fake customer data

fake_customer_data.py

import polars as pl
from faker import Faker
import random

# Initialize the Faker instance
fake = Faker()

# Define the number of unique customers and the total number of records
num_customers = 100
num_records = 1000

# Generate unique customer names
customer_names = [fake.name() for _ in range(num_customers)]

# Generate the fake data
data = {
    'shipment_id': [fake.uuid4() for _ in range(num_records)],
    'customer_id': [random.choice(customer_names) for _ in range(num_records)],
    'shipment_created_date_time': [fake.date_time_between(start_date='-2y', end_date='now') for _ in range(num_records)]
}

# Create a Polars DataFrame
df = pl.DataFrame(data)

# Display the first few rows of the DataFrame
print(df.head())

# Optionally, save the DataFrame to a CSV file
df.write_csv('fake_shipments.csv')