cities_without_airports

gistfile1.txt

# Code by chatgpt
# Cities database:
# https://simplemaps.com/static/data/world-cities/basic/simplemaps_worldcities_basicv1.76.zip
# (Needs to be unzipped -- copy worldcities.csv to the same directory)

# Airports database:
# https://davidmegginson.github.io/ourairports-data/airports.csv

import pandas as pd
import numpy as np
from sklearn.neighbors import BallTree

pd.set_option('display.max_rows', None)  # add this line to display all rows
SOME_THRESHOLD=100

def load_data(file):
    df = pd.read_csv(file)
    return df

def find_furthest_metros(metro_data, airport_data):
    airport_data = airport_data[airport_data['scheduled_service'] == 'yes']
    metro_data = metro_data[metro_data['population'] > 100000]

    # Convert latitude and longitude to radians for BallTree
    metro_coords = np.radians(metro_data[['lat', 'lng']])
    airport_coords = np.radians(airport_data[['latitude_deg', 'longitude_deg']])

    # Construct a BallTree for efficient spatial look-ups
    tree = BallTree(airport_coords)

    # Query the BallTree for the distance to the nearest airport for each metro area
    distances, indices = tree.query(metro_coords, k=1)

    # Convert distances (which are in radians) to kilometers
    earth_radius = 6371  # approximate radius of earth in km
    distances_in_km = distances * earth_radius

    # Add distances to metro_data DataFrame
    metro_data['distance_to_nearest_airport'] = distances_in_km

    # Filter metro_data for those cities furthest from an airport
    furthest_metros = metro_data[metro_data['distance_to_nearest_airport'] > SOME_THRESHOLD]

    return furthest_metros[['city_ascii', 'country', 'population', 'distance_to_nearest_airport']]

def main():
    metro_data = load_data('worldcities.csv')
    airport_data = load_data('airports.csv')
    furthest_metros = find_furthest_metros(metro_data, airport_data)
    # Sort by 'distance_to_nearest_airport' in descending order before printing
    furthest_metros_sorted = furthest_metros.sort_values(by='distance_to_nearest_airport', ascending=False)
    print(furthest_metros_sorted.to_string(index=False))  # print without index column

if __name__ == '__main__':
    main()