story_bike_share_clean_4.py

# Separate the stations without station IDs
no_ids = stations[stations['station_id'].isnull()]
for idx, miss in no_ids.iterrows():
    max_score = 0
    
    # Compare the similarity of the station without ID to each station in the API data
    for i, exist in bikeshare_stations[['station_id', 'name']].iterrows():
        score = fuzz.ratio(miss['name'], exist['name'])
        
        if score > 80 and score > max_score:
            max_score = score
            no_ids.at[idx, 'station_id'] = exist['station_id']
    
    # Warn if the station was not able to be matched
    if max_score <= 80:
        print('WARN: {0} station could not be matched to an existing station'.format(miss['name']))
        
# Remove all stations that were not matched
no_ids = no_ids.dropna()