df['Date/Time'] = pd.to_datetime(df['Date/Time'], errors='coerce')
        df.rename(columns={'Date/Time': 'Timestamps'}, inplace=True)
    else:
        pass

    if 'Type_of_building' not in df.columns:
        df['Type_of_building'] = ''
    if 'Equipment' not in df.columns:
        df['Equipment'] = 0
    if 'Lighting' not in df.columns:
        df['Lighting'] = 0
    if 'Heating' not in df.columns:
        df['Heating'] = 0
    if 'Cooling' not in df.columns:
        df['Cooling'] = 0
    if 'DHW' not in df.columns:
        df['DHW'] = 0
    if 'Equipment and lighting' not in df.columns:
        df['Equipment and lighting'] = 0
    if 'Surface' not in df.columns:
        df['Surface'] = 0
    if 'Timestamps' not in df.columns:
        df['Timestamps'] = pd.NaT

    df['Usage'] = usage
    df['Vintage'] = vintage

    df = df[final_columns]

    return df


for filepath in glob.glob("./data/*_Results.csv"):
    archetype_df = process_archetype_file(filepath)
    main_df = pd.concat([main_df, archetype_df], ignore_index=True)

main_df.to_csv("energy_demand_data_combined.csv", index=False)