data/population_based/pbfqchiw.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")
    
    data_2023 = main_data[main_data['Timestamp'].dt.year == 2023]
    state_pm25_avg = data_2023.groupby('state')['PM2.5'].mean().reset_index()
    merged_df = state_pm25_avg.merge(states_data, on='state',how='inner')
    merged_df['per_capita_pm25'] = (merged_df['PM2.5'] / merged_df['population']) * 1000000
    
    sorted_df = merged_df.sort_values('per_capita_pm25', ascending=False)
    fifth_most_polluted = sorted_df.iloc[4]['state']
    
    print(fifth_most_polluted)

true_code()