Data Generation

import csv
import random
from faker import Faker

fake = Faker()

departments = ["Engineering", "Marketing", "Sales", "HR", "Finance", "IT", "Support", "Legal"]
salary_ranges = {
    "Engineering": (60000, 120000),
    "Marketing": (50000, 100000),
    "Sales": (45000, 90000),
    "HR": (50000, 95000),
    "Finance": (55000, 110000),
    "IT": (60000, 115000),
    "Support": (40000, 80000),
    "Legal": (65000, 125000)
}

employee_id = 1

for file_index in range(1, 17):
    filename = f"employees_{file_index}.csv"
    with open(filename, mode='w', newline='') as file:
        writer = csv.writer(file)
        writer.writerow(["EmployeeID", "LastName", "FirstName", "Department", "Salary"])

        for _ in range(1000):
            dept = random.choice(departments)
            salary = round(random.uniform(*salary_ranges[dept]), 2)
            writer.writerow([
                employee_id,
                fake.last_name(),
                fake.first_name(),
                dept,
                salary
            ])
            employee_id += 1

print("✅ Done! Check the notebook folder for 16 CSV files.")