Copilot Python Excel customer churn dataset

copilot-python-excel-customer-churn-dataset.py

import pandas as pd
import numpy as np
from faker import Faker

# Set random seed for reproducibility
np.random.seed(1234)

# Initialize Faker instance with seed
fake = Faker(seed=1234)

# Generate customer data
n_customers = 5000
customer_ids = range(1, n_customers + 1)

# Generate normally distributed ages
ages = np.random.normal(loc=35, scale=10, size=n_customers)

# Generate uniformly distributed tenures
tenures = np.random.randint(low=1, high=73, size=n_customers)

# Generate normally distributed monthly charges
monthly_charges = np.random.normal(loc=70, scale=20, size=n_customers)

# Calculate total charges
total_charges = monthly_charges * tenures

# Generate churn (0 or 1) with a probability of 0.2
churn_prob = 0.2
churn = np.random.choice([0, 1], size=n_customers, p=[1 - churn_prob, churn_prob])

# Create DataFrame
customer_df = pd.DataFrame({
    'Customer ID': customer_ids,
    'Age': ages,
    'Tenure': tenures,
    'Monthly Charges': monthly_charges,
    'Total Charges': total_charges,
    'Churn': churn
})

# Save to Excel workbook
customer_df.to_excel('customer_churn.xlsx', index=False)
print("Synthetic dataset saved to 'customer_churn.xlsx'")