namegen.py

from names_dataset import NameDataset
import json

nd = NameDataset()
firsts = []
lasts = []

countries = ["GB", "US", "FR", "DE", "PT", "ES", "NL", "IT", "MX", "CO", "ZA", "US"]
for country in countries:
    print(country)

    names = nd.get_top_names(n=1000, country_alpha2=country)
    firsts.extend(names[country]["M"])
    firsts.extend(names[country]["F"])

    names = nd.get_top_names(n=2000, country_alpha2=country, use_first_names=False)
    lasts.extend(names[country])

firsts = list(set(filter(lambda n: not " " in n, firsts)))
lasts = list(set(filter(lambda n: not " " in n, lasts)))

print(f"Found {len(firsts)} first names")
with open("first.json", "w", encoding="utf_8") as f:
    f.write(json.dumps(firsts, ensure_ascii=False))

print(f"Found {len(lasts)} last names")
with open("last.json", "w", encoding="utf_8") as f:
    f.write(json.dumps(lasts, ensure_ascii=False))