create_regression_sample.py

import pandas as pd
import numpy as np

def create_regression_sample():
    np.random.seed(42)
    n = 200
    
    data = {
        'id': range(1001, 1001 + n),
        'listing_date': pd.date_range(start='2023-01-01', periods=n, freq='D').strftime('%Y-%m-%d'),
        'square_feet': np.random.randint(500, 5000, n),
        'bedrooms': np.random.randint(1, 6, n),
        'bathrooms': np.random.randint(1, 4, n),
        'neighborhood': np.random.choice(['Downtown', 'Suburbs', 'Westside', 'Eastside'], n),
        'price': []
    }
    
    # Simple pricing formula + noise
    for i in range(n):
        base = data['square_feet'][i] * 150 + data['bedrooms'][i] * 50000 + data['bathrooms'][i] * 30000
        noise = np.random.normal(0, 15000)
        data['price'].append(int(base + noise))
        
    df = pd.DataFrame(data)
    df.to_csv('Housing_Price_Sample.csv', index=False)
    print("Created Housing_Price_Sample.csv")

if __name__ == "__main__":
    create_regression_sample()