■anond:20241010082411

https://www.geonames.org から取れる、人口500人以上の都市の名前に限定すると、

Santa Maria Magdalena Cahuacan

が10文字の `a` を含んで最大。

import logging
import tempfile
import zipfile

from collections import Counter

import httpx

FILE_NAME_BASE = 'cities500'
GEONAME_FIELDS = (
    'geoname_id',
    'name',
    'ascii_name',
    'alternate_names',
    'latitude',
    'longitude',
    'feature_class',
    'feature_code',
    'country_code',
    'cc2',
    'admin1_code',
    'admin2_code',
    'admin3_code',
    'admin4_code',
    'population',
    'elevation',
    'dem',
    'timezone',
    'modification_date',
)

def retrieve_cities():
    """Retrieve city names from a remote server."""
    response = httpx.get(f'https://download.geonames.org/export/dump/{FILE_NAME_BASE}.zip')
    response.raise_for_status()

    tmpdir = tempfile.TemporaryDirectory()
    with open(tmpdir.name + f'/{FILE_NAME_BASE}.zip', 'wb') as f:
        f.write(response.content)
    with zipfile.ZipFile(tmpdir.name + f'/{FILE_NAME_BASE}.zip', 'r') as z:
        z.extractall(tmpdir.name)
    with open(tmpdir.name + f'/{FILE_NAME_BASE}.txt', 'r') as f:
        for line in f:
            yield line.split('\t')


def count_characters(to_check='ascii_name', filter_func=lambda _: True):
    """Count characters in city names."""
    cities = {}
    for city_fields in retrieve_cities():
        city = dict(zip(GEONAME_FIELDS, city_fields))
        if not filter_func(city):
            continue
        counter = Counter()
        for c in city[to_check]:
            counter[c] += 1
        cities[city['geoname_id']] = {'characters': counter, 'city': city}
    return cities


def count_chars_of_city_names(cities, char=None):
    """Find the city with the most occurrences of a given character."""
    cities_by_char_count = {}
    max_count = 0
    max_count_char = None
    for city_id, data in cities.items():
        if 'characters' not in data or not data['characters']:
            logging.debug(f'No characters found for city {city_id}', data)
            continue

        count = 0
        if char and char in data['characters']:
            count = data['characters'][char]

            cities_by_char_count.setdefault(count, []).append(data)
        elif char is None:
            most_common = data['characters'].most_common(1)[0]
            char, count = most_common
            cities_by_char_count.setdefault(count, []).append(data)

        if count > max_count:
            max_count = count
            max_count_char = char
            cities_by_char_count.setdefault(count, []).append(data)
    return cities_by_char_count.get(max_count, []), max_count_char


def not_contain_invalid_chars(city):
    return (
            '(' not in city.get('ascii_name', '')
            and '/' not in city.get('ascii_name', '')
    )


def main():
    cities = count_characters(filter_func=not_contain_invalid_chars)
    for char in 'abcdefghijklmnopqrstuvwxyz':
        cities_counted, char = count_chars_of_city_names(cities, char)
        max_count = cities_counted[0]['characters'][char]
        print(f'The character "{char}" appears the most ({max_count} times) in the following cities:')
        for city in cities_counted:
            print("\t", city['city']['ascii_name'])

if __name__ == "__main__":
    main()

Permalink | 記事への反応(0) | 22:36

ツイートシェア