read_names.py

import csv
from itertools import islice

import Levenshtein

# Why are people named Dante and Deante
BAD_DISTANCE = 3

names = [
    "Ashley", "Grace", "Isaac", "Hannah", "James", "Olivia", "Noah", "Emma",
    "Liam", "Ava", "Ethan", "Mia", "Lucas", "Sofia", "Mason", "Amelia",
    "Logan", "Harper", "Elijah", "Evelyn", "Henry", "Abigail", "Jack", "Ella",
    "Leo", "Scarlett", "Owen", "Luna", "Caleb", "Nora", "Miles", "Chloe",
]
initial_len = len(names)

with open('./girl_boy_names_1990.csv') as file:
    reader = csv.reader(file)
    for row in islice(reader, 1, None):
        for name in row[1:]:
            names.append(name)

# remove names that are too similar
filtered_names = names[:initial_len]
for name in names[initial_len:]:
    # Check other names for similarity
    accept = True
    for accepted_name in filtered_names:
        dist = Levenshtein.distance(accepted_name, name)
        if dist < BAD_DISTANCE:
            #print(f'bad: {accepted_name} > {name}')
            accept = False
            break

    if accept:
        filtered_names.append(name)

with open('./ace-id-names.txt', 'w+') as file:
    file.writelines(f'{x}\n' for x in filtered_names)