data-generate.py

import csv
import random
from datetime import datetime, timedelta

# 75 unique first names
first_names = [
    "Aaron","Abel","Abigail","Adam","Adrian","Aiden","Alan","Albert","Alex","Alexander",
    "Alice","Alicia","Allan","Amelia","Amy","Andrea","Andrew","Angela","Anna","Anthony",
    "Arthur","Ashley","Austin","Barbara","Benjamin","Betty","Beverly","Blake","Brandon","Brian",
    "Brianna","Bruce","Bryan","Caleb","Cameron","Carl","Carol","Caroline","Catherine","Charles",
    "Charlotte","Cheryl","Christian","Christina","Christopher","Claire","Clara","Colin","Connor","Craig",
    "Daisy","Daniel","Danielle","David","Deborah","Dennis","Diana","Diane","Dominic","Donna",
    "Dylan","Edward","Elizabeth","Emily","Emma","Eric","Ethan","Evelyn","Felix","Fiona",
    "Francis","Frank","Gabriel","Gavin","George","Grace","Hannah"
]

# 75 unique last names
last_names = [
    "Adams","Allen","Anderson","Bailey","Baker","Barnes","Bell","Bennett","Brooks","Brown",
    "Bryant","Campbell","Carter","Clark","Collins","Cook","Cooper","Cox","Davis","Diaz",
    "Edwards","Evans","Flores","Foster","Garcia","Gonzalez","Gray","Green","Griffin","Hall",
    "Harris","Hayes","Henderson","Hernandez","Hill","Howard","Hughes","Jackson","James","Jenkins",
    "Johnson","Jones","Kelly","King","Lee","Lewis","Long","Lopez","Martin","Martinez",
    "Miller","Mitchell","Moore","Morgan","Murphy","Nelson","Parker","Perez","Perry","Peterson",
    "Powell","Price","Ramirez","Reed","Richardson","Rivera","Roberts","Robinson","Rodriguez","Ross",
    "Sanchez","Scott","Smith","Stewart","Taylor","Thomas","Thompson","Torres","Turner","Walker",
    "Ward","Washington","Watson","White","Williams","Wilson","Wood"
]

records = 5000
output_file = "data.csv"

# Shuffle the combinations to avoid sequential patterns
combinations = [(f, l) for f in first_names for l in last_names]
random.shuffle(combinations)

with open(output_file, mode='w', newline='') as file:
    writer = csv.writer(file)
    writer.writerow(["id", "name", "ssn", "dob", "card", "exp"])  # header

    for i in range(records):
        first, last = combinations[i]
        name = f"{first} {last}"

        ssn = f"{random.randint(100,999)}-{random.randint(10,99)}-{random.randint(1000,9999)}"
        dob = f"{(datetime.now() - timedelta(days=random.randint(0, 80*365))).strftime('%m-%d-%Y')}"
        card = f"{random.randint(1000,9999)}-{random.randint(1000,9999)}-{random.randint(1000,9999)}-{random.randint(1000,9999)}"
        exp = f"{(datetime.now() + timedelta(days=random.randint(1, 730))).strftime('%m/%Y')}"
        writer.writerow([i + 1, name, ssn, dob, card, exp])

print(f"Generated {records} records in {output_file}")