data/area_based/6sc_glob.py

def true_code():
    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")
    
    state_avg_pm25 = main_data.groupby('state')['PM2.5'].mean().reset_index()
    merged_df = state_avg_pm25.merge(states_data, on='state', how='inner')
    merged_df['pm25_per_sqkm'] = merged_df['PM2.5'] / merged_df['area (km2)']
    highest_pm25_state = merged_df.loc[merged_df['pm25_per_sqkm'].idxmax(), 'state']
    
    print(highest_pm25_state)

true_code()