data/area_based/ud7do2gk.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_avg_pm10 = main_data.groupby('state')['PM10'].mean().reset_index()
    merged_data = pd.merge(state_avg_pm10, states_data, on='state')
    merged_data['pm10_per_capita'] = (merged_data['PM10'] * merged_data['area (km2)']) / merged_data['population']
    max_state = merged_data.loc[merged_data['pm10_per_capita'].idxmax()]['state']
    
    print(max_state)

true_code()