data/area_based/fpta7la6.py

def true_code():
    import numpy as np
    import pandas as pd
    main_data = pd.read_csv("raw_data/main_data.csv")
    main_data['Timestamp'] = pd.to_datetime(main_data['Timestamp'])
    states_data = pd.read_csv("raw_data/State_data.csv")
    ncap_funding_data = pd.read_csv("raw_data/NCAP_Funding.csv")
    ncap_funding_data.replace('-', np.nan, inplace=True)
    ncap_funding_data['Amount released during FY 2019-20'] = ncap_funding_data['Amount released during FY 2019-20'].astype('float64')
    ncap_funding_data['Amount released during FY 2020-21'] = ncap_funding_data['Amount released during FY 2020-21'].astype('float64')
    ncap_funding_data['Amount released during FY 2021-22'] = ncap_funding_data['Amount released during FY 2021-22'].astype('float64')
    ncap_funding_data['Utilisation as on June 2022'] = ncap_funding_data['Utilisation as on June 2022'].astype('float64')
    
    state_pm25_avg = main_data.groupby('state')['PM2.5'].mean().reset_index()
    state_pm25_avg = state_pm25_avg.sort_values('PM2.5', ascending=False)
    top_5_polluted_states = state_pm25_avg.head(5)['state'].tolist()
    top_5_states_area = states_data[states_data['state'].isin(top_5_polluted_states)]
    max_area_state = top_5_states_area.loc[top_5_states_area['area (km2)'].idxmax()]['state']
    print(max_area_state)

true_code()