INNER CODE UNIT · Python
main
tuangauss/DataScienceProjects · Python/flights_networkx.py:9
def main():
# download airport info data
airport_col = ['ID', 'Name', 'City', 'Country','IATA', 'ICAO', 'Lat', 'Long', 'Alt',
'Timezone', 'DST', 'Tz database time zone', 'type', 'source']
airport_df = pd.read_csv("https://raw.githubusercontent.com/jpatokal/openflights/master/data/airports.dat",
names = airport_col, index_col = 0)
# download flight routes data
route_cols = ['Airline', 'Airline ID', 'Source Airport', 'Source Airport ID',
'Dest Airport', 'Dest Airport ID', 'Codeshare', 'Stops', 'equipment']
routes_df = pd.read_csv("https://raw.githubusercontent.com/jpatokal/openflights/master/data/routes.dat",
names = route_cols)
#clean up data, change 'object' type to numeric and drops NaNs
routes_df['Source Airport ID'] = pd.to_numeric(routes_df['Source Airport ID'].astype(str), 'coerce')
routes_df['Dest Airport ID'] = pd.to_numeric(routes_df['Dest Airport ID'].astype(str), 'coerce')
routes_df = routes_df.dropna(subset=["Source Airport ID", "Dest Airport ID"])